BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Robotics Institute Carnegie Mellon University - ECPv6.15.12.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Robotics Institute Carnegie Mellon University
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: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
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20261116T153000
DTEND;TZID=America/New_York:20261116T170000
DTSTAMP:20261114T173128
CREATED:20261109T160626Z
LAST-MODIFIED:20261109T160626Z
UID:154152-1794843000-1794848400@www.ri.cmu.edu
SUMMARY:RI PhD Thesis Proposal - Philip Huang
DESCRIPTION:Date: November 16\, 2026\nTime: 3:30-5:00PM ET\nType: RI PhD Thesis Proposal\nZoom Link\nLocation: NSH 3305\nTitle: Towards Efficient\, Versatile and Robust Multi-Arm Manipulation and Assembly\nWho: Philip Huang \nAbstract: \n\nRobotic manipulation with multiple robot arms can dramatically improve efficiency and versatility compared with a single robot arm. By scheduling and parallelizing tasks across multiple robot arms\, multi-arm systems can increase throughput. They can also perform tasks that require dexterity or coordination beyond a single arm’s capabilities\, such as assembling objects or handling bulky parts.\nThese coordinated capabilities can enable a broad range of applications\, including robotic grinding\, welding\, and high-mix\, low-volume assembly. Yet\, this vision of ubiquitous\, useful multi-arm systems remains far from reality because of limitations in existing algorithms and tools. \nWe use a bimanual LEGO assembly system to illustrate the algorithmic gaps in long-horizon assembly tasks. We argue that a practical multi-arm system needs efficient algorithms to schedule tasks\, coordinate motions\, execute them safely on real robots\, and adapt to different targets and requirements. We present APEX-MR\, an asynchronous planning and execution framework that systematically integrates multi-arm motions and manipulation skills for safe execution under uncertainty. We also show how APEX-MR can incorporate perception skills to assemble diverse and complex LEGO brick structures. As a proposed work\, we will extend APEX-MR to efficiently replan tasks and motions online for execution failures. \nBuilding this system\, we study more general problems in multi-arm motion planning and task and motion planning (TAMP). To improve motion quality\, we first benchmark multi-arm shortcutting\, an important yet often overlooked postprocessing technique for geometric motion planners. To accelerate both motion generation and postprocessing\, we then introduce VAMP-MR\, which leverages CPU SIMD vectorization to speed up collision checking by up to two orders of magnitude over prior work.\nBuilding on these results\, we propose cuArms\, a GPU-accelerated\, conflict-based multi-arm manipulation planner that can plan long-horizon problems with 8 arms and 40 tasks in approximately one second. cuArms can also be combined with a high-level scheduler for domain-agnostic\, full multi-arm task and motion planning with collaborative bimanual skills. \nA remaining question is how to combine planning and learning to make multi-arm systems versatile enough for new tasks that require dexterous\, precise manipulations. To study this question\, we propose fixtureless bimanual assembly of LEGO components as a testbed. Our goal is to extend system capability along two orthogonal axes: (1) adapting to a more diverse set of component and connector types\, and (2) learning and integrating more flexible bimanual skills\, such as non-prehensile or in-hand manipulation. We will investigate how model-based planning can improve the efficiency of learning bimanual assembly skills from demonstrations\, and how to represent the preconditions\, outcomes\, and constraints of these skills for structured long-horizon planning and execution. By addressing efficiency\, robustness to failures\, and versatility\, this thesis develops algorithmic foundations for practical multi-arm manipulation systems. \nCOMMITTEE MEMBERS\nJiaoyang Li (Chair)\nChangliu Liu\nOliver Kroemer\nTom Silver\,  Princeton University
URL:https://www.ri.cmu.edu/event/ri-phd-thesis-proposal-philip-huang/
LOCATION:Newell-Simon Hall 3305
CATEGORIES:PhD Thesis Proposal,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20261120T093000
DTEND;TZID=America/New_York:20261120T110000
DTSTAMP:20261114T173128
CREATED:20261110T194637Z
LAST-MODIFIED:20261110T194658Z
UID:154156-1795167000-1795172400@www.ri.cmu.edu
SUMMARY:RI PhD Thesis Proposal - Hung-Jui (Joe) Huang
