Howie Choset
Professor Carnegie Mellon University
- Pittsburgh PA
Howie Choset's research reduces complicated high-dimensional problems found in robotics to low-dimensional simpler ones.
Biography
Areas of Expertise
Media Appearances
HEBI Robotics promotes Raida to CEO, Rollinson to CTO
The Robot Report Staff online
2023-01-13
HEBI Robotics, a Pittsburgh-based creator of a modular platform for robotics development, named Bob Raida its CEO and Dave Rollinson CTO. Howie Choset, who has been acting CEO, has been named chairman of the board. HEBI said this change in leadership reflects its transition from providing technology to researchers to providing solutions to end-users.
CMU's Snakebot Goes for a Swim
Carnegie Mellon University News online
2021-04-13
"We can go places that other robots cannot," said Howie Choset, the Kavčić-Moura Professor of Computer Science. "It can snake around and squeeze into hard-to-reach underwater spaces." The project is led by Choset and Matt Travers, co-directors of the Biorobotics Lab.
Robotics Leaders Choset, Morris to Receive 2019 Engelberger Awards
Robotics Business Review online
2019-03-06
The Robotics Industries Association (RIA) today announced the recipients of the 2019 Engelberger Robotics Awards. Howie Choset, the Kavčić-Moura Professor of Computer Science at Carnegie Mellon University, will receive the Engelberger Robotics Award for Education, and Catherine Morris, group leader and director of automotive sales at ATI Industrial Automation, will receive the Engleberger Award for Leadership.
Interview with IJARS, with Howie Choset and Seth Hutchinson
ROBOTS Association online
2016-01-05
The IJARS team sat down at ICRA with two influential academics in robotics: Professor Howie Choset (Carnegie Mellon University) and Professor Seth Hutchinson (University of Illinois at Urbana-Champaign) to discuss some of the latest developments in robotics, what students of robotics should be focusing on, and what research they most hope to be remembered for.
The Evolution of the Bioinspired Robot
NOVA online
2013-11-17
If you're not prepared for the sight of them, Howie Choset's robot snakes can make you jump. They slither between chairs and tables in his Carnegie Mellon lab, rear their heads to peer into crevices, and inch their way along pipes on the ceiling. When dropped into a pond, they switch over to sea serpent-mode, twisting tightly as they skim through the water. Like an ophidiophobe's worst nightmare, they will even wrap around your leg and inch their way up toward your groin, if given the chance. "The benefit of the snake is that it's able to reliably get to locations that people and machines can't," Choset says.
Media
Social
Industry Expertise
Accomplishments
Fellow of the Institute of Electrical and Electronics Engineers (IEEE)
2015
MIT Technology Review TR100
2002
Education
University of Pennsylvania
B.S.Econ
Entrepreneurial Management
1990
California Institute of Technology
Ph.D.
Mechanical Engineering
1996
California Institute of Technology
M.S.
Mechanical Engineering
1991
University of Pennsylvania
B.S.Eng.
Computer Science
1990
Affiliations
- IEEE
Links
Patents
Vision Sensing Device and Method
US20230186496A1
2023-06-16
Provided is a vision sensing device including a housing, a camera, a laser pattern generator, an inertial measurement unit, and at least one processor configured to project a laser pattern within the field of view of the camera, capture inertial data from the inertial measurement unit as a user moves the housing, capture visual data from the field of view with the camera as the user moves the housing, capture depth data with the laser pattern generator as the user moves the housing, and generate an RGB-D point cloud based on the visual data, the inertial data, and the depth data.
Articles
Representation granularity enables time-efficient autonomous exploration in large, complex worlds
Science Robotics2023
We propose a dual-resolution scheme to achieve time-efficient autonomous exploration with one or many robots. The scheme maintains a high-resolution local map of the robot’s immediate vicinity and a low-resolution global map of the remaining areas of the environment. We believe that the strength of our approach lies in this low- and high-resolution representation of the environment: The high-resolution local map ensures that the robots observe the entire region in detail, and because the local map is bounded, so is the computation burden to process it.
Learning Modular Robot Control Policies
IEEE Transactions on Robotics2023
Modular robots can be rearranged into a new design, perhaps each day, to handle a wide variety of tasks by forming a customized robot for each new task. However, reconfiguring just the mechanism is not sufficient: each design also requires its own unique control policy. One could craft a policy from scratch for each new design, but such an approach is not scalable, especially given the large number of designs that can be generated from even a small set of modules.
A Curvature and Trajectory Optimization-based 3D Surface Reconstruction Pipeline for Ultrasound Trajectory Generation
2023 IEEE International Conference on Robotics and Automation (ICRA)2023
Ultrasound scanning is an efficient imaging modality preferred for quick medical procedures. However, due to the lack of skilled sonographers, researchers have developed many Robotic Ultrasound System (RUS) prototypes for various procedures. Most of these systems have a human-in-the-loop and require an expert to point the robot to the region of the subject to be scanned. Only a few systems try to incorporate some knowledge from the exterior shape of the subject for ultrasound scanning.
A Conflict-Based Search Framework for Multiobjective Multiagent Path Finding
IEEE Transactions on Automation Science and Engineering2023
Conventional multi-agent path planners typically compute an ensemble of paths while optimizing a single objective, such as path length. However, many applications may require multiple objectives, say fuel consumption and completion time, to be simultaneously optimized during planning and these criteria may not be readily compared and sometimes lie in competition with each other. The goal of the problem is thus to find a Pareto-optimal set of solutions instead of a single optimal solution.
GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation
Proceedings of The 6th Conference on Robot Learning2023
Robots have been used in all sorts of automation, and yet the design of robots remains mainly a manual task. We seek to provide design tools to automate the design of robots themselves. An important challenge in robot design automation is the large and complex design search space which grows exponentially with the number of components, making optimization difficult and sample inefficient.
