Micah Corah is a post-doc at the NASA Jet Propulsion Laboratory with Ali-akbar Agha-mohammadi. Micah is competing with team CoSTAR on the DARPA Subterranean Challenge working on drone and multi-robot autonomy. Micah completed a Ph.D. in Robotics at Carnegie Mellon University in fall 2020 and an M.S. in the same in 2017 both working with his advisor professor Nathan Michael. Micah's thesis involved active perception, exploration, and target tracking for aerial robots with a focus on greedy methods for distributed sensor planning. Micah received B.S. degrees in Computer Science and Mechanical Engineering from the Rensselaer Polytechnic Institute in 2015. Micah's research interests include informative planning and active perception, robotic exploration and mapping, and distributed planning and control for aerial and mobile robots.
Ph.D. in Robotics, Carnegie Mellon University
Informative planning; active perception; robotic exploration and mapping; distributed planning and control; aerial robotics; submodular maximization
NASA Jet Propulsion Laboratory, California Institute of Technology
- Advisor: Dr. Ali-akbar Agha-mohammadi
- Member of team CoSTAR, competing in the DARPA Subterranean Challenge
- Responsibilities: aerial autonomy and exploration, multi-robot autonomy, field test scouting and planning
Carnegie Mellon University
Aug 2015–Sept 2020
- Advisor: Prof. Nathan Michael
- Developed algorithms and analysis techniques for multi-robot sensing, coverage, exploration, and target tracking based on submodular maximization, higher-order monotonicity conditions, and spatial locality
- Design and analysis of a planner for exploration at high speed (2.25 m/s) with an aerial robot in collaboration with Kshitij Goel and Curtis Boirum. This system was tested in simulation and on a hexrotor robot, outdoors, on the CMU campus
- Developed a system for multi-robot exploration combining Cauchy-Schwarz mutual information for ranging sensors, Monte-Carlo tree search for path planning, and multi-robot planning via submodular maximization
- Implemented core components of a system providing control and autonomy for aerial robots. Contributions include trajectory representation and management and a modular finite state machine
- Instructor: Prof. Michael Erdmann
- Course: Mathematical Fundamentals for Robotics (16-811)
- Responsibilities: grading assignments, holding office hours
- Prepared and gave a lecture on submodular maximization
Carnegie Mellon University (Internships)
RESEARCH INTERN: PERSISTENT COVERAGE
- Advisor: Prof. Nathan Michael
- NSF Research Experience for Undergraduates (REU)
- Implemented minimum snap, collision free, multi-vehicle trajectory generation
- Implemented controller for tracking of discretized trajectories
RESEARCH INTERN: WING ASSEMBLY
- Advisor: Prof. Reid Simmons
- Developed a simulation of multi-robot assembly of an airplane wing-ladder
- Implemented an autonomous behavior where a mobile robot attaches and aligns to an airplane wing spar
Micah Corah. Sensor planning for large numbers of robots. PhD thesis, Carnegie Mellon University, 2020.
Selected journal publications:
Micah Corah and Nathan Michael. Distributed matroid-constrained submodular maximization for multi-robot exploration: theory and practice.
Autonomous Robots, 2019.
Micah Corah, Cormac O’Meadhra, Kshitij Goel, and Nathan Michael. Communication-efficient planning and mapping for multi-robot exploration
in large environments. Robotics and Automation Letters, 2019.
Erik Nelson, Micah Corah, and Nathan Michael. Environment model adaptation for mobile robot exploration. Autonomous Robots, 2018.
Selected conference publications:
Micah Corah and Nathan Michael. Scalable distributed planning for multi-robot, multi-target tracking. International Conference on Intelligent
Robots and Systems, 2021. Submitted.
Micah Corah and Nathan Michael. Volumetric objectives for multi-robot exploration of three-dimensional environments. International Confer-
ence on Robotics and Automation, 2021. Accepted.
Kshitij Goel, Micah Corah, Curtis Boirum, and Nathan Michael. Fast exploration using multirotors: Analysis, planning, and experimentation. Field
and Service Robotics, 2019.
Micah Corah and Nathan Michael. Distributed submodular maximization on partition matroids for planning on large sensor networks. Conference on Decision and Control, 2018.
Micah Corah and Nathan Michael. Efficient online multi-robot exploration via distributed sequential greedy assignment. Robotics: Science and
Micah Corah and Nathan Michael. Active estimation of mass properties for safe cooperative lifting. International Conference on Robotics and
Wennie Tabib, Micah Corah, Nathan Michael, and Red Whittaker. Computationally efficient information-theoretic exploration of pits and caves.
International Conference on Intelligent Robots and Systems, 2016.
Derek Mitchell, Micah Corah, Nilanjan Chakraborty, Katia Sycara, and Nathan Michael. Multi-robot long-term persistent coverage with fuel constrained robots. International Conference on Robotics and Automation, 2015.