BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Robotics Institute Carnegie Mellon University - ECPv6.15.12.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ri.cmu.edu
X-WR-CALDESC:Events for Robotics Institute Carnegie Mellon University
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20170312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20171105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20181104T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250415T100000
DTEND;TZID=America/New_York:20250415T110000
DTSTAMP:20260918T040935
CREATED:20250324T205411Z
LAST-MODIFIED:20250324T205758Z
UID:145859-1744711200-1744714800@www.ri.cmu.edu
SUMMARY:Faculty Candidate Talk: Jason Ma
DESCRIPTION:Title: Internet Supervision for Robot Learning \nAbstract: The availability of internet-scale data has led to impressive large-scale AI models in various domains\, such as vision and language. For learning robot skills\, despite recent efforts in crowd-sourcing robot data\, robot-specific datasets remain orders of magnitude smaller. Rather than focusing on scaling robot data\, my research takes the alternative path of directly using available internet data and models as supervision for robots — in particular\, learning general feedback models for robot actions. Feedback can be relatively agnostic to robot embodiments\, applicable to various policy learning algorithms\, and as I will show\, can be learned even from exclusively non-robot data. I will present two complementary approaches in this talk. First\, I will present a novel reinforcement learning algorithm that can directly use in-the-wild human videos to learn value functions\, producing zero-shot dense rewards for manipulation tasks specified in images and texts. Second\, I will demonstrate how grounding large language models code search with simulator feedback enables automated reward design for sim-to-real transfer of complex robot skills\, such as a quadruped robot dog balancing on a yoga ball. \nBio: Jason Ma is a fifth-year PhD student at the University of Pennsylvania. His research interests span robot learning\, reinforcement learning\, and deep learning. His work has received Best Paper Finalist at ICRA 2024\, Top 10 NVIDIA Research Projects of 2023\, and covered by popular media such as the Economist\, Fox\, Yahoo\, and TechCrunch. Jason is supported by Apple Scholar in AI/ML PhD Fellowship as well as OpenAI Superalignment Fellowship.
URL:https://www.ri.cmu.edu/event/faculty-candidate-talk-jason-ma/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/03/Jason-Ma-headshot.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250409T100000
DTEND;TZID=America/New_York:20250409T110000
DTSTAMP:20260918T040935
CREATED:20250324T182034Z
LAST-MODIFIED:20250324T205717Z
UID:145852-1744192800-1744196400@www.ri.cmu.edu
SUMMARY:Faculty Candidate Talk: Carlo Sferrazza
DESCRIPTION:Title: The Path to Humanoid Intelligence \nAbstract:\nHumanoid robots represent the ideal physical embodiment to assist us in the diversity of our daily tasks and human-centric environments. Driven by substantial hardware advancements\, progress in artificial intelligence (AI)\, and a growing demand for adaptable automation\, this vision appears increasingly feasible.\nYet\, to date\, humanoid intelligence remains far from achieving its envisioned general-purpose capabilities. What sets it apart from other challenges in machine learning — and even within robotics?\nMy research seeks to address this question and ultimately aims to bridge the gap between humanoid AI and human intelligence. In this talk\, I outline two key strategies: (1) developing algorithms\, systems\, and architectures that leverage embodiment-aware priors and inductive biases to manage the high-dimensional complexity of humanoid robot learning\, and (2) harnessing multi-sensory feedback from the environment — such as vision\, touch\, and audio — to enable a unified\, versatile embodiment capable of effectively reasoning across a wide range of tasks. \nBio:\nCarmelo (Carlo) Sferrazza is a postdoctoral researcher at UC Berkeley\, working with Prof. Pieter Abbeel. His research focuses on advancing humanoid robots’ intelligence by incorporating priors\, inductive biases\, and multi-sensory feedback. Carlo obtained his Ph.D. from ETH Zurich under the supervision of Prof. Raffaello D’Andrea. During his doctoral research\, he worked on the design of vision-based\, data-driven tactile sensors\, and the applications of such sensors to robot control and dexterous manipulation. Carlo’s Ph.D. thesis was awarded the ETH Medal\, and in 2022\, he was selected as a Robotics Science and Systems Pioneer. He is also the recipient of an SNSF Postdoctoral Fellowship\, a Rising Star Award and a Best Paper Award at the IEEE International Conference on Soft Robotics\, and the 2017 ETEL Award. He frequently shares his research with the general public\, including presentations at events such as the WORLD.MINDS Annual Symposium and TEDxZurich.
URL:https://www.ri.cmu.edu/event/faculty-candidate-talk-carlo-sferrazza/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/03/Headshot-Carlo-Sferrazza.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250408T100000
DTEND;TZID=America/New_York:20250408T110000
DTSTAMP:20260918T040935
CREATED:20250326T185849Z
LAST-MODIFIED:20250326T190020Z
UID:145899-1744106400-1744110000@www.ri.cmu.edu
SUMMARY:Faculty Candidate Talk: Aja Carter
DESCRIPTION:Title: Paleorobotics: Design Principles 540 million years in the making \nAbstract:\nBioinspiration has provided key design insights in many fields\, particularly in robotics\, where there has been an explosion of interest in quadrupedal robot “dogs” and bipedal humanoid robots. However\, the designs prescribed by only considering living animals are a small subset of available designs; over 99% of all animal species that have ever lived are now extinct. Extinction events in Earth’s history unrelated to mechanical capability repeatedly occur over Geologic time\, arbitrarily wiping groups of animals and\, in turn\, successful\, informative biological designs. By only considering living animals\, we lose access to design insights only available when considering deep-time\, such as more explored regions of design space\, repeated design convergence\, or changes in design associated with new habitat occupancy. In this talk\, I will present work that covers two such evolutionary events: 1) spinal function in the first large animals capable of dynamic behaviors and 2) structural changes in forelimb structure during an environmental transition. I will relate the insights from these projects to more general challenges in design\, such as secondary uses for existing structures and developing novel robot designs. Finally\, I will outline how these two projects are examples of a more general field of Paleorobotics and the insights they will lend to design philosophy. \nBio:\nAja Carter received her Ph.D. in 2020 from the Earth and Environmental Sciences Department at the University of Pennsylvania. Her PhD work centered on changes in the spinal column spanning the earliest diverse tetrapods that transitioned from aquatic to terrestrial environments. During that time\, she also authored papers on 3D printing technologies to probe the fossil record experimentally. Her first postdoctoral appointment was in the Kod*Lab under Professor Daniel Koditschek in the General Robotics Automation Sensing and Perception Lab at the University of Pennsylvania. She published works in theoretical approaches uniting paleobiology and bio-inspired legged robot design during that time. She is currently a postdoctoral researcher in the Robomechanics lab under Professor Aaron Johnson at Carnegie Mellon University\, where she is exploring robot design in quadrupedal robots and investigating spring and damper properties in the spines of the earliest large herbivores through multi-material printing. She is a member of the Explorers Club\, Sigma XI Honor Society\, and the National Society for Black Engineers.
