A Study of the Efficacy of Generative Flow Networks for Robotics and Machine Fault-Adaptation

作     者：Sufiyan, Zahin Golestan, Shadan Miwa, Shotaro Mitsuka, Yoshihiro Zaiane, Osmar 

作者机构：Department of Computing Science University of Alberta 8900 114 St NW EdmontonABT6G 2S4 Canada Advanced Technology R&D Center Mitsubishi Electric Corporation 8-1-1 Tsukaguchi-honmachi Amagasaki-shi Hyogo661-8661 Japan Information Technology R&D Center Mitsubishi Electric Corporation 5-1-1 Ofuna Kamakura-shi Kanagawa247-8501 Japan Alberta Machine Intelligence Institute 10065 Jasper Ave #1101 EdmontonABT5J 3B1 Canada 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2025年

核心收录：

主　　题：Generative adversarial networks 

摘      要：Advancements in robotics have opened possibilities to automate tasks in various fields such as manufacturing, emergency response and healthcare. However, a significant challenge that prevents robots from operating in real-world environments effectively is out-of-distribution (OOD) situations, wherein robots encounter unforseen situations. One major OOD situations is when robots encounter faults, making fault adaptation essential for real-world operation for robots. Current state-of-the-art reinforcement learning algorithms show promising results but suffer from sample inefficiency, leading to low adaptation speed due to their limited ability to generalize to OOD situations. Our research is a step towards adding hardware fault tolerance and fast fault adaptability to machines. In this research, our primary focus is to investigate the efficacy of generative flow networks in robotic environments, particularly in the domain of machine fault adaptation. We simulated a robotic environment called Reacher in our experiments. We modify this environment to introduce four distinct fault environments that replicate real-world machines/robot malfunctions. The empirical evaluation of this research indicates that continuous generative flow networks (CFlowNets) indeed have the capability to add adaptive behaviors in machines under adversarial conditions. Furthermore, the comparative analysis of CFlowNets with reinforcement learning algorithms also provides some key insights into the performance in terms of adaptation speed and sample efficiency. Additionally, a separate study investigates the implications of transferring knowledge from pre-fault task to post-fault environments. Our experiments confirm that CFlowNets has the potential to be deployed in a real-world machine and it can demonstrate adaptability in case of malfunctions to maintain functionality. © 2025, CC BY.