This SGER project addresses the largely open problem of motion planning of a high-degree-of-freedom robot (such as a manipulator, a mobile manipulator, or a humanoid robot, etc.) working in a mostly unknown or uncertain and dynamic environment with unknown obstacle motions. A novel real-time adaptive motion planning approach is proposed to tackle the problem. The project focuses on investigating key issues to make the approach feasible beyond simulation in the real world with imperfect sensing. Real-world experiments will be conducted for validation.
The proposed research will significantly advance the state of the art in robot motion planning to enable more adaptive and autonomous robots and promise to broaden the application potential of robotics. This project will provide comprehensive training to student researchers in robotics. The research results could be used to attract students of all levels, especially under-represented groups, to science and technology. This project will also help enhancing outreach activities of the PI's lab related to high school students.
