Title: Adapting Random Tree Search to Fixed Wing Aerial Vehicles with Closed-Loop Prediction and Hybrid Control
Date: Monday, June 24th
Time: 1 PM EST
Location: Georgia Tech Manufacturing Institute (GTMI) Auditorium 101
Teams Link:
teams.microsoft.com
Samuel Deal
Robotics PhD Candidate
School of Aerospace Engineering
Georgia Institute of Technology
Committee:
Dr. Anirban Mazumdar (Advisor) - School of Mechanical Engineering, Georgia Institute of Technology
Dr. Shreyas Kousik - School of Mechanical Engineering, Georgia Institute of Technology
Dr. Seth Hutchinson- School of Interactive Computing, Georgia Institute of Technology
Dr. Jonathan Rogers - School of Aerospace Engineering, Georgia Institute of Technology
Dr. Kyle Williams - Distinguished Member of R&D Staff - Sandia National Labs
Abstract:
Path planning for mobile robots is a developing and evolving area of robotics research in order to improve their autonomous capabilities. UAVs present difficult challenges to path planning algorithms that require unique solutions to overcome. In this work, we suggest certain improvements to existing planning algorithms for the application of fixed-wing UAVs. We propose three aims as follows: 1) utilize hybrid control to improve flight planning and performance capabilities, 2) leverage closed-loop prediction of fixed-wing aerial vehicles for path planning decisions, and 3) apply RL techniques to learn control policies for fixed-wing aerial vehicles. In this proposal, we go over the methods to further these aims, including control architecture, planning algorithms, preliminary results, and the final objectives we hope to achieve. The key contributions we want to highlight in this work are 1) novel control schemes for fixed-wing UAVs, 2) improvements made to closed-loop path planning that leverage the forward simulation for prediction, and 3) leveraging reinforcement learning for improving the hybrid control performance.