URL:https://www.ri.cmu.edu/event/faculty-candidate-talk-aja-carter/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/03/Aja-Carter-Headshot-scaled.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250407T100000
DTEND;TZID=America/New_York:20250407T110000
DTSTAMP:20260918T040935
CREATED:20250331T170856Z
LAST-MODIFIED:20250331T170856Z
UID:145953-1744020000-1744023600@www.ri.cmu.edu
SUMMARY:Faculty Candidate Talk: Karl Pertsch
DESCRIPTION:Talk Title: \nUnlocking Scalable Robot Learning in the Real World\n\n\n\nAbstract: \nMany domains of machine learning\, from language modeling to computer vision\, have recently undergone a shift towards generalist models\, whose broad generalization abilities are fueled by large and diverse real-world training datasets and high-capacity model architectures. In robotics\, however\, it has been challenging to apply the same recipe: after all\, we cannot easily scrape millions of hours of robot data from the internet and existing model architectures for scalable learning in vision or language modeling are not designed for the continuous control tasks we need to solve in robotics. In this talk\, I will describe my work on unlocking scalable robot learning in the real world\, focusing on the three key elements of any modern ML pipeline: data\, models\, and evaluations. I will discuss important differences between robotics and other machine learning domains\, and describe how we can adapt scalable learning approaches for robotics. My work has enabled the construction of the largest robot learning datasets to date\, and the training of generalist robot policies that can perform a range of manipulation tasks out of the box in unseen environments\, simply by prompting them in natural language. I will close with a description of current limitations and open challenges towards building truly general robot control policies.\n\nBio: \nKarl Pertsch is a postdoc at UC Berkeley and Stanford\, jointly advised by Sergey Levine and Chelsea Finn. He also is a member of the technical staff at Physical Intelligence. His work focuses on building generalist robot policies that can solve a wide range of physical manipulation tasks in the real world. Karl obtained his PhD from USC\, advised by Joseph Lim. During his PhD he interned at MetaAI and Google Brain. His work has been awarded the Best Conference Paper Award at ICRA’24 and two Outstanding Paper Award Finalists at CoRL’24.
URL:https://www.ri.cmu.edu/event/faculty-candidate-talk-karl-pertsch/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2025/03/headshot-Karl-Pertsch.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20230411T130000
DTEND;TZID=America/New_York:20230411T140000
DTSTAMP:20260918T040935
CREATED:20230405T161212Z
LAST-MODIFIED:20230405T161346Z
UID:135515-1681218000-1681221600@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Wenshan Wang
DESCRIPTION:Title: Towards General Autonomy: Learning from Simulation\, Interaction\, and Demonstration \nAbstract: Today’s autonomous systems are still brittle in challenging environments or rely on designers to anticipate all possible scenarios to respond appropriately. On the other hand\, leveraging machine learning techniques\, robot systems are trained in simulation or the real world for various tasks. Due to the expensive nature of acquiring robotic data\, learning algorithms are prone to overfitting to a specific task or a specific type of environment. To address these issues\, my goal is to develop general robot systems that can learn and adapt while interacting with the environment. In this talk\, I will introduce my first few steps toward a general and self-adaptive system. Specifically\, I will describe my research in applying large-scale training\, self-supervised learning\, and inverse reinforcement learning to perception\, state estimation\, and planning components of the autonomy system. Finally\, I will discuss future works that I believe would be key to improving the robustness and bringing robots to more real-world tasks.  \nBio: Wenshan Wang is a Senior Project Scientist in AirLab at Carnegie Mellon University. She completed her Ph.D. in Robotics Institute at Shanghai Jiao Tong University in 2017\, and has since spent time in AirLab as Postdoctoral Researcher and Project Scientist. Her research focuses on developing autonomous robot systems that are robust to challenging environments and tasks using machine learning. She organized workshops about SLAM\, robot learning\, and multi-modal pretraining at CVPR2020 and ICCV2023
URL:https://www.ri.cmu.edu/event/faculty-candidate-wenshan-wang/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2023/04/Headshot.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190328T120000
DTEND;TZID=America/New_York:20190328T130000
DTSTAMP:20260918T040935
CREATED:20190312T135454Z
LAST-MODIFIED:20190312T141157Z
UID:112136-1553774400-1553778000@www.ri.cmu.edu
SUMMARY:Understanding 3D Scans
DESCRIPTION:Abstract: \nWith recent developments in both commodity range sensors as well as mixed reality devices\, capturing and creating 3D models of the world around us has become increasingly important. As the world around us lives in a three-dimensional space\, such 3D models will not only facilitate capture and display for content creation but also provide a basis for fundamental scene understanding\, from semantic understanding to virtual interactions\, which must be formulated in 3D for many applications such as augmented or virtual reality. \nMy talk will focus on constructing a generative formulation for the construction of 3D models from RGB-D data\, and the use of 3D reconstructions towards a 3D semantic and instance understanding of these scenes. I will begin with the capture and reconstruction of RGB-D scan data\, and discuss two major challenges towards democratization of 3D content: inferring 3D semantic understanding (by way of semantic and instance segmentation)\, and generating high-quality 3D model geometry. I will present 3D deep learning approaches based on 3D\, RGB-D nature of these scans\, to predict spatially consistent semantic and instance segmentations of 3D scenes\, and follow by presenting a generative deep learning formulation\, conditional on an input scan\, to construct the complete geometry of a partially observed scene. In particular\, this formulation enables the inference of complete 3D model geometry from partial 3D scan observations at scale\, generating room- and building floor-scale models\, and further extending to real-world scans. \n  \nBio: \nAngela Dai is a postdoctoral fellow at the Technical University of Munich. Her research focuses on creating high-quality 3D models of real-world environments\, towards enabling human-level scene understanding and democratizing 3D scanning for content creation and mixed reality scenarios. She completed her Ph.D. in Computer Science at Stanford University\, advised by Pat Hanrahan. During her PhD\, she has advanced real-time 3D reconstruction\, and leveraged this towards developing machine learning approaches towards improving the reconstruction quality and semantic and instance understanding of these 3D scans. Angela received her Bachelors degree in Computer Science from Princeton University. Her work has been recognized with a Professor Michael J. Flynn Stanford Graduate Fellowship and a 1.25mil euro ZDB junior research group award
URL:https://www.ri.cmu.edu/event/understanding-3d-scans/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/03/dai.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190327T120000
DTEND;TZID=America/New_York:20190327T130000
DTSTAMP:20260918T040935
CREATED:20190312T200012Z
LAST-MODIFIED:20190315T234620Z
UID:112251-1553688000-1553691600@www.ri.cmu.edu
SUMMARY:AI-Driven Videos Synthesis and its Implications
DESCRIPTION:Abstract:\nIn this talk\, I will present my research vision in how to create photo-realistic digital replica of the real world\, and how to make holograms become a reality. Eventually\, I would like to see photos and videos evolve to become interactive\, holographic content indistinguishable from the real world. Imagine taking such 3D photos to share with friends\, family\, or social media; the ability to fully record historical moments for future generations; or to provide content for upcoming augmented and virtual reality applications. AI-based approaches\, such as generative neural networks\, are becoming more and more popular in this context since they have the potential to transform existing image synthesis pipelines. I will specifically talk about an avenue towards neural rendering where we can retain the full control of a traditional graphics pipeline but at the same time exploit modern capabilities of deep learning\, such has handling the imperfections of content from commodity 3D scans.\nWhile the capture and photo-realistic synthesis of imagery opens up unbelievable possibilities for applications ranging from entertainment to communication industries\, there are also important ethical considerations that must be kept in mind. Specifically\, in the content of fabricated news (e.g.\, fakenews)\, it is critical to highlight and understand digitally-manipulated content. I believe that media forensics plays an important role in this area\, both from an academic standpoint to better understand image and video manipulation\, but even more importantly from a societal standpoint to create and raise awareness around the possibilities and moreover\, to highlight potential avenues and solutions regarding trust of digital content. \nBio:\nDr. Matthias Niessner is a Professor at the Technical University of Munich where he leads the Visual Computing Lab. Before\, he was a Visiting Assistant Professor at Stanford University. Prof. Nießner’s research lies at the intersection of computer vision\, graphics\, and machine learning\, where he is particularly interested in cutting-edge techniques for 3D reconstruction\, semantic 3D scene understanding\, video editing\, and AI-driven video synthesis. In total\, he has published over 70 academic publications\, including 22 papers at the prestigious ACM Transactions on Graphics (SIGGRAPH / SIGGRAPH Asia) journal and 18 works at the leading vision conferences (CVPR\, ECCV\, ICCV); several of these works won best paper awards\, including at SIGCHI’14\, HPG’15\, SPG’18\, and the SIGGRAPH’16 Emerging Technologies Award for the best Live Demo.\nProf. Niessner’s work enjoys wide media coverage\, with many articles featured in main-stream media including the New York Times\, Wall Street Journal\, Spiegel\, MIT Technological Review\, and many more\, and his was work led to several TV appearances such as on Jimmy Kimmel Live\, where Prof. Niessner demonstrated the popular Face2Face technique; Prof. Niessner’s academic Youtube channel currently has over 5 million views.\nFor his work\, Prof. Niessner received serval awards: he is a TUM-IAS Rudolph Moessbauer Fellow (2017 – ongoing)\, he won the Google Faculty Award for Machine Perception (2017)\, the Nvidia Professor Partnership Award (2018)\, as well as the prestigious ERC Starting Grant 2018 which comes with 1.500.000 Euro in research funding.\nIn addition to his academic impact\, Prof. Niessner is a co-founder and director of Synthesia Inc. – https://www.synthesia.io/ -\, a brand-new startup backed by Marc Cuban whose aim is to empower storytellers with cutting-edge AI-driven video synthesis.
