Robust motion planning for mobile robots under attacks against obstacle localization

• Published in: Robotica 2024-08, Vol.42 (8), p.2781-2800
• Main Authors: Wu, Fenghua, Tang, Wenbing, Zhou, Yuan, Lin, Shang-Wei, Ding, Zuohua, Liu, Yang
• Format: Article
• Language: English
• Subjects: Algorithms; Approximation; Barriers; Collision avoidance; Efficiency; Generative adversarial networks; Global positioning systems; GPS; Localization; Methods; Motion planning; Performance evaluation; Planning; Real time; Robot control; Robot dynamics; Robots; Robust control; Sensors; Velocity
• ISSN: 0263-5747; 1469-8668
• DOI: 10.1017/S0263574724001115

Thanks to its real-time computation efficiency, deep reinforcement learning (DRL) has been widely applied in motion planning for mobile robots. In DRL-based methods, a DRL model computes an action for a robot based on the states of its surrounding obstacles, including other robots that may communicate with it. These methods always assume that the environment is attack-free and the obtained obstacles’ states are reliable. However, in the real world, a robot may suffer from obstacle localization attacks (OLAs), such as sensor attacks, communication attacks, and remote-control attacks, which cause the robot to retrieve inaccurate positions of the surrounding obstacles. In this paper, we propose a robust motion planning method ObsGAN-DRL, integrating a generative adversarial network (GAN) into DRL models to mitigate OLAs in the environment. First, ObsGAN-DRL learns a generator based on the GAN model to compute the approximation of obstacles’ accurate positions in benign and attack scenarios. Therefore, no detectors are required for ObsGAN-DRL. Second, by using the approximation positions of the surrounding obstacles, ObsGAN-DRL can leverage the state-of-the-art DRL methods to compute collision-free motion commands (e.g., velocity) efficiently. Comprehensive experiments show that ObsGAN-DRL can mitigate OLAs effectively and guarantee safety. We also demonstrate the generalization of ObsGAN-DRL.