ALAN: Adaptive Learning for Multi-Agent Navigation

TL;DR

ALAN introduces an adaptive, scalable approach for multi-agent navigation that enables agents to dynamically choose velocities for efficient, collision-free movement, outperforming existing methods in speed and safety.

Contribution

This work presents ALAN, a novel adaptive method allowing agents to independently optimize their velocities for improved global navigation efficiency.

Findings

Agents using ALAN reach destinations faster than ORCA and Social Forces.

ALAN is highly scalable for large multi-agent systems.

Experimental results demonstrate superior performance of ALAN in crowded environments.

Abstract

In multi-agent navigation, agents need to move towards their goal locations while avoiding collisions with other agents and static obstacles, often without communication with each other. Existing methods compute motions that are optimal locally but do not account for the aggregated motions of all agents, producing inefficient global behavior especially when agents move in a crowded space. In this work, we develop methods to allow agents to dynamically adapt their behavior to their local conditions. We accomplish this by formulating the multi-agent navigation problem as an action-selection problem, and propose an approach, ALAN, that allows agents to compute time-efficient and collision-free motions. ALAN is highly scalable because each agent makes its own decisions on how to move using a set of velocities optimized for a variety of navigation tasks. Experimental results show that the agents using ALAN, in general, reach their destinations faster than using ORCA, a state-of-the-art collision avoidance framework, the Social Forces model for pedestrian navigation, and a Predictive collision avoidance model.