URL:https://www.ri.cmu.edu/event/ai-driven-videos-synthesis-and-its-implications/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/03/matthias_photo1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190325T140000
DTEND;TZID=America/New_York:20190325T150000
DTSTAMP:20260918T040935
CREATED:20190315T233915Z
LAST-MODIFIED:20190315T233915Z
UID:112304-1553522400-1553526000@www.ri.cmu.edu
SUMMARY:Augmenting Imagination: Capturing\, Modeling\, and Exploring the World Through Video
DESCRIPTION:Abstract: \nCameras offer a rich and ubiquitous source of data about the world around us\, providing many opportunities to explore new computational approaches to real-world problems. In this talk\, I will show how insights from art\, science\, and engineering can help us connect progress in visual computing with typically non-visual problems in other domains\, allowing us to leverage the convenience and power of video to solve new problems. The first section of the talk will focus on visual vibration analysis: I will show how insights from physics can help us extract sound from silent video\, reason about structural and material properties that are perceptually invisible to humans\, and even build interactive physical simulations of visible objects. The second section of the talk will give an overview of how similar methodologies can be applied to artistic domains\, using insights from music\, dance\, and cinematography to design computational tools that offer creative control over large amounts of media. \n  \nBio: \nAbe Davis is a postdoctoral researcher at Stanford University working at the intersections of computer graphics\, vision\, HCI\, and civil engineering. He earned his Ph.D. in Electrical Engineering and Computer Science from MIT in 2016 and is the recipient of the MIT Sprowls Award for Outstanding Dissertation in Computer Science and the ACM SIGGRAPH Outstanding Doctoral Dissertation Honorable Mention Award. Abe was awarded NSF and Mathworks graduate fellowships\, named one of Forbes Magazine’s “30 under 30”\, Business Insider’s “50 Scientists Who are Changing the World” and “8 Innovative Scientists in Tech and Engineering.” As a postdoc\, he won the “Most Practical SHM Solution for Civil Infrastructures” Award at IWSHM 2017\, and has been the recipient of two Magic Grants from the Brown Institute for Media Innovation.
URL:https://www.ri.cmu.edu/event/augmenting-imagination-capturing-modeling-and-exploring-the-world-through-video/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/03/Unknown.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190321T100000
DTEND;TZID=America/New_York:20190321T110000
DTSTAMP:20260918T040935
CREATED:20190220T171227Z
LAST-MODIFIED:20190220T171636Z
UID:111898-1553162400-1553166000@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Angjoo Kanazawa
DESCRIPTION:Title: Perceiving Humans in the 3D World \nAbstract: \nSince the dawn of civilization\, we have functioned in a social environment where we spend our days interacting with other humans. As we approach a society where intelligent systems and humans coexist\, these systems must also interpret and interact with humans that reside in the 3D world. While computer vision systems today work well for finding 2D patterns in images or reconstructing rigid objects in 3D\, they still struggle to perceive non-rigid objects in 3D\, like moving human bodies. My goal is to build a system that can perceive and understand embodied agents in the 3D world from visual input. Such systems can enable motion capture in-the-wild\, robots that learn to act by visually observing people\, and ultimately\, socially intelligent machines that understand human behavior. \nIn this talk\, I will discuss my work in reconstructing 3D non-rigid\, deformable objects such as humans and animals from everyday photographs and video\, and show how such systems can be used to train a simulated character to learn to act by watching YouTube videos. I will discuss the challenges related to the limited availability and quality of ground-truth 3D data and how we can overcome these challenges using weakly supervised approaches. \n  \nBio: \nAngjoo Kanazawa is a BAIR postdoctoral researcher at UC Berkeley advised by Jitendra Malik\, Alyosha Efros\, and Trevor Darrell. Her research is at the intersection of computer vision graphics and machine learning\, focusing on 3D reconstruction of deformable objects such as humans and animals from everyday photographs and video.  She received her PhD in Computer Science from the University of Maryland\, College Park where she was advised by David Jacobs and her Bachelor’s in Computer Science and Math from New York University\, working with Rob Fergus. She has also spent time at the Max Planck Institute for Intelligent Systems with Michael Black\, as well as NEC Labs America and Google’s self-driving car team. Her work has received the best paper award at Eurographics 2016 and she is the recipient of the Google Anita Borg Memorial Scholarship.
URL:https://www.ri.cmu.edu/event/faculty-candidate-angjoo-kanazawa/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2019/02/Unknown-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190319T120000
DTEND;TZID=America/New_York:20190319T130000
DTSTAMP:20260918T040935
CREATED:20190305T150639Z
LAST-MODIFIED:20190312T141541Z
UID:112144-1552996800-1553000400@www.ri.cmu.edu
SUMMARY:Learning to Synthesize Images
DESCRIPTION:Abstract: People are avid consumers of visual content. Every day\, we watch videos\, play games\, and share photos on social media. However\, there is an asymmetry – while everybody is able to consume visual content\, only a chosen few (e.g.\, painters\, sculptors\, film directors) are talented enough to express themselves visually. For example\, in modern computer graphics workflows\, professional artists have to explicitly specify everything “just right” including geometry\, materials\, and lighting\, for a human to perceive an image as realistic. To automate this tedious process\, I present several general-purpose machine learning algorithms for image synthesis. Our methods can discover the structure of the visual world from the data itself and learn to synthesize realistic high-dimensional outputs directly. I then demonstrate applications in different fields such as vision\, graphics\, and robotics\, as well as usages by developers and visual artists. Finally\, I discuss our ongoing efforts on learning to synthesize 3D objects and high-resolution videos\, with the ultimate goal of building machines that can recreate the visual world and help everyone tell their visual stories. \n  \nBio: Jun-Yan Zhu is a postdoctoral researcher at MIT CSAIL. He obtained his Ph.D. in computer science from UC Berkeley after studying at CMU and UC Berkeley\, and before that\, received his B.E. from Tsinghua University. He studies computer graphics\, computer vision\, and machine learning\, with the goal of building intelligent machines\, capable of recreating the visual world. He is the recipient of Facebook Fellowship\, ACM SIGGRAPH Outstanding Doctoral Dissertation Award\, and UC Berkeley EECS David J. Sakrison Memorial Prize for outstanding doctoral research. His work has been covered in the New Yorker\, the New York Times\, and the Economist. Jun-Yan has served as a Technical Paper Committee member at SIGGRAPH Asia 2018\, a guest editor of International Journal of Computer Vision (IJCV)\, and a co-instructor of the Deep Learning course at Udacity.
URL:https://www.ri.cmu.edu/event/learning-to-synthesize-images/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/03/portrait.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190307T100000
DTEND;TZID=America/New_York:20190307T110000
DTSTAMP:20260918T040935
CREATED:20190301T145920Z
LAST-MODIFIED:20190312T140200Z
UID:112141-1551952800-1551956400@www.ri.cmu.edu
SUMMARY:Learning to see the physical world
DESCRIPTION:Abstract: Human intelligence is beyond pattern recognition. From a single image\, we’re able to explain what we see\, reconstruct the scene in 3D\, predict what’s going to happen\, and plan our actions accordingly. In this talk\, I will present our recent work on physical scene understanding—building versatile\, data-efficient\, and generalizable machines that learn to see\, reason about\, and interact with the physical world. The core idea is to exploit the causal structure behind the scene\, including knowledge from computer graphics\, physics\, and language\, in the form of approximate simulation engines\, and to integrate them with deep learning. Here\, deep learning plays two major roles: first\, it learns to invert simulation engines for efficient inference; second\, it learns to augment simulation engines for constructing powerful forward models. I’ll focus on a few topics to demonstrate this idea: building scene representation for both object geometry and physics; learning expressive dynamics models for planning and control; perception and reasoning beyond vision. \n  \nBio: Jiajun Wu is a Ph.D. student in Electrical Engineering and Computer Science at Massachusetts Institute of Technology. He received his B.Eng. from Tsinghua University in 2014. His research interests lie in the intersection of computer vision\, machine learning\, robotics\, and computational cognitive science. His research has been recognized through the IROS Best Paper Award on Cognitive Robotics and fellowships from Facebook\, Nvidia\, Samsung\, Baidu\, and Adobe\, and his work has been covered by major media outlets including CNN\, BBC\, WIRED\, and MIT Tech Review.
URL:https://www.ri.cmu.edu/event/learning-to-see-the-physical-world/
LOCATION:Newell-Simon Hall 3305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/03/Jiajun_Wu.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190304T100000
DTEND;TZID=America/New_York:20190304T110000
DTSTAMP:20260918T040935
CREATED:20190301T145525Z
LAST-MODIFIED:20190312T140309Z
UID:112138-1551693600-1551697200@www.ri.cmu.edu
SUMMARY:Self-Directed Learning
DESCRIPTION:Abstract: \nGeneralization\, i.e.\, the ability to adapt to novel scenarios\, is the hallmark of human intelligence. While we have systems that excel at recognizing objects\, cleaning floors\, playing complex games and occasionally beating humans\, they are incredibly specific in that they only perform the tasks they are trained for and are miserable at generalization. In this talk\, I will present our initial efforts toward endowing artificial agents with a human-like ability to generalize in diverse scenarios. The main insight is to allow the agent to learn general-purpose skills in a completely self-directed manner\, without optimizing for any external goal. These skills are then later repurposed to solve complex tasks. I will discuss how this framework can be instantiated to develop curiosity-driven agents (virtual as well as real) that can learn to play games\, learn to walk\, and learn to perform real-world object manipulation without any rewards or supervision. These self-directed robotic agents\, after exploring the environment\, can find their way in office environments\, tie knots using rope\, rearrange object configuration\, and compose their skills in a modular fashion. \n  \nBio: \nDeepak Pathak is a Ph.D. candidate in Computer Science at UC Berkeley\, advised by Prof. Trevor Darrell and Prof. Alexei A. Efros. His research spans computer vision\, machine learning\, and robotics. Deepak is a recipient of the Facebook Graduate Fellowship\, the NVIDIA Fellowship\, and the Snapchat Fellowship\, and his research has been featured in popular press outlets\, including The Wall Street Journal\, The Economist\, Quanta Magazine\, Wired\, and MIT Technology Review. Deepak received his Bachelor’s in Computer Science from IIT Kanpur and was a recipient of the Gold Medal and the best undergraduate thesis award. He has also spent time at Facebook\, Microsoft and founded VisageMap Inc. which was later acquired by FaceFirst Inc. \nFor papers and open-sourced code see: https://people.eecs.berkeley.edu/~pathak/
URL:https://www.ri.cmu.edu/event/self-directed-learning/
LOCATION:Newell-Simon Hall 3305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/03/DeepakPathak.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190227T100000
DTEND;TZID=America/New_York:20190227T110000
DTSTAMP:20260918T040935
CREATED:20190220T172059Z
LAST-MODIFIED:20251101T152814Z
UID:111902-1551261600-1551265200@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Yuke Zhu
DESCRIPTION:Talk: Closing the perception-action loop \nAbstract: \nRobots and autonomous systems have been playing a significant role in the modern economy. Custom-built robots have remarkably improved productivity\, operational safety\, and product quality. However\, these robots are usually programmed for specific tasks in well-controlled environments\, unable to perform diverse tasks in the real world. In this talk\, I will present my work on building more effective and generalizable robot intelligence by closing the perception-action loop. I will discuss my research that establishes a tighter coupling between perception and action at three levels of abstraction: 1) learning primitive motor skills from raw sensory data\, 2) sharing knowledge between sequential tasks in visual environments\, and 3) learning hierarchical task structures from video demonstrations. \nBio: \nYuke Zhu is a final year Ph.D. candidate in the Department of Computer Science at Stanford University\, advised by Prof. Fei-Fei Li and Prof. Silvio Savarese. His research interests lie at the intersection of robotics\, computer vision\, and machine learning. His work builds machine learning and perception algorithms for general-purpose robots. He received a Master’s degree from Stanford University and dual Bachelor’s degrees from Zhejiang University and Simon Fraser University. He also collaborated with research labs including Snap Research\, Allen Institute for Artificial Intelligence\, and DeepMind.
URL:https://www.ri.cmu.edu/event/faculty-candidate-yuke-zhu/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/02/yuke.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190221T140000
DTEND;TZID=America/New_York:20190221T150000
DTSTAMP:20260918T040935
CREATED:20190212T153517Z
LAST-MODIFIED:20190213T192713Z
UID:111031-1550757600-1550761200@www.ri.cmu.edu
SUMMARY:Rethinking the Relationship between Data and Robotics.
DESCRIPTION:Abstract: \nWhile robotics has made tremendous progress over the last few decades\, most success stories are still limited to carefully engineered and precisely modeled environments. Interestingly\, one of the most significant successes in the last decade of AI has been the use of Machine Learning (ML) to generalize and robustly handle diverse situations. So why don’t we just apply current learning algorithms to robots? The biggest reason is a complicated relationship between data and robotics. In other fields of AI such as computer vision\, we were able to collect diverse real-world\, large-scale data with lots of supervision. These three key ingredients which fueled the success of deep learning in other fields are the key bottlenecks in robotics. We do not have millions of training examples in robots; it is unclear how to supervise robots and most importantly\, most of simulation/lab data is not real-world and diverse. My research has focused on rethinking the relationship between data and robotics to fuel the success of robot learning. Specifically\, in this talk\, I will discuss three aspects of data that will bring us closer to generalizable robotics: (a) size of data we can collect\, (b) amount of supervisory signal we can extract\, and (c) diversity of data we can get from robots. \n  \nBio: \nLerrel Pinto is a PhD candidate at The Robotics Institute at Carnegie Mellon University. His research interests focus on machine learning and computer vision for robots. He received an MS degree from CMU in 2016\, and prior to that a B.Tech in Mechanical Engineering from IIT-Guwahati.  His work on large-scale learning for grasping received the Best Student Paper award at ICRA 2016. Several of his works have been featured in popular media like TechCrunch\, MIT Tech Review and BuzzFeed among others. \n 
URL:https://www.ri.cmu.edu/event/rethinking-the-relationship-between-data-and-robotics/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/02/pinto_lennel.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190219T100000
DTEND;TZID=America/New_York:20190219T110000
DTSTAMP:20260918T040935
CREATED:20190212T153931Z
LAST-MODIFIED:20190213T192530Z
UID:111034-1550570400-1550574000@www.ri.cmu.edu
SUMMARY:Resilient Safety Assurance for Human-Centered Autonomous Systems
