Autonomous Navigation of Unmanned Vehicle Through Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning approach using DDPG for autonomous navigation of unmanned vehicles, demonstrating superior path planning performance over traditional algorithms in simulation.

Contribution

The paper introduces the application of DDPG to high-dimensional continuous control for unmanned vehicle navigation, with experimental validation showing improved results.

Findings

DDPG outperforms DQN and DDQN in path planning tasks

Simulation results confirm the feasibility of the DDPG-based navigation method

The approach effectively handles high-dimensional continuous action spaces

Abstract

This paper explores the method of achieving autonomous navigation of unmanned vehicles through Deep Reinforcement Learning (DRL). The focus is on using the Deep Deterministic Policy Gradient (DDPG) algorithm to address issues in high-dimensional continuous action spaces. The paper details the model of a Ackermann robot and the structure and application of the DDPG algorithm. Experiments were conducted in a simulation environment to verify the feasibility of the improved algorithm. The results demonstrate that the DDPG algorithm outperforms traditional Deep Q-Network (DQN) and Double Deep Q-Network (DDQN) algorithms in path planning tasks.