DESCRIPTION:Date: November 20\, 2026\nTime: 9:30-11:00 AM ET\nType:  RI PhD Thesis Proposal\nZoom Link\nLocation: GHC 4303\nTitle: Unlocking the Power of Touch: From High-Precision Tactile Perception to Tactile-Driven Dexterous Manipulation\nWho: Hung-Jui (Joe) Huang\n\n\n\nAbstract: \n\n\nTouch plays a critical role in how we perceive and interact with the environment in everyday life. Through touch\, we can feel an object’s shape\, sense how it moves\, and manipulate it with greater dexterity and precision. Without touch\, even simple tasks such as holding an object steadily or lighting a match become challenging. Despite recent advances in high-resolution tactile sensors that enable robots to capture rich contact information\, accurately perceiving object properties\, such as pose and shape\, and leveraging tactile feedback for dexterous manipulation remain significant challenges. This thesis explores how tactile sensing can enable precise object perception and reliable dexterous manipulation. \nTo enable high-precision tactile perception\, we introduce NormalFlow\, a fast\, accurate\, and robust algorithm for tracking an object’s 6DoF pose using tactile sensing. By directly aligning tactile-derived surface normal maps instead of point clouds\, NormalFlow consistently outperforms existing methods in tracking accuracy and robustness\, and can even track low-texture objects such as ping-pong balls. It runs in 8 ms per frame on a CPU and maintains a rotational tracking error of only 2.5 degrees after a full 360-degree rotation. NormalFlow provides a foundation for future high-precision tactile perception and precise manipulation tasks. \nBuilding on NormalFlow\, we develop GelSLAM\, a real-time tactile SLAM system for long-horizon object tracking and high-fidelity 3D reconstruction. By leveraging tactile-derived surface normals and curvatures for tracking and loop closure\, GelSLAM effectively corrects accumulated drift and maintains global consistency. GelSLAM enables accurate tracking across tens of thousands of frames and hundreds of contact breaks\, and is the first system to robustly reconstruct high-fidelity 3D object shapes with submillimeter accuracy using touch alone. GelSLAM extends tactile sensing beyond local contact measurements to global spatial understanding\, opening new possibilities for tactile perception. \nBeyond geometric perception\, we investigate dynamic tactile sensing for liquid property estimation. Inspired by how humans shake a container to infer its contents\, we develop a physics-inspired model of liquid oscillations and their corresponding tactile signals. By analyzing the frequency and decay of these oscillations\, our method estimates liquid properties such as viscosity and height using limited training data. Experiments demonstrate accurate estimation of liquid properties\, including subtle differences in sugar concentration. This work highlights the potential of dynamic tactile sensing to reveal physical properties that are difficult to observe through vision\, extending tactile perception beyond surface geometry. \nBeyond perceiving objects\, we further explore how tactile feedback can improve dexterous manipulation. In the proposed work of this thesis\, we introduce Contact Tamer\, a learned contact-centric tactile policy that aims to make dexterous manipulation more efficient and reliable by directly regulating finger contacts. Unlike conventional object-centric policies that rely on visual feedback\, Contact Tamer uses tactile sensing and proprioception to maintain desired contact behaviors in real time. Preliminary simulation results demonstrate improved task success and reduced unintended slipping. This work aims to enable robots to perform complex contact-rich manipulation tasks more robustly and efficiently. \nTogether\, these works advance tactile sensing from understanding object geometry and physical properties to regulating contact during manipulation\, laying the foundation for robots that can perceive and manipulate the physical world more precisely and reliably through touch. \n\nCOMMITTEE MEMBERS\nMichael Kaess (Co-Chair)\nWenzhen Yuan (Co-Chair)\nJeff Ichnowski\nMaria Bauza (Google DeepMind)
URL:https://www.ri.cmu.edu/event/ri-phd-thesis-proposal-hung-jui-joe-huang/
LOCATION:GHC 4303
CATEGORIES:PhD Thesis Proposal,Student Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20261120T143000
DTEND;TZID=America/New_York:20261120T153000
DTSTAMP:20261114T173128
CREATED:20260828T170225Z
LAST-MODIFIED:20260929T165739Z
UID:153359-1795185000-1795188600@www.ri.cmu.edu
SUMMARY:RI Seminar with Farrell Helbling
DESCRIPTION:
URL:https://www.ri.cmu.edu/event/ri-seminar-with-farrell-helbling/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2026/08/helbling.png
END:VEVENT
END:VCALENDAR