DESCRIPTION:In order for autonomous systems like robots\, drones\, and self-driving cars to be reliably introduced into our society\, they must be able to actively account for safety during their operation. While safety analysis has traditionally been conducted offline for controlled environments like cages on factory floors\, the much higher complexity of open\, human-populated spaces like our homes\, cities\, and roads means that any precomputed guarantees may become invalid when modeling assumptions made at design time are violated during the system’s operation. My research aims to enable autonomous systems to proactively ensure safety during their operation by explicitly reasoning about the gap between their models and the real world. \n  \nIn this talk I will present recent contributions to safety assurance for autonomous systems. I will first discuss new advances in efficient safety computation\, and demonstrate their use in large-scale unmanned air traffic. Next\, I will present a general safety framework enabling the use of learning control schemes (e.g. reinforcement learning) for safety-critical robotic systems in uncertain environments. I will then turn my attention to the important problem of safe human-robot interaction\, and introduce a real-time Bayesian method to monitor the reliability of predictive human models. The talk will end with a discussion of challenges and opportunities ahead\, including the introduction of game-theoretic planning in autonomous driving and the bridging of safety analysis and deep reinforcement learning. \n  \n  \nBio: Jaime Fernández Fisac is a Ph.D. candidate in Electrical Engineering and Computer Sciences at UC Berkeley. His research interests lie in control theory and artificial intelligence\, with a focus on safety assurance for autonomous systems. He works to enable robotic systems to safely interact with uncertain environments and human beings despite using inaccurate models. Jaime received a B.S./M.S. degree in Electrical Engineering from the Universidad Politécnica de Madrid\, Spain\, in 2012\, and a M.Sc. in Aeronautics from Cranfield University\, U.K.\, in 2013. He is a recipient of the La Caixa Foundation fellowship. \n 
URL:https://www.ri.cmu.edu/event/resilient-safety-assurance-for-human-centered-autonomous-systems/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/02/Unknown.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190218T120000
DTEND;TZID=America/New_York:20190218T130000
DTSTAMP:20260918T040935
CREATED:20190212T154738Z
LAST-MODIFIED:20190213T192619Z
UID:111040-1550491200-1550494800@www.ri.cmu.edu
SUMMARY:Towards Generalization and Efficiency in Reinforcement Learning
DESCRIPTION:Abstract: In classic supervised machine learning\, a learning agent behaves as a passive observer: it receives examples from some external environment which it has no control over and then makes predictions. Reinforcement Learning (RL)\, on the other hand\, is fundamentally interactive : an autonomous agent must learn how to behave in an unknown and possibly hostile environment\, by actively interacting with the environment to collect useful feedback. One central challenge in RL is how to explore an unknown environment and collect useful feedback efficiently. In recent practical RL success stories\, we notice that most of them rely on random exploration which requires large a number of interactions with the environment before it can learn anything useful.  The theoretical RL literature has developed more sophisticated algorithms for efficient learning\, however\, the sample complexity of these algorithms has to scale exponentially with respect to key parameters of underlying systems such as the dimensionality of state vector\, which prohibits a direct application of these theoretically elegant RL algorithms to large-scale applications. Without any further assumptions\, RL is hard\, both in practice and in theory. \nIn this work\, we improve generalization and efficiency on RL problems by introducing  extra sources of help and additional assumptions. The first contribution of this work comes from improving RL sample efficiency via Imitation Learning (IL). Imitation Learning reduces policy improvement to classic supervised learning. We study in both theory and in practice how one can imitate experts to reduce sample complexity compared to RL approaches. The second contribution of this work comes from exploiting the underlying structures of the RL problems via model-based learning approaches.  While there exist efficient model-based RL approaches specialized for specific RL problems (e.g.\, tabular MDPs\, Linear Quadratic Systems)\, we develop a unified model-based algorithm that generalizes a large number of RL problems that were often studied independently in the literature. We also revisit the long standing debate on whether model-based RL is more efficient than model-free RL from a theoretical perspective\, and demonstrate that model-based RL can be exponentially more sample efficient than model-free ones\, which to the best of our knowledge\, is the first that separates model-based and model-free general approaches. \n  \nBio: Wen Sun is a PhD candidate in the Robotics Institute within the School of Computer Science at Carnegie Mellon University. He is generally interested in fundamental and applied research in machine learning and robotics\, with a focus on Reinforcement Learning and Imitation Learning. He is the recipient of the Best Student Paper Award at the Conference on Uncertainty in Artificial Intelligence (UAI)\, 2015.
URL:https://www.ri.cmu.edu/event/towards-generalization-and-efficiency-in-reinforcement-learning/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2019/02/Unknown.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190214T100000
DTEND;TZID=America/New_York:20190214T110000
DTSTAMP:20260918T040935
CREATED:20190212T154342Z
LAST-MODIFIED:20190213T192930Z
UID:111037-1550138400-1550142000@www.ri.cmu.edu
SUMMARY:Service Robots for All
DESCRIPTION:Robots have the unique potential to help people\, especially people with disabilities\, in their daily lives.  However\, providing continuous physical and social support in human environments requires new algorithmic approaches that are fast\, adaptable\, robust to real-world noise\, and can handle unconstrained behavior from diverse users. \nThis talk will describe my work developing and studying algorithms that enable service robots to make effective use of computation to address the most critical elements of interaction with people\, while being flexible enough to support the full richness of human behavior.  This includes developing fast\, data-efficient algorithms for group interaction in noisy real-world environments\, algorithms for temporal integration of task and social behavior\, and understanding how algorithmic choices affect perceptions of robot agency. \nUltimately\, these components can come together to create robots that people want to have around\, not because they perfectly imitate human behavior\, but because they seamlessly blend into the background while making people’s lives easier.  These robots will be capable of improving the lives of many people\, but will be a life-changing benefit for people with disabilities for whom human assistance comes at a significant cost to privacy and autonomy. \n  \n  \nBIO \nElaine Schaertl Short is a postdoctoral fellow in the Socially Intelligent Machines Lab at the University of Texas at Austin.  She completed her PhD under the supervision of Prof. Maja Matarić in the Department of Computer Science at the University of Southern California (USC).  She received her MS in Computer Science from USC in 2012 and her BS in Computer Science from Yale University in 2010.   Elaine is a recipient of a National Science Foundation Graduate Research Fellowship\, USC Provost’s Fellowship\, and a Google Anita Borg Scholarship.  At USC\, she was recognized for excellence in research\, teaching\, and service: she was awarded the Viterbi School of Engineering Merit Award and the Women in Science and Engineering (WiSE) Merit Award for Current Doctoral Students\, as well as the Best Research Assistant Award\, Best Teaching Assistant Award\, and Service Award from the Department of Computer Science.  At Yale she was the recipient of the Saybrook College Mary Casner Prize.  Her research focuses on building algorithms that enable fast and robust assistive human-robot interaction in schools\, homes\, crowds and other natural environments.
URL:https://www.ri.cmu.edu/event/service-robots-for-all/
LOCATION:Gates Hillman Center 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/02/EWlaine-Short.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20190211T133000
DTEND;TZID=America/New_York:20190211T143000
DTSTAMP:20260918T040935
CREATED:20190207T153828Z
LAST-MODIFIED:20190325T200641Z
UID:110977-1549891800-1549895400@www.ri.cmu.edu
SUMMARY:Automatic Human Behavior Analysis and Recognition for Research and Clinical Use
DESCRIPTION:Nonverbal behavior is multimodal and interpersonal. In several studies\, I addressed the dynamics of facial expression and head movement for emotion communication\, social interaction\, and clinical applications. By modeling multimodal and interpersonal communication my work seeks to inform affective computing and behavioral health informatics. In this talk\, I will address some of my recent work that has addressed computational methods for affect communication in children with facial abnormalities\, automatic measurement of pain intensity\, and depression severity assessment. I will conclude my talk by sketching future directions in moving from the lab to the real world. \n  \nBio: Zakia Hammal is a senior project scientist at the Robotics Institute at Carnegie Mellon University. Her areas of expertise are affective computing (also known as Emotion AI)\, multimodal human behavior modeling in social interaction\, and behavioral health informatics. She organized successful workshops in Interpersonal Synchrony and Influence (INTERPERSONAL at ICMI 2015)\, and in Face and Gesture Analysis for Health Informatics (FGAHI at CVPR 2019\, FG 2018). To promote the critical importance of context in affect recognition\, she leads a series of six successful Context-Based Affect Recognition workshops at premier IEEE conferences in computer vision\, affective computing\, social communication\, and multimedia (CBAR at FG 2019\, ACII 2017\, CVPR 2016\, FG 2015\, ACII 2013\, and SocialCom 2012). Her honors include an outstanding paper award\, at ACM ICMI 2012\, Best paper ward at IEEE ACII 2015\, and Outstanding Reviewer Award at IEEE FG 2015.
