Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation

TL;DR

This paper introduces NCF2, a novel algorithm for fair-delay multi-robot navigation that uses counterfactual inference to balance travel delays among agents while ensuring safety and efficiency.

Contribution

We propose NCF2, a new algorithm that addresses fairness in multi-robot navigation through counterfactual inference, improving delay fairness without sacrificing safety or efficiency.

Findings

NCF2 outperforms existing fairness-aware methods in experiments.

Counterfactual inference effectively addresses credit assignment in multi-agent navigation.

NCF2 maintains high safety and efficiency while ensuring delay fairness.

Abstract

Multi-robot navigation is the task of finding trajectories for a team of robotic agents to reach their destinations as quickly as possible without collisions. In this work, we introduce a new problem: fair-delay multi-robot navigation, which aims not only to enable such efficient, safe travels but also to equalize the travel delays among agents in terms of actual trajectories as compared to the best possible trajectories. The learning of a navigation policy to achieve this objective requires resolving a nontrivial credit assignment problem with robotic agents having continuous action spaces. Hence, we developed a new algorithm called Navigation with Counterfactual Fairness Filter (NCF2). With NCF2, each agent performs counterfactual inference on whether it can advance toward its goal or should stay still to let other agents go. Doing so allows us to effectively address the aforementioned credit assignment problem and improve fairness regarding travel delays while maintaining high efficiency and safety. Our extensive experimental results in several challenging multi-robot navigation environments demonstrate the greater effectiveness of NCF2 as compared to state-of-the-art fairness-aware multi-agent reinforcement learning methods. Our demo videos and code are available on the project webpage: https://omron-sinicx.github.io/ncf2/