Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
2026-04-09 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors address the challenge of teaching mobile robots to navigate socially in different real-world environments, where usual simulations fall short. They introduce a method called incremental residual reinforcement learning (IRRL) that allows robots to learn directly in the real world more efficiently, using less computing power. Their experiments show that IRRL performs as well as other methods that need more resources and helps robots adapt to new places effectively. This approach could improve how robots learn to move around among people in varied settings.
mobile robotssocial navigationreinforcement learningincremental learningresidual learningreal-world learningreplay bufferdeep learningedge devices
Authors
Haruto Nagahisa, Kohei Matsumoto, Yuki Tomita, Yuki Hyodo, Ryo Kurazume
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.