URL:https://www.ri.cmu.edu/event/automatic-human-behavior-analysis-and-recognition-for-research-and-clinical-use/
LOCATION:Gates-Hillman Center 8102
CATEGORIES:Faculty Candidate,Faculty Events
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20181212T093000
DTEND;TZID=America/New_York:20181212T103000
DTSTAMP:20260918T040935
CREATED:20181209T154752Z
LAST-MODIFIED:20190212T155150Z
UID:111043-1544607000-1544610600@www.ri.cmu.edu
SUMMARY:Faster\, Safer\, Smaller: The future of autonomy needs all three
DESCRIPTION:Abstract \nIn this talk I will start with state estimation as my PhD work. Very often\, state estimation plays a crucial role in a robotic system serving as a building block for autonomy. Challenges are to carry out state estimation in 6-DOF\, in real-time at high frequencies\, with high precision\, robust to aggressive motion and environmental changes. The proposed state estimation method leverages range\, vision\, and inertial sensing. Then\, I will discuss more recent work regarding autonomous navigation of lightweight UAVs in cluttered environments. For collision avoidance and exploration\, the work involves a fast planner which is based on an efficient representation of the environment. The talk will finish with the latest results from the DARPA Subterranean Challenge project. \n  \nBiography \nJi Zhang is postdoctoral fellow at the Robotics Institute of CMU. He received his PhD degree in Feb. 2017. His PhD research focused on ego-motion estimation and mapping. His method is ranked #1 on the odometry leaderboard of the internationally well-known KITTI Vision Benchmark\, and won the Microsoft Indoor Localization Competition in 2016 and 2017. His recent work expanded to collision avoidance and exploration of aerial vehicles. Ji Zhang was founder and Chief Scientist of Kaarta\, a CMU spin-off commercializing 3D lidar mapping and 3D modeling technologies as the outcome of his research work.
URL:https://www.ri.cmu.edu/event/faster-safer-smaller-the-future-of-autonomy-needs-all-three/
LOCATION:Gates-Hillman Center 8102
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2016/12/zhang_ji_2014_3.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20181108T143000
DTEND;TZID=America/New_York:20181108T153000
DTSTAMP:20260918T040935
CREATED:20181108T155618Z
LAST-MODIFIED:20190212T155755Z
UID:111046-1541687400-1541691000@www.ri.cmu.edu
SUMMARY:Multimodal Computational Behavior Understanding
DESCRIPTION:Emotions influence our lives. Observational methods of measuring affective behavior have yielded critical insights\, but a persistent barrier to their wide application is that they are labor-intensive to learn and to use. An automated system that can quantify and synthesize human affective behavior in real-world environments would be a transformational tool for research and for our everyday life. Are we there yet? \nRecent breakthroughs in automated multimodal analysis and synthesis make possible objective\, repeatable\, efficient measure of emotion-relevant behavior in naturalistic environments. In this talk I will present my work on: (1) novel deep learning based computational approaches to measure and synthesize affective behavior; (2) their applications to realize closed-loop adaptive Deep Brain Stimulation (aDBS) systems for non-motor neuropsychiatric disorders and to gain new understanding of the neural and social bases of emotion; and (3) current challenges that affective computing faces in real-world conditions. \nBio: László A. Jeni is Project Scientist in the Robotics Institute at Carnegie Mellon University\, Pittsburgh\, PA\, USA. He specializes in computational behavior science\, specifically in areas of modelling\, understanding\, and synthesizing human behavior using diverse sensors. He received his Ph.D. in 2012 from the University of Tokyo\, Japan. He worked as a Senior Computer Vision Specialist at Realeyes – Emotional Intelligence\, before joining the Robotics Institute. To his credit he has over 40 peer reviewed publications. His honors include Best Paper Awards at the IEEE Conference on Human System Interaction (HSI’2011) for work on validating observations of human activity and at the Conference on Automatic Face and Gesture Recognition (FG’2015) for work on dense 3D face alignment from 2D video. He has organized workshops and challenges on 3D Face Alignment in the Wild at ECCV and on Facial Expression Recognition and Analysis at FG.
URL:https://www.ri.cmu.edu/event/multimodal-computational-behavior-understanding/
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2019/02/lazlo.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180405T100000
DTEND;TZID=America/New_York:20180405T113000
DTSTAMP:20260918T040935
CREATED:20180228T152713Z
LAST-MODIFIED:20180302T013542Z
UID:104768-1522922400-1522927800@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Petter Nilsson
DESCRIPTION:Areas of Interest: \n\n\n\nImproving design practices and advancing the capabilities of autonomous systems\n\nHost: Stephen Smith \nAdmin Contact: Keyla Cook keylac@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-petter-nilsson/
LOCATION:GHC 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2018/02/portrait.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180402T100000
DTEND;TZID=America/New_York:20180402T113000
DTSTAMP:20260918T040935
CREATED:20180228T152304Z
LAST-MODIFIED:20180319T181749Z
UID:104765-1522663200-1522668600@www.ri.cmu.edu
SUMMARY:Social Signal Processing: A Computational Approach to Sensing\, Reconstructing and Understanding Social Interaction
DESCRIPTION:Abstract:\nHumans convey their thoughts\, emotions\, and intentions through a concert of social displays: voice\, facial expressions\, hand gestures\, and body posture. Despite advances in machine perception technology\, machines are unable to discern the subtle and momentary nuances that carry so much of the information and context of human communication. The encoding of conveyed information by human body movements is still poorly understood\, and a major obstacle to scientific progress in understanding human behavior is the inability to measure the full spectrum of social signals in groups of interacting individuals. \nIn this talk\, I will describe my early exploration in building sensors that can capture the full spectrum of human social signaling—from voice\, to facial expressions\, to hand gestures\, to body posture—among groups of multiple people. Leveraging more than 500 synchronized cameras\, our method enables us to markerlessly measure subtle 3D movements of interacting people\, providing a new opportunity to computationally study social interaction. I will also talk about my ongoing efforts to understand social interaction in a predictive way\, based on our novel dataset containing 3D social signals from hundreds of participants. \nBio:\nHanbyul Joo is a Ph.D. candidate in the Robotics Institute\, Carnegie Mellon University. His research focuses on measuring social signals in interpersonal social communication to computationally model social behavior\, using tools of computer vision\, computer graphics\, and machine learning. Hanbyul has been developing the Panoptic Studio at CMU\, a sensing system designed to capture social interaction using more than 500 synchronized cameras. Hanbyul’s research has been covered in various media outlets including Discovery\, Reuters\, IEEE Spectrum\, NBC News\, Voice of America\, The Verge\, and WIRED. He is a recipient of the Samsung Scholarship. \nAreas of Interest: \n\n\n\nMeasuring the full spectrum of 3D social signals\, computational behavioral science\n\n  \nHost: Chris Atkeson \n\n\nAdmin Contact: Chris Downey cdowney@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-hanbyul-joo/
LOCATION:Newell-Simon Hall 3305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/02/han_dec_2017.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180329T130000
DTEND;TZID=America/New_York:20180329T143000
DTSTAMP:20260918T040935
CREATED:20180228T151726Z
LAST-MODIFIED:20180312T134622Z
UID:104761-1522328400-1522333800@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Probing Light Transport for 3D Shape
