Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces

Abstract

This paper presents a technique for trajectory planning based on continuously parameterized high-level actions (motion primitives) of variable duration. This technique leverages deep reinforcement learning (Deep RL) to formulate a policy which is suitable for real-time implementation. There is no separation of motion primitive generation and trajectory planning: each individual short-horizon motion is formed during the Deep RL training to achieve the full-horizon objective. Effectiveness of the technique is demonstrated numerically on a well-studied trajectory generation problem and a planning problem on a known obstacle-rich map. This paper also develops a new loss function term for policy-gradient-based Deep RL, which is analogous to an anti-windup mechanism in feedback control. We demonstrate the inclusion of this new term in the underlying optimization increases the average policy return in our numerical example.

References in corpus (13)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• Soft Actor-Critic Algorithms and Applications
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Dota 2 with Large Scale Deep Reinforcement Learning
• Model-based Reinforcement Learning: A Survey
• A Reinforcement Learning Approach for Transient Control of Liquid Rocket Engines
• Trust Region-Guided Proximal Policy Optimization
• Clipped Action Policy Gradient
• Objective Mismatch in Model-based Reinforcement Learning
• Motion Primitives for Robotic Flight Control
• Policy Optimization by Genetic Distillation

Cited by in corpus (2)

• Formal Certification Methods for Automated Vehicle Safety Assessment
• Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions