Presented By: Aerospace Engineering
Planning under Uncertainty: Theory and Practice
Jonathan P. How, Richard C. Maclaurin Professor of Aeronautics and Astronautics at Massachusetts Institute of Technology
Jonathan P. How
Richard C. Maclaurin Professor of Aeronautics and Astronautics
Massachusetts Institute of Technology
This talk will describe recent progress on planning, learning, and control of autonomous systems operating in dynamic environments, with an emphasis on addressing the planning challenges faced on various timescales. For example, autonomous robotic agents need to plan/execute safe paths and avoid imminent collisions given noisy sensory information (short timescale), interact with other dynamic agents whose intents are typically not known (medium timescale), and perform complex cooperative tasks given imperfect models and knowledge of the environment (long timescale). These planning tasks are often constrained to be done using onboard computation and perception, which typically adds significant complexity to the system. The talk will highlight several recently developed solutions to these challenges that have been implemented to robustly plan paths and demonstrate high-speed agile flight of a quadrotor in unknown, cluttered environments; autonomous navigation of ground vehicles in complex indoor environments alongside non-communicating agents; near-optimal resource-aware communication planning for distributed loop closure detection in collaborative simultaneous localization and mapping under budgeted communication; and an augmented reality testbed for testing, evaluation and verification of complex robotic systems using controlled indoor simulations of outdoor environments.
About the speaker...
Jonathan P. How, the Richard C. Maclaurin Professor of Aeronautics and Astronautics, was honored for contributions to guidance and control of air and space vehicles. He currently serves as the head of the Information sector within the Department of Aeronautics and Astronautics, is the Director of the Ford-MIT Alliance, and was a member of the USAF Scientific Advisory Board (SAB) from 2014-2017. His research focuses on planning and learning under uncertainty, and he was the control lead for the MIT DARPA Urban Challenge team.
He is the editor-in-chief of the IEEE Control Systems Magazine, associate editor for the AIAA Journal of Aerospace Information Systems, and associate editor for the IEEE Transactions on Neural Networks and Learning Systems. His work has been recognized with multiple awards, including the Institute of Navigation Burka Award, the IFAC Automatica award for best applications paper, the AeroLion Technologies Outstanding Paper Award for the Journal Unmanned Systems, the IEEE Control Systems Society Video Clip Contest, and numerous AIAA Best Paper in Conference Awards. He was awarded the Air Force Commander's Public Service Award (2017) for his contributions to the SAB. He is both an IEEE Fellow and an AIAA Fellow.
Richard C. Maclaurin Professor of Aeronautics and Astronautics
Massachusetts Institute of Technology
This talk will describe recent progress on planning, learning, and control of autonomous systems operating in dynamic environments, with an emphasis on addressing the planning challenges faced on various timescales. For example, autonomous robotic agents need to plan/execute safe paths and avoid imminent collisions given noisy sensory information (short timescale), interact with other dynamic agents whose intents are typically not known (medium timescale), and perform complex cooperative tasks given imperfect models and knowledge of the environment (long timescale). These planning tasks are often constrained to be done using onboard computation and perception, which typically adds significant complexity to the system. The talk will highlight several recently developed solutions to these challenges that have been implemented to robustly plan paths and demonstrate high-speed agile flight of a quadrotor in unknown, cluttered environments; autonomous navigation of ground vehicles in complex indoor environments alongside non-communicating agents; near-optimal resource-aware communication planning for distributed loop closure detection in collaborative simultaneous localization and mapping under budgeted communication; and an augmented reality testbed for testing, evaluation and verification of complex robotic systems using controlled indoor simulations of outdoor environments.
About the speaker...
Jonathan P. How, the Richard C. Maclaurin Professor of Aeronautics and Astronautics, was honored for contributions to guidance and control of air and space vehicles. He currently serves as the head of the Information sector within the Department of Aeronautics and Astronautics, is the Director of the Ford-MIT Alliance, and was a member of the USAF Scientific Advisory Board (SAB) from 2014-2017. His research focuses on planning and learning under uncertainty, and he was the control lead for the MIT DARPA Urban Challenge team.
He is the editor-in-chief of the IEEE Control Systems Magazine, associate editor for the AIAA Journal of Aerospace Information Systems, and associate editor for the IEEE Transactions on Neural Networks and Learning Systems. His work has been recognized with multiple awards, including the Institute of Navigation Burka Award, the IFAC Automatica award for best applications paper, the AeroLion Technologies Outstanding Paper Award for the Journal Unmanned Systems, the IEEE Control Systems Society Video Clip Contest, and numerous AIAA Best Paper in Conference Awards. He was awarded the Air Force Commander's Public Service Award (2017) for his contributions to the SAB. He is both an IEEE Fellow and an AIAA Fellow.
Explore Similar Events
-
Loading Similar Events...
