MetaTOC stay on top of your field, easily

Mobile robot path planning based on the improved DDPG algorithm

, , , , ,

Transactions of the Institute of Measurement and Control

Published online on

Abstract

Transactions of the Institute of Measurement and Control, Volume 48, Issue 12, Page 3341-3351, August 2026.
An improved Deep Deterministic Policy Gradient (DDPG) algorithm, integrating self-attention mechanisms, adversarial training, and prioritized experience replay, is proposed to address the limitations of state representation capability, sample efficiency, ...