|Adaptive Introspection for Robust Long Duration Autonomy |
Long duration autonomy for unmanned systems is difficult to achieve as current systems are design limited to anticipated exceptions and do not adapt to long-term changes in the environment. In addition, the challenge of designing experiments for long durations that provoke unanticipated exceptions is difficult. In this project we will enable long-term operation in unpredictable environments by developing an adaptive introspection and deployment approach and evaluating the ideas in an experimental setup that will provoke exceptions.
Automates copper processing
|Assistive Robots for Blind Travelers |
As robotics technology evolves to a stage where co-robots, or robots that can work with humans, become a reality, we need to ensure that these co-robots are equally capable of interacting with humans with disabilities. This project addresses this challenge by exploring meaningful human-robot interaction (HRI) in the context of assistive robots for blind travelers.
|Autonomous Robotics Manipulation |
Carnegie Mellon’s Autonomous Robotic Manipulation (ARM-S) team develops software that autonomously performs complex manipulation tasks.
Non-contact 3-D surgical instrument tracking for device testing and surgeon assessment.
|Micron: Intelligent Microsurgical Instruments |
Suppression of hand tremor to improve precision in
We are developing a curriculum for the Introduction to Computer Science (CS1) course taught at two and four year colleges and for high school Computer Science courses.
|Lego Educational Robotics |
Self-paced robotics education labs
|Lunar Regolith Excavation and Transport |
This research develops lightweight robotic excavators for digging and transporting regolith (loose soil) on the Moon.
|Lunar Rover for Polar Crater Exploration |
The Scarab lunar rover has been designed to carry a 1-meter coring drill and a payload of science instruments that can analyze the abundance of hydrogen, oxygen and other materials.
|Automated Reverse Engineering of Buildings |
The goal of this project is to use data from 3D sensors to automatically reconstruct compact, accurate, and semantically rich models of building interiors.
|The Aerial Robotic Infrastructure Analyst (ARIA) |
The Aerial Robotic Infrastructure Analyst (ARIA) rapidly creates comprehensive, high-resolution, semantically rich 3D models of infrastructure – an interactive assistant for infrastructure inspection.
|GPS-denied Localization using ground and air vehicles |
In this project, we are developing mapping and localization methods that combine aerial imagery from satellite and aerial platforms with maps and perception from ground-based robots to produce integrated maps even when GPS is unavailable.
|The Intelligent Workcell |
This project is studying methods for augmenting industrial workcells with sensors and feedback mechanisms to enable workers and robots to operate safely in the same environment.
|Micro Air Vehicle Scouts for Intelligent Semantic Mapping |
The goal of this project is develop the next level of capability for a low-flying, map building MAV scout. The research will demonstrate rapid scouting in cluttered environments and acquire relevant semantically annotated maps.
|Indoor Flight in Degraded Visual Environments |
Our goal is to fly indoors in degraded visual environments to localize people and fire. We are developing accurate real-time localization and control to be able to fly in these challenging conditions.
|Helicopter Obstacle Avoidance and Landing |
In this project we develop the trajectory planning system for an autonomous helicopter. The helicopter is used for cargo delivery. To read more about the trajectory planning system see the following publications.
|Simple Hands |
Designing simple grippers for autonomous general purpose manipulation.
|Extrinsic Dexterity |
"Extrinsic Dexterity" is a way to get dexterous manipulation with a very simple hand, by coordinating finger motion with arm motion. The more common approach is to depend entirely on the fingers of the hand, which requires at least three fingers and at least nine motors. We have demonstrated Extrinsic Dexterity using the single motor of the MLab Hand, coordinated with the motions of the arm.
|Harnessing Human Manipulation |