*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Improving Motion Primitive-based Planning for Dynamic Environments via Reinforcement Learning and Genetic Algorithms
Date: Monday, December 5, 2022
Time: 1PM EST
Location: MRDC 4211, Virtual
Zachary Goddard
Robotics PhD Student
School of Mechanical Engineering
Georgia Institute of Technology
Committee:
Dr. Anirban Mazumdar (Advisor) – School of Mechanical Engineering, Georgia Institute of Technology
Dr. Jonathan Rogers – School of Aerospace Engineering, Georgia Institute of Technology
Dr. Panagiotis Tsiotras – School of Aerospace Engineering, Georgia Institute of Technology
Dr. Seth Hutchinson – School of Interactive Computing, Georgia Institute of Technology
Dr. Kyle Williams – Pathfinder Technologies, Sandia National Laboratories
Abstract:
Motion primitives provide a powerful means of rapid kinodynamic planning; however, the design of an effective primitive library for complex systems or tasks requires substantial expert knowledge. This work proposes an autonomous framework for learning motion primitives with minimal human input and demonstrates the process on simulated F-16 dynamics for navigation with and without obstacles. The framework combines deep reinforcement learning with our own contributions in the form of algorithms and shaping rewards to generate and select motion primitives for a maneuver automaton. Additionally, we contribute our own heuristics and post-processing algorithm to improve planning time with a state-of-the-art search algorithm, Hybrid A*. The demonstrated examples show significant improvement to the time to reach the goal on navigation tasks. This proposal also presents further work to extend this framework's application to adversarial tasks, such as aerial dogfighting. Future work will include a formulation of game tree search to apply motion primitives to solve games with continuous state and action spaces. This search algorithm will be demonstrated with primitives learned directly from the adversarial environment using our framework.
