Robotic Manipulation/DARPA ARMS
We collaborate with the Jet Propulsion Laboratory as one of the 6 teams in the DARPA-ARMS (DARPA
Autonomous Robotic Manipulation--Software) competition. As part of its contribution to the overall
team effort, Caltech is working on:
- Estimation: Our goal is to fuse various visual modalities (stereo, LADAR, appearance) with
force-torque sensing, tactile sensing, and proprioception to better estimate the locations of the
objects to be manipulated as well as the posture of the arm.
- Grasp Planning: We are trying to extend the basic theory of caging manipulation to 3-dimensional objects.
- Task Decomposition: We are investigating the use of formal systems theory (e.g., the use of correct-by-construction control synthesis based on Linear Temporal Logic system specification and model checking) to construct correct-by-design automata for complex manipulation tasks.
Robotic Field Manipulation/RCTA
We are part of the RCTA (Robotics Collaborative Technology Aliance) program, which is sponsored by
the Army Research Labs (ARL), and lead by General Dynamics Robotics Systmes (GDRS). One of the main
objectives of this program is to develop the capabilities for mobile robots to carry out complex
operations in unstructured field environments. In collaboration with the Jet Propulsion Laboratory,
we are developing novel grasp planning algorithms for low-degree-of-freedom grippers, as well as
techniques to estimate the state of the grasped object and the manipulator system.|}
Axel and DuAxel Rovers for extreme planetary terrains
Conventional robotic Martian explorers, such as Sojourner, Spirit, and Opportunity, have sufficient
mobility to access ~60% of the Martian surface. However, some of the most interesting science
targets occur in the currently inaccessible extreme terrains, such as steep craters, overhangs,
loose soil, and layered stratigraphy. Access to extreme terrains on other planets (besides Mars)
and moons is also of potential interest. In collaboration with JPL, we are developing the Axel
and DuAxel rovers. Axel is a minimalist tethered robot that can ascend and descend vertical
and steeps slopes, as well as navigate over large (relative to the body size) obstacles. In the
DuAxel configuration, two Axels dock with a central module to form a self-contained
4-wheeled rover, which can then disassemble as needed to allow one or both Axels to descend into
extreme terrain. The goal of this work is to develop and demonstrate the motion planning, novel
mobility mechanisms, mobility analysis, and steep terrain sampling technologies that would allow
Axel and DuAxel to be viable concepts for future scientific missions to extreme terrains.
Locomotion Rehabilitation After Severe Spinal Cord Injury
Approximately 250,000 people in the U.S. suffer from a major Spinal Cord Injury (SCI), and ~11,000
new people will be afflicted each year. Our lab collaborates with Prof. Reggie Edgerton at UCLA,
Prof. Susan Harkema at Univ. of Louisville, and Prof. Y.C. Tai here at Caltech to develop new
therapies and new technologies that hopefully one day will enable patients suffering from SCI to
partially or fully recover the ability to walk. Currently, we focus on these topics:
- Novel high density epidural spinal stimulating electrode arrays for locomotion recovery. For more on
this topic, see this link.
- New robotic mechanisms for active rehabilitation of SCI in animal (mice and rat) models.
- New adaptive training algorithms to optimize the rehabilitation afforded by robotic devices.
- Drug therapies to improve locomotion recovery.
Planning in Uncertain Environments
Probabilistic Search Strategies, IEEE Trans. Robotics, vol. 28, no.1, Feb. 2012, pp. 132-144.
- Scott C. Livingston, Richard M. Murray, and Joel W. Burdick, Backtracking
Temporal Logic Synthesis for Uncertain Environments, Proc. IEEE Int. Conf. Robotics and Automation,
May 2012, Minneapolis, MN.
- Paul Hebert, Nicolas Hudson, Jeremy Ma, Thomas Howard, Thomas Fuchs, Max Bajracharya, Joel Burdick,
Combined Shape, Appearance, and Silhouette for Simultaneous Manipulator and
Object Tracking,Proc. IEEE Int. Conf. Robotics and Automation, May 2012, Minneapolis, MN.
- N. Hudson, T. Howard, J. Ma, A. Jain, M. Bajracharya, C. Kuo, L. Matthies, P. Backes, P. Hebert, T. Fuchs, J. Burdick, End-to-End Dextrous Manipulation with Deliberate Interactive Estimation, \'\'Proc. IEEE Int. Conf. Robotics and Automation,\'\' May 2012, Minneapolis, MN.\n\n\'\'\'Axel/Mobility\'\'\'
- I.A.D. Nesnas, J.B. Matthews, P. Abad-Manterola, J.W. Burdick, J.A. Edlund, R.D. Peters, M.M. Tanner, R.N. Miyake, B.S. Solish, and R.C. Anderson, Axel and DuAxel Rovers for the Sustainable Exploration of Extreme Terrains, \'\'J. Field Robotics,\'\' Feb., 2012.
Spinal Cord Injury (SCI) Rehabilitation
Recent Research Topics
Here are a some recent research topics that were actively pursued in our group.
Human Detection & Tracking Using UWB Radar
While Ultra-Wide-Band (UWB) Radar has existed for decades, it has been more actively investigated in recent years as both an alternative wireless communication technology, as well as a biometric sensor because of its excellent ranging resolution, low power, and sensitivity to human motion. In collaboration with Prof. Hossein Hashimi at USC, we are investigating the use of UWB radar to detect and track human motion for safety and security applications.
Animal Tracking and Activity Recognition
We are interested in developing methods to automatically identify and classify "activities" in data
streams, such as video sequences. A practical application and motivation for this work is automated
tracking and recognition of biological organism behavior in controlled laboratory environments.
Sensor-Based Motion Planning and Sensor Processing
Sensor Based Planning incorporates sensor information, reflecting the current state of the
environment, into a robot\'s planning process, as opposed to classical planning , where full
knowledge of the world\'s geometry is assumed to be known prior to the planning event. Current and
recent interests of our group include
- Motion planning in Cluttered, Dynamic, and Uncertain environments
- Sensor-based motion planning algorithms
Neural Prosthetics and Brain-Machine Interfaces
A neural prosthesis is a direct brain interface that enables a human, via the use of surgically
implanted electrode arrays and associated computer decoding algorithms, to control external
electromechanical devices by pure thought alone. In this manner, some useful motor functions that
have been lost through disease or accident can be partially restored. Our lab collaborates with the
laboratories of Prof. Richard Andersen and Prof. Y.C. Tai to develop neural prostheses and brain-machine
interfaces. Our group focuses on these particular issues:
- Autonomously Positioned (robotic) Neural Recording Electrodes. To optimize the quality of
the neural signal recorded by an extracellular electrode, the active recording site must be
positioned very close (at least within 30 microns, and preferably a few microns from the soma) to
the neural cell body. However, due to blood pressure variations, breathing, and mechanical shocks,
the electrode-soma geometry varies significantly over time. We have developed algorithms which
allow an actuated electrode to autonomously reposition itself in real time to maintain high quality
- Neural decoding algorithms. A decoding algorithm attempts to decode, or decipher, the
intent of a paralyzed neural prosthetic user from the recorded electrode signals. Neural decoding
has become a well developed subject. We have chosen to explore the concept of a supervisory
decoder whose aim is to estimate the current cognitive and planning state of the prosthetic user.
E.g., is the user awake? Do they want to use the prosthetic? Are they currently in the planning
process? Do they want to execute the plan? Do the want to change or scrub the current prosthetic
action? We have chosen to formulate the design of a supervisory decoder as a problem in hybrid