Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay

Park, Minjae; Park, Chaneun; Kwon, Nam Kyu

doi:10.3390/biomimetics9010051

Open AccessArticle

Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay

by

Minjae Park

¹,

Chaneun Park

² and

Nam Kyu Kwon

^1,*

¹

Department of Electronic Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea

²

School of Electronics Engineering, Kyungpook National University, Daegu 41566, Republic of Korea

^*

Author to whom correspondence should be addressed.

Biomimetics 2024, 9(1), 51; https://doi.org/10.3390/biomimetics9010051

Submission received: 1 November 2023 / Revised: 10 January 2024 / Accepted: 11 January 2024 / Published: 13 January 2024

(This article belongs to the Special Issue Artificial Intelligence for Autonomous Robots 2024)

Download

Browse Figures

Review Reports Versions Notes

Abstract

In this paper, we propose a reinforcement learning-based end-to-end learning method for the autonomous driving of a mobile robot in a dynamic environment with obstacles. Applying two additional techniques for reinforcement learning simultaneously helps the mobile robot in finding an optimal policy to reach the destination without collisions. First, the multifunctional reward-shaping technique guides the agent toward the goal by utilizing information about the destination and obstacles. Next, employing the hindsight experience replay technique to address the experience imbalance caused by the sparse reward problem assists the agent in finding the optimal policy. We validated the proposed technique in both simulation and real-world environments. To assess the effectiveness of the proposed method, we compared experiments for five different cases.

Keywords: deep deterministic policy gradient; multifunctional reward shaping; hindsight experience replay; mobile robot; autonomous driving

Share and Cite

MDPI and ACS Style

Park, M.; Park, C.; Kwon, N.K. Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay. Biomimetics 2024, 9, 51. https://doi.org/10.3390/biomimetics9010051

AMA Style

Park M, Park C, Kwon NK. Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay. Biomimetics. 2024; 9(1):51. https://doi.org/10.3390/biomimetics9010051

Chicago/Turabian Style

Park, Minjae, Chaneun Park, and Nam Kyu Kwon. 2024. "Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay" Biomimetics 9, no. 1: 51. https://doi.org/10.3390/biomimetics9010051

APA Style

Park, M., Park, C., & Kwon, N. K. (2024). Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay. Biomimetics, 9(1), 51. https://doi.org/10.3390/biomimetics9010051

Article Menu

Autonomous Driving of Mobile Robots in Dynamic Environments Based on Deep Deterministic Policy Gradient: Reward Shaping and Hindsight Experience Replay

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI