HTRON:Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm

07/08/2022
by   Kasun Weerakoon, et al.
0

We present a novel approach to improve the performance of deep reinforcement learning (DRL) based outdoor robot navigation systems. Most, existing DRL methods are based on carefully designed dense reward functions that learn the efficient behavior in an environment. We circumvent this issue by working only with sparse rewards (which are easy to design), and propose a novel adaptive Heavy-Tailed Reinforce algorithm for Outdoor Navigation called HTRON. Our main idea is to utilize heavy-tailed policy parametrizations which implicitly induce exploration in sparse reward settings. We evaluate the performance of HTRON against Reinforce, PPO and TRPO algorithms in three different outdoor scenarios: goal-reaching, obstacle avoidance, and uneven terrain navigation. We observe in average an increase of 34.41 decrease in the average time steps taken to reach the goal, and a 24.9 decrease in the elevation cost compared to the navigation policies obtained by the other methods. Further, we demonstrate that our algorithm can be transferred directly into a Clearpath Husky robot to perform outdoor terrain navigation in real-world scenarios.

READ FULL TEXT

page 6

page 7

research
05/18/2022

Sim-to-Real Strategy for Spatially Aware Robot Navigation in Uneven Outdoor Environments

Deep Reinforcement Learning (DRL) is hugely successful due to the availa...
research
09/11/2018

Danger-aware Weighted Advantage Composition of Deep Reinforcement Learning for Robot Navigation

Self-navigation, referring to automatically reaching the goal while avoi...
research
08/06/2021

A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning

Deep Reinforcement Learning (DRL) is a promising approach for teaching r...
research
06/12/2022

Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies

In this paper, we present a novel Heavy-Tailed Stochastic Policy Gradien...
research
05/07/2022

AdaptiveON: Adaptive Outdoor Navigation Method For Stable and Reliable Actions

We present a novel outdoor navigation algorithm to generate stable and e...
research
08/12/2023

CoverNav: Cover Following Navigation Planning in Unstructured Outdoor Environment with Deep Reinforcement Learning

Autonomous navigation in offroad environments has been extensively studi...
research
10/20/2020

Learn to Navigate Maplessly with Varied LiDAR Configurations: A Support Point Based Approach

Deep reinforcement learning (DRL) demonstrates great potential in maples...

Please sign up or login with your details

Forgot password? Click here to reset