Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach

Abstract

The potential of autonomous driving technology to revolutionize the transportation industry has attracted significant attention. Path following, a fundamental task in autonomous driving, involves accurately and safely guiding a vehicle along a specified path. Conventional path-following methods often rely on rule-based or parameter-tuning aspects, which may not be adaptable to complex and dynamic scenarios. Reinforcement learning (RL) has emerged as a promising approach that can learn effective control policies from experience without prior knowledge of system dynamics. This paper investigates the effectiveness of the Deep Deterministic Policy Gradient (DDPG) algorithm for steering control in ground vehicle path following. The algorithm quickly converges and the trained agent achieves stable and fast path following, outperforming three baseline methods. Additionally, the agent achieves smooth control without excessive actions. These results validate the proposed approach’s effectiveness, which could contribute to the development of autonomous driving technology.

A Deep Reinforcement Learning Strategy for Surrounding Vehicles-Based Lane-Keeping Control

“…The DDPG RL algorithm has demonstrated its potential in the field of control by outperforming traditional path control methods when applied to vehicles following predefined paths [ 33 ]. The DDPG algorithm employs the actor–critic network framework to update the actor and critic models [ 34 ].…”

Path Following for Autonomous Mobile Robots with Deep Reinforcement Learning

“…Ensuring the adaptability of the policy to various challenges is crucial, as it cultivates the ability to handle generalized scenarios, thereby reducing the risk of overfitting to specific paths. We employed a stochastic path generation algorithm proposed in our previous work [ 35 ], randomly generating a reference path for the robot to follow at the beginning of each episode. In this paper, the parameters of the stochastic path generation algorithm is defined with , m, and m. Straight paths with a generation probability of are also introduced into the training.…”