Adaptive Online Distributed Optimal Control of Very-Large-Scale Robotic Systems

Abstract

This paper presents an adaptive online distributed optimal control approach that is applicable to optimal planning for very-large-scale robotics systems in highly uncertain environments. This approach is developed based on the optimal mass transport theory. It is also viewed as an online reinforcement learning and approximate dynamic programming approach in the Wasserstein-GMM space, where a novel value functional is defined based on the probability density functions of robots and the time-varying obstacle map functions describing the changing environmental information. The proposed approach is demonstrated on the path planning problem of very-largescale robotic systems where the approximated layout of obstacles in the workspace is incrementally updated by the observations of robots, and compared with some existing state-of-the-art approaches. The numerical simulation results show that the proposed approach outperforms these approaches in aspects of the average traveling distance and the energy cost.

arXiv commentControl law ${\mathcal{C}}_k$ is re-defined for the proof of Theorem 1

References in corpus (7)

• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Mean Field Multi-Agent Reinforcement Learning
• Deep Reinforcement Learning for Swarm Systems
• Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning
• Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods
• Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients
• Represented Value Function Approach for Large Scale Multi Agent Reinforcement Learning