The Problem of Many: Efficient Multi-arm, Multi-object Task and Motion Planning with Optimality Guarantees
Thursday, March 05, 2020, 01:00pm - 04:00pm
Speaker: Rahul Shome
Location : 1 Spring Street, Room 403
Kostas Bekris, Jingjin Yu, Abdeslam Boularias, Danica Kragic (Royal Institute of Technology (KTH), Stockholm, Sweden)
Event Type: PhD Defense
Abstract: This thesis deals with task and motion planning challenges, specifically those involving manipulating multiple objects using multiple robot manipulators. The contributions range from a new foundational understanding of the problem and the conditions for achieving asymptotic optimality to devising application-oriented and efficient planning algorithms as well as experimenting on real systems. On the application side, the focus is on overcoming scalability challenges in motion planning for multiple robots, culminating in the dRRT* algorithm. Composing such motions can enable robotic systems to solve complex tasks, motivating the design of task planning algorithms for multiple arms and multiple objects using a rich set of actions, such as picks, placements and handoffs. Extensions into collaborative robotics are also considered.