Dynamic Goal Tracking for Differential Drive Robot using Deep Reinforcement Learning
Authors:
Preprint
- 2 November 2022
- preprint
- Published by Springer Nature in Research Square
Abstract
To ensure the steady navigation for robot stable controls are one of the basic requirements. Control values selection is highly environment dependent. To ensure reusability of control parameter system needs to generalize over the environment. Adding adaptability in robots to perform effectively in the environments with no prior knowledge reinforcement leaning is a promising approach. However, tuning hyper parameters and attaining correlation between state space and reward function to train a stable reinforcement learning agent is a challenge. In this paper we designed a continuous reward function to minimizing the sparsity and stabilizes the policy convergence, to attain control generalization for differential drive robot. We Implemented Twin Delayed Deep Deterministic Policy Gradient on Open-AI Gym Race Car. System was trained to achieve smart primitive control policy, moving forward in the direction of goal by maintaining an appropriate distance from walls to avoid collisions. Resulting policy was tested on unseen environments including dynamic goal environment, boundary free environment and continuous path environment on which it outperformed Deep Deterministic Policy Gradient.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Twin Delayed Deep Deterministic Policy Gradient-Based Target Tracking for Unmanned Aerial Vehicle With Achievement Rewarding and Multistage TrainingIEEE Access, 2022
- Deep reinforcement learning based control for Autonomous Vehicles in CARLAMultimedia Tools and Applications, 2022
- Deep Reinforcement Learning-Based Accurate Control of Planetary Soft LandingSensors, 2021
- Reinforcement Learning versus Conventional Control for Controlling a Planar Bi-rotor Platform with Tail AppendageJournal of Intelligent & Robotic Systems, 2021
- ARI: the Social Assistive Robot and Companion2020
- Optimal Torque Distribution Control of Multi-Axle Electric Vehicles with In-wheel Motors Based on DDPG AlgorithmEnergies, 2020
- Learning to Walk Via Deep Reinforcement Learning2019
- A review of mobile robots: Concepts, methods, theoretical framework, and applicationsInternational Journal of Advanced Robotic Systems, 2019
- MIT Cheetah 3: Design and Control of a Robust, Dynamic Quadruped Robot2018
- Model learning for robot control: a surveyCognitive Processing, 2011