Benjamin Riviere.

Title: “What Do Robots Dream of? Search-Based Decision-Making and Control of Continuous Systems”

Abstract:What do robots dream of? My research seeks answers to this question by designing how robots simulate the effect of their actions on the future, and how they use that information to make intelligent decisions. This is formalized in a tree-search framework that solves new decision-making and control problems in real-time, provides optimality and stability guarantees, and synergizes with deep learning. However, search requires a discrete space, and therefore its application to the high-dimensional continuous world of physical robots presents challenges. In this talk, I will discuss advances in three key areas: (i) search with complex dynamics applied to a quadrotor navigating a windy arena of moving obstacles, (ii) search with uncertainty applied to a spacecraft with faulty components that must simultaneously diagnose its state and maintain safety, and (iii) search for N-player differential games applied to a swarm of quadrotors coordinating and competing for objectives.

Bio: Benjamin Riviere is a PhD student at the California Institute of Technology, advised by Prof. Soon-Jo Chung. He received the B.S. in Mechanical Engineering from Stanford University in 2017 and the M.S. in Aeronautics from Caltech in 2018. His research interests are at the intersection of search-based planning, machine-learning, and dynamical systems with applications in robotics, space autonomy, and self-driving cars. He has received multiple awards including Honorable Mention for Best Paper at IEEE RA-L and Best Graduate Student GNC paper at AIAA Scitech, and was selected as an RSS Pioneer and a Microsoft Future Leader in Robotics and AI.

Website: https://me.jhu.edu/event/meche-lcsr-iaa-seminar-ben-riviere-from-california-institute-of-technology/

Zoom: https://wse.zoom.us/j/95583667779
Meeting ID 955 8366 7779
Passcode 530803