Autonomy Talks - Yuxiao Chen: Towards Safe Multiagent Autonomy скачать в хорошем качестве

Autonomy Talks - Yuxiao Chen: Towards Safe Multiagent Autonomy

Autonomy Talks - 29/03/2021 Speaker: Dr. Yuxiao Chen, AMBER Lab, California Institute of Technology Title: Towards safe multi agent autonomy Abstract: Autonomy has the potential to change the society in which we live for the better, and the first requirement for autonomous systems is safety. In particular, many important applications such as transportation, robotics, and power networks involve multiple agents, which poses additional challenges to the design of safe autonomy such as controllability and scalability. This talk presents some new results on the synthesis of safe multiagent autonomy and contains two parts. The first part discusses the case where agents collaborate and focuses on a contract-based approach that guarantees safety with decentralized implementation. The second part discusses the case where agents do not collaborate and focuses on a data-driven reactive modeling framework for these non-collaborating agents and the subsequent motion planning under the reactive model. Bio: Yuxiao Chen is currently a Postdoctoral researcher from the California Institute of Technology working on safe autonomy. He obtained his B.S. from Tsinghua University in 2013 and his Ph.D. in mechanical engineering from the University of Michigan in 2018. His research centers around safety-critical autonomy and multi-agent systems with applications such as autonomous vehicles, robotics, and power networks. If you want to know more, check: https://idsc.ethz.ch/research-frazzol...