Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM

TL;DR

This paper introduces a decentralized, safe, and scalable multi-agent control method using deep FBSDEs and ADMM, ensuring safety through stochastic control barrier functions and consensus-based optimization.

Contribution

It develops a novel end-to-end differentiable framework combining deep FBSDEs with ADMM for safe, decentralized stochastic control in multi-agent systems.

Findings

Ensures safe multi-agent operation during training with collision avoidance.

Demonstrates superior scalability and computational efficiency over centralized methods.

Validates effectiveness on complex multi-robot simulation tasks.

Abstract

In this work, we propose a novel safe and scalable decentralized solution for multi-agent control in the presence of stochastic disturbances. Safety is mathematically encoded using stochastic control barrier functions and safe controls are computed by solving quadratic programs. Decentralization is achieved by augmenting to each agent's optimization variables, copy variables, for its neighbors. This allows us to decouple the centralized multi-agent optimization problem. However, to ensure safety, neighboring agents must agree on "what is safe for both of us" and this creates a need for consensus. To enable safe consensus solutions, we incorporate an ADMM-based approach. Specifically, we propose a Merged CADMM-OSQP implicit neural network layer, that solves a mini-batch of both, local quadratic programs as well as the overall consensus problem, as a single optimization problem. This layer is embedded within a Deep FBSDEs network architecture at every time step, to facilitate end-to-end differentiable, safe and decentralized stochastic optimal control. The efficacy of the proposed approach is demonstrated on several challenging multi-robot tasks in simulation. By imposing requirements on safety specified by collision avoidance constraints, the safe operation of all agents is ensured during the entire training process. We also demonstrate superior scalability in terms of computational and memory savings as compared to a centralized approach.