DESCRIPTION:Abstract: There is a rising demand for high-performance 3D sensors in response to the rapid development of autonomous cars\, 3D printers\, and virtual/augmented reality systems.  These sensors often make use of controllable light sources to send light signals into an environment\, and cameras to measure the signal reflected back in response.  This approach can\, however\, fail in critical scenarios where objects with complex material properties are present\, when imaging objects under overwhelmingly bright sunlight\, or when the object of interest is hidden behind an occluder. \n  \nIn this talk\, I will address these key challenges by presenting a new family of computational cameras that explicitly control what light paths contribute to an image.  First\, I will identify the crucial link between stereo geometry and light transport used to attenuate the contribution of multiply-scattered light paths which make 3D imaging hard.  Second\, I will show how this link can be further exploited to optimize the energy-efficiency of these camera systems\, which enables 3D imaging under strong ambient lighting.  Finally\, I will explain how sampling a specific set of light paths leads to the derivation of an efficient\, closed-form solution for reconstructing images of objects hidden from view. \n  \nBio: Matthew O’Toole is a postdoctoral scholar with the Department of Electrical Engineering at Stanford University.  His research focus is on computational imaging\, a highly multi-disciplinary topic that makes use of novel combinations of computation\, electronics\, and optics to overcome the limitations of conventional imaging systems.  He completed his Ph.D. at the University of Toronto in 2016\, and his thesis received the ACM SIGGRAPH Outstanding Dissertation Honorable Mention award in 2017.  His research accolades also include two runner-up best paper awards (CVPR 2014\, ICCV 2007) and two best demo awards (CVPR 2015\, ICCP 2015).  He co-organized two workshops on Computational Cameras and Displays at CVPR 2016 and 2017\, and a course by the same name at SIGGRAPH 2014.  He is supported by a Banting Postdoctoral Fellowship from the Government of Canada. \n  \nAreas of Interest: \n\n\n\n\n\n\n\nComputational Imaging\, Light transport analysis\, time-resolved imaging\n\n\n\n\n\n\n\n\nHost: Ioannis Gkioulekas\nAdmin Contact: CSD
URL:https://www.ri.cmu.edu/event/faculty-candidate-matt-otoole/
LOCATION:GHC 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/02/headerphoto.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180327T100000
DTEND;TZID=America/New_York:20180327T113000
DTSTAMP:20260918T040935
CREATED:20180122T185726Z
LAST-MODIFIED:20180306T145223Z
UID:103953-1522144800-1522150200@www.ri.cmu.edu
SUMMARY:Faculty Candidate Talk: Visual Perception and Navigation in 3D Scenes
DESCRIPTION:Abstract: In recent times\, computer vision has made great leaps towards 2D understanding of sparse visual snapshots of the world. This is insufficient for robots that need to exist and act in the 3D world around them based on a continuous stream of multi-modal inputs. In this talk\, I will present some of my efforts in bridging this gap between computer vision and robotics. I will show how thinking about computer vision and robotics together\, brings out limitations of current computer vision tasks and techniques\, and motivates joint study of perception and action for robotic tasks. I will showcase these aspects via three examples: visual navigation\, 3D scene understanding and representation learning for varied modalities. I will conclude by pointing out future research directions at the intersection of computer vision and robotics\, thus showing how the two fields are ready to get back together. \n  \nBio: Saurabh Gupta is a Ph.D. student at UC Berkeley\, where he is advised by Jitendra Malik. His research interests include computer vision\, robotics and machine learning. His PhD work focuses on 3D scene understanding\, and visual navigation. His work is supported by a Berkeley Fellowship and a Google Fellowship in Computer Vision. \n  \nAreas of Interest: \n\n\n\n\n\n\nComputer vision and robotics\n\n\n\n\n\n\nHost: Abhinav Gupta \nAdmin Contact: Chris Downey cdowney@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-talk-6/
LOCATION:GHC 8102
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2018/01/gupta.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180326T100000
DTEND;TZID=America/New_York:20180326T113000
DTSTAMP:20260918T040935
CREATED:20180122T190938Z
LAST-MODIFIED:20180227T211535Z
UID:103955-1522058400-1522063800@www.ri.cmu.edu
SUMMARY:Faculty Candidate Talk: Computational Design for the Next Manufacturing Revolution
DESCRIPTION:Areas of interest: \n\n\n\n\n\n\nComputational design for manufacturing\n\nAbstract: \nOver the next few decades\, we are going to transition to a new economy where highly complex\, customizable products are manufactured on demand by flexible robotic systems. In many fields\, this shift has already begun. 3D printers are revolutionizing production of metal parts in the aerospace\, automotive\, and medical industries. Whole-garment knitting machines allow automated production of complex apparel and shoes. Manufacturing electronics on flexible substrates makes it possible to build a whole new range of products for consumer electronics and medical diagnostics. Collaborative robots\, such as Baxter from Rethink Robotics\, allow flexible and automated assembly of complex objects. Overall\, these new machines enable batch-one manufacturing of products that have unprecedented complexity. \nIn my talk\, I argue that the field of computational design is essential for the next revolution in manufacturing. To build increasingly functional\, complex and integrated products\,  we need to create design tools that allow their users to efficiently explore high-dimensional design spaces by optimizing over a set of performance objectives that can be measured only by expensive computations. I will discuss how to overcome these challenges by 1) developing data-driven methods for efficient exploration of these large spaces and 2) performance-driven algorithms for automated design optimization based on high-level functional specifications. I will showcase how these two concepts are applied by developing new systems for designing robots\, drones\, and furniture. I will conclude my talk by discussing open problems and challenges for this emerging research field. \n\nBio: \nAdriana Schulz is a Ph.D. student in the department of Electrical Engineering and Computer Science at MIT where she works at the Computer Science and Artificial Intelligence Laboratory. She is advised by Professor Wojciech Matusik and her research spans computational design\, digital manufacturing\, interactive methods\, and robotics. Before coming to MIT\, she obtained a M.S. in mathematics from IMPA\, Brazil and a B.S. in electronics engineering from UFRJ\, Brazil. \n\nHost: Jessica Hodgins \nAdmin Contact: Jess Butterbaugh jessb@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-talk-7/
LOCATION:Gates 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/01/aschulz.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180322T130000
DTEND;TZID=America/New_York:20180322T143000
DTSTAMP:20260918T040935
CREATED:20180201T151428Z
LAST-MODIFIED:20180306T145354Z
UID:104312-1521723600-1521729000@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Toward Semi-Autonomous Surgical Tasks using Continuum Robots: Modeling\, Calibration\, and Intelligent Assistance
DESCRIPTION:Abstract: \nContinuum robots for surgical applications can support complex surgical tasks within deep confined spaces of the body. Such surgical paradigms often present surgeons with sensory and surgical scene interpretation challenges that diminish situational awareness. These robots can reach deep into the body\, while in some scenarios\, using them in a semi-automated mode of operation may alleviate the cognitive burden of surgeons. However\, these exciting capabilities of continuum robots are unattainable without the availability of accurate kinematic models. Meanwhile\, the situational awareness may be augmented\, but the augmentation requires methods for reconciling preoperative imaging information with the surgical scene in a way that helps the surgeon in executing surgical tasks safely. \nI will describe two aspects of research: how to obtain accurate robot models via calibration\, and how to update a preoperative surgical plan using force information in surgery. The modeling and calibration approach was validated using a surgical continuum robot (IREP) developed in ARMA lab. The surgical plan updating method was demonstrated on da Vinci Research Kit (dVRK) and IREP. As an extension of my current research\, collaborative work will be briefly introduced on modeling approach of continuum robots applied for pneumatic bellow actuators\, and on other force information usage during robotic surgery. \n  \nBiography: \nLong Wang is a Ph.D. candidate in the Department of Mechanical Engineering at Vanderbilt University\, under the supervision of Dr. Nabil Simaan. He received his B.S. and M.S. degrees in Mechanical Engineering from Tsinghua University and from Columbia University\, respectively. Since 2013 he has been working as a research assistant on a 5-year collaborative NRI Large grant (National Robotic Initiative) – Complementary Situational Awareness for Human-Robot Partnerships. His research interests include modeling\, calibration\, and control of continuum robots\, surgical robotics\, force-controlled robot exploration\, and robotic hands. \n  \nAreas of Interest: \n\n\n\nModeling and control of continuum robots\n\nHost: Howie Choset \nAdmin Contact: Peggy Martin pm1e@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-long-wang/
LOCATION:GHC 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/02/Long_Wang_2018.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180321T100000
DTEND;TZID=America/New_York:20180321T113000
DTSTAMP:20260918T040935
CREATED:20180201T150937Z
LAST-MODIFIED:20180201T150937Z
