Sample Efficient Social Navigation Using Inverse Reinforcement Learning

TL;DR

This paper introduces a sample-efficient inverse reinforcement learning algorithm for socially compliant navigation, enabling robots to learn social cues from human trajectories with reduced data requirements.

Contribution

The paper presents a novel, sample-efficient IRL algorithm leveraging replay buffers to learn social navigation policies from observational data without requiring action labels.

Findings

Outperforms existing methods in accuracy and efficiency

Reduces training time and sample complexity

Successfully learns socially compliant behaviors from pedestrian data

Abstract

In this paper, we present an algorithm to efficiently learn socially-compliant navigation policies from observations of human trajectories. As mobile robots come to inhabit and traffic social spaces, they must account for social cues and behave in a socially compliant manner. We focus on learning such cues from examples. We describe an inverse reinforcement learning based algorithm which learns from human trajectory observations without knowing their specific actions. We increase the sample-efficiency of our approach over alternative methods by leveraging the notion of a replay buffer (found in many off-policy reinforcement learning methods) to eliminate the additional sample complexity associated with inverse reinforcement learning. We evaluate our method by training agents using publicly available pedestrian motion data sets and compare it to related methods. We show that our approach yields better performance while also decreasing training time and sample complexity.