Structured learning and inference for robot motion generation

Motion planning;Machine learning

Mukadam, Mustafa ; Boots, Byron Electrical and Computer Engineering Dellaert, Frank Chernova, Sonia Theodorou, Evangelos Ratliff, Nathan ; Boots, Byron

University:Georgia Institute of Technology

Department:Electrical and Computer Engineering

关键词: Motion planning;    Machine learning;   

Others  :  https://smartech.gatech.edu/bitstream/1853/61714/1/MUKADAM-DISSERTATION-2019.pdf

美国|英语

来源: SMARTech Repository

【 摘 要 】

The ability to generate motions that accomplish desired tasks is fundamental to any robotic system. Robots must be able to generate such motions in a safe and feasible manner, sufficiently quickly, and in dynamic and uncertain environments. In addressing these problems, there exists a dichotomy between traditional methods and modern learning-based approaches. Often both of these paradigms exhibit complementary strengths and weaknesses, for example, while the former are interpretable and integrate prior knowledge, the latter are data-driven and flexible to design. In this thesis, I present two techniques for robot motion generation that exploit structure to bridge this gap and leverage the best of both worlds to efficiently find solutions in real-time. The first technique is a planning as inference framework that encodes structure through probabilistic graphical models, and the second technique is a reactive policy synthesis framework that encodes structure through task-map trees. Within both frameworks, I present two strategies that use said structure as a canvas to incorporate learning in a manner that is generalizable and interpretable while maintaining constraints like safety even during learning.