UID:104309-1521626400-1521631800@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Katie Bouman
DESCRIPTION:Areas of Interest: \nComputational imaging\, computational photography\, computer vision\, image and video processing\, inverse problems\, machine learning \nHost: Srinivasa Narasimhan \nAdmin Contact: jessb@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-katie-bouman/
LOCATION:Gates 6115
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/02/bouman.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180308T160000
DTEND;TZID=America/New_York:20180308T173000
DTSTAMP:20260918T040935
CREATED:20180201T150516Z
LAST-MODIFIED:20180227T210749Z
UID:104306-1520524800-1520530200@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Recovering a Functional and Three Dimensional Understanding of Images
DESCRIPTION:Areas of Interest: \n\n\n\n3D Vision\n\nAbstract: What does it mean to understand an image? One common answer in computer vision has been that understanding means naming things: this part of the image corresponds to a refrigerator and that to a person\, for instance. While important\, the ability to name is not enough: humans can effortlessly reason about the rich 3D world that images depict and how this world functions and can be interacted with. For example\, just looking at an image\, we know what surfaces we could put a cup on\, what would happen if we tugged on all the handles in the image\, and what parts of the image could be picked up and moved. A computer\, on the other hand\, understands none of this. My research aims to address this by giving computers the ability to understand these 3D and functional (or interactive) properties. \n  \nIn this talk\, I will discuss my efforts towards building this understanding. In particular\, I will show work addressing what 3D representations we should infer from images\, how we can learn them\, and how to reconcile our prior knowledge with data-driven techniques. I will also discuss how to scalably gather data of humans interacting with the world and how to learn from this data. \n  \nBio: David Fouhey is a postdoctoral fellow at the University of California\, Berkeley. His research interests include computer vision and machine learning\, with a particular focus on scene understanding. He received a Ph.D. in robotics in 2016 from Carnegie Mellon University where he was supported by NSF and NDSEG fellowships. He has spent time at the University of Oxford’s Visual Geometry Group and at Microsoft Research. http://people.eecs.berkeley.edu/~dfouhey/ \n  \nHost: Kris Kitani \nAdmin Contact: jessb@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-david-fouhey/
LOCATION:NSH 3305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2018/02/Fouhey.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180307T140000
DTEND;TZID=America/New_York:20180307T153000
DTSTAMP:20260918T040935
CREATED:20180228T145934Z
LAST-MODIFIED:20180228T145934Z
UID:104757-1520431200-1520436600@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Human-centric Understanding of 3D Environments
DESCRIPTION:Areas of Interest: \nHuman-centric 3D Scene Analysis\, Scene synthesis for 3D content creation and learning through simulation\, Data visualization \n  \nAbstract: \nCreating 3D environments is hard. Experts spend much time and effort using complex software to create virtual 3D interiors. This 3D content creation bottleneck limits the use of virtual environments for applications in entertainment\, education\, research\, and design. I address this bottleneck by leveraging the insight that real indoor environments are designed by people for people to inhabit. \n  \nIn this talk\, I will discuss a human-centric representation of the structure and semantics of 3D environments learned from observations of people acting in the real world. First\, I will demonstrate how we can use this embodied representation to analyze 3D environments and predict how likely they are to support specific human actions. Then I will show how we can use the same representation to generate 3D environments and human poses depicting common actions. Finally\, I will describe my work on using virtual environments to build a simulation platform for research on intelligent embodied agents. With this platform we can leverage computer graphics to generate 3D environments with controlled variation\, enabling systematic learning for computer vision\, robotics\, NLP\, and AI. \n  \nBio: \nManolis Savva is a postdoc at Princeton University. He completed his PhD at the Stanford graphics lab\, advised by Pat Hanrahan. His research focuses on human-centric 3D scene analysis and generation\, and simulation of 3D interior environments. He has also worked in data visualization\, grounding of natural language to 3D content\, and on establishing several large-scale 3D datasets: ShapeNet\, SUNCG\, ScanNet\, and Matterport3D. More details at: http://graphics.stanford.edu/~msavva \n  \nHost: Keenan Crane
URL:https://www.ri.cmu.edu/event/faculty-candidate-human-centric-understanding-3d-environments/
LOCATION:Newell-Simon Hall 3305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/02/saava.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180306T100000
DTEND;TZID=America/New_York:20180306T113000
DTSTAMP:20260918T040935
CREATED:20180228T145219Z
LAST-MODIFIED:20180302T215818Z
UID:104754-1520330400-1520335800@www.ri.cmu.edu
SUMMARY:Faculty Candidate: Mixed-autonomy mobility: scalable learning and optimization
DESCRIPTION:Areas of Interest: \n\n\n\n\nLearning\, optimization\, and control for mixed-autonomy mobility\n\nAbstract:\nHow will self-driving cars change urban mobility? This talk describes contributions in machine learning and optimization critical for enabling mixed-autonomy mobility\, the gradual and complex integration of automated vehicles into the existing transportation system. The talk first explores and quantifies the potential impact of a small fraction of automated vehicles on low-level traffic flow dynamics\, using novel techniques in model-free deep reinforcement learning. Second\, the talk presents generic reinforcement learning techniques for improved variance reduction\, developed for large-scale control systems such as traffic networks and robotic manipulation. To anchor this work in a broader mobility planning context\, automated vehicles are expected to increase transportation demand through a phenomenon called induced demand. To address this\, joint work with Microsoft Research is presented\, which provides theoretical justification for the application of widely used clustering algorithms to ridesharing problems\, designed to mitigate the strain on existing infrastructure. Finally\, the coordination of automated vehicles relies on accurate traffic flow sensing. To this end\, a new convex optimization method for cellular network measurements from AT&T for all of California is introduced to address a flow estimation problem previously believed to be intractable. Together\, these contributions demonstrate\, through principled learning and optimization methods\, that a small number of vehicles and sensors can be harnessed for significant impact on urban mobility. \nBio:\nCathy Wu is a PhD candidate in machine learning in Electrical Engineering and Computer Sciences (EECS) at UC Berkeley\, the Berkeley Artificial Intelligence Research lab\, Berkeley DeepDrive\, California PATH\, and the Berkeley RISELab. She is interested in developing principled computational tools to enable reliable and complex decision-making for critical societal infrastructure\, such as transportation systems. Cathy received her Masters and Bachelors degrees in EECS from MIT.  She is the recipient of several fellowships including the NSF graduate fellowship\, the Berkeley Chancellor’s fellowship\, the NDSEG fellowship\, and the Dwight David Eisenhower graduate fellowship.  Her work was acknowledged by several awards\, including the 2016 IEEE ITSC Best Paper Award and the 2017 ITS Outstanding Graduate Student Award. Her leadership\, in particular as the Research Lead of the Learning Traffic Team at Berkeley\, was recognized by numerous awards and invitations\, such as multiple NSF early-career investigator workshops on cyber-physical systems and the 2017 IEEE Leaders Summit.  Throughout her career\, Cathy has collaborated or interned broadly across fields\, including civil engineering\, mechanical engineering\, urban planning\, and public policy\, and institutions\, including OpenAI\, Microsoft Research\, the Google Self-Driving Car Team\, AT&T\, Facebook\, and Dropbox.  As the founder and Chair of the Interdisciplinary Research Initiative within the ACM Future of Computing Academy\, she is actively working to create international programs to further enable and support interdisciplinary research in computing. \nHost: Stephen Smith \nAdmin Contact: Keyla Cook keylac@andrew.cmu.edu
URL:https://www.ri.cmu.edu/event/faculty-candidate-cathy-wu/
LOCATION:Newell-Simon Hall 3305
CATEGORIES:Faculty Candidate,Faculty Events
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2018/02/wu.jpg
END:VEVENT
END:VCALENDAR