Abstract: Unlike the problem of safe task and motion planning in a completely known environment, the setting where the obstacles in a robot's workspace are not initially known and are incrementally revealed online has so far received little theoretical interest, with existing algorithms usually demanding constant replanning in the presence of unanticipated conditions. In this talk, I will present a hierarchical framework for task and motion planning, that exploits recent developments in semantic SLAM and object pose and triangular mesh extraction using convolutional neural net architectures. Under specific sufficient conditions, formal results accompanying the vector field motion planner guarantee collision avoidance and convergence to fixed or slowly moving targets, for both a single robot and a robot gripping and manipulating objects. Using this reactive motion planner as a module for high-level task planning, I will discuss how we can efficiently solve geometric rearrangement tasks with legged robots or satisfy complicated temporal logic specifications involving mobile manipulation, in previously unexplored workspaces cluttered with non-convex obstacles.
Bio: Vasileios is a Postdoctoral Researcher in the Department of Electrical & Systems Engineering at the University of Pennsylvania, working with Dan Koditschek and George Pappas. His research focuses on motion and task planning with legged robots in partially known or completely unknown environments. Specifically, he works on developing algorithms that make autonomous robots capable of interacting with the physical environment around them and solving tasks that require autonomous mobile manipulation. To this end, he frequently employs tools from motion planning, topology and perception. He obtained a Ph.D. in Mechanical Engineering from the University of Pennsylvania, advised by Dan Koditschek. He also holds a M.S.E. from the University of Pennsylvania and a Diploma from the National Technical University of Athens, both in Mechanical Engineering.