Multi-Robot Cooperative Navigation in Crowds: A Game-Theoretic Learning-Based Model Predictive Control Approach

TL;DR

This paper presents a game-theoretic, learning-based control framework for multi-robot navigation in crowded environments, integrating social behavior prediction and coordinated decision-making.

Contribution

It introduces a novel combination of model predictive control and game theory for multi-robot coordination amid human crowds, with both centralized and distributed solutions.

Findings

Effective robot coordination demonstrated in simulations

Integration of social trajectory forecasting improves navigation safety

Game-theoretic approach enhances multi-robot decision-making

Abstract

In this paper, we develop a control framework for the coordination of multiple robots as they navigate through crowded environments. Our framework comprises of a local model predictive control (MPC) for each robot and a social long short-term memory model that forecasts pedestrians' trajectories. We formulate the local MPC formulation for each individual robot that includes both individual and shared objectives, in which the latter encourages the emergence of coordination among robots. Next, we consider the multi-robot navigation and human-robot interaction, respectively, as a potential game and a two-player game, then employ an iterative best response approach to solve the resulting optimization problems in a centralized and distributed fashion. Finally, we demonstrate the effectiveness of coordination among robots in simulated crowd navigation.