Hybrid Decision Making for Scalable Multi-Agent Navigation: Integrating Semantic Maps, Discrete Coordination, and Model Predictive Control

TL;DR

This paper introduces a scalable multi-agent navigation framework that combines semantic mapping, discrete area coordination, and predictive control to improve safety, efficiency, and deadlock avoidance in dynamic environments.

Contribution

It integrates semantic maps, claim policies, and model predictive control into a unified framework for multi-agent navigation, enhancing scalability and deadlock prevention.

Findings

Effective deadlock avoidance demonstrated in simulations and experiments

Scalability achieved by removing inter-agent collision constraints

Improved navigation safety and efficiency in dynamic environments

Abstract

This paper presents a framework for multi-agent navigation in structured but dynamic environments, integrating three key components: a shared semantic map encoding metric and semantic environmental knowledge, a claim policy for coordinating access to areas within the environment, and a Model Predictive Controller for generating motion trajectories that respect environmental and coordination constraints. The main advantages of this approach include: (i) enforcing area occupancy constraints derived from specific task requirements; (ii) enhancing computational scalability by eliminating the need for collision avoidance constraints between robotic agents; and (iii) the ability to anticipate and avoid deadlocks between agents. The paper includes both simulations and physical experiments demonstrating the framework's effectiveness in various representative scenarios.