Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Path Planning Using Wassertein Distributionally Robust Deep Q-learning

Alpturk, Cem and Renganathan, Venkatraman LU (2023)
Abstract
We investigate the problem of risk averse robot path planning using the deep reinforcement learning and distributionally robust optimization perspectives. Our problem formulation involves modelling the robot as a stochastic linear dynamical system, assuming that a collection of process noise samples is available. We cast the risk averse motion planning problem as a Markov decision process and propose a continuous reward function design that explicitly takes into account the risk of collision with obstacles while encouraging the robot’s motion towards the goal. We learn the risk-averse robot control actions through Lipschitz approximated Wasserstein distributionally robust deep Q-learning to hedge against the noise uncertainty. The learned... (More)
We investigate the problem of risk averse robot path planning using the deep reinforcement learning and distributionally robust optimization perspectives. Our problem formulation involves modelling the robot as a stochastic linear dynamical system, assuming that a collection of process noise samples is available. We cast the risk averse motion planning problem as a Markov decision process and propose a continuous reward function design that explicitly takes into account the risk of collision with obstacles while encouraging the robot’s motion towards the goal. We learn the risk-averse robot control actions through Lipschitz approximated Wasserstein distributionally robust deep Q-learning to hedge against the noise uncertainty. The learned control actions result in a safe and risk averse trajectory from the source to the goal, avoiding all the obstacles. Various supporting numerical simulations are presented to demonstrate our proposed approach. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
in press
subject
host publication
European Control Conference
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
project
Scalable Control of Interconnected Systems
language
English
LU publication?
yes
id
76561318-f9e2-4904-8109-ff215780a362
date added to LUP
2023-04-06 13:31:32
date last changed
2023-04-18 13:44:03
@inbook{76561318-f9e2-4904-8109-ff215780a362,
  abstract     = {{We investigate the problem of risk averse robot path planning using the deep reinforcement learning and distributionally robust optimization perspectives. Our problem formulation involves modelling the robot as a stochastic linear dynamical system, assuming that a collection of process noise samples is available. We cast the risk averse motion planning problem as a Markov decision process and propose a continuous reward function design that explicitly takes into account the risk of collision with obstacles while encouraging the robot’s motion towards the goal. We learn the risk-averse robot control actions through Lipschitz approximated Wasserstein distributionally robust deep Q-learning to hedge against the noise uncertainty. The learned control actions result in a safe and risk averse trajectory from the source to the goal, avoiding all the obstacles. Various supporting numerical simulations are presented to demonstrate our proposed approach.}},
  author       = {{Alpturk, Cem and Renganathan, Venkatraman}},
  booktitle    = {{European Control Conference}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Path Planning Using Wassertein Distributionally Robust Deep Q-learning}},
  url          = {{https://lup.lub.lu.se/search/files/142814377/2211.02372.pdf}},
  year         = {{2023}},
}