Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation

TL;DR

This paper introduces Incremental Residual Reinforcement Learning (IRRL), a novel method that combines incremental learning and residual RL to improve real-world social navigation for robots, achieving efficient adaptation without replay buffers.

Contribution

The paper presents IRRL, a new RL approach that enhances learning efficiency and adaptability in real-world robot navigation without relying on replay buffers.

Findings

IRRL achieves performance comparable to traditional methods in simulation.

IRRL outperforms existing incremental learning approaches.

Robots using IRRL can adapt effectively to unseen environments in real-world tests.

Abstract

As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions vary widely across different regions, simulations cannot easily encompass all possible real-world scenarios. Real-world RL, in which agents learn while operating directly in physical environments, presents a promising solution to this issue. Nevertheless, this approach faces significant challenges, particularly regarding constrained computational resources on edge devices and learning efficiency. In this study, we propose incremental residual RL (IRRL). This method integrates incremental learning, which is a lightweight process that operates without a replay buffer or batch updates, with residual RL, which enhances learning efficiency by training only on the residuals relative to a base policy. Through the simulation experiments, we demonstrated that, despite lacking a replay buffer, IRRL achieved performance comparable to those of conventional replay buffer-based methods and outperformed existing incremental learning approaches. Furthermore, the real-world experiments confirmed that IRRL can enable robots to effectively adapt to previously unseen environments through the real-world learning.