Robust Motion Planning for Multi-Robot Systems Against Position Deception Attacks

摘要

Deep reinforcement learning (DRL) is widely applied in motion planning for multi-robot systems as DRL leverages the offline training process to improve the real-time computation efficiency. In DRL-based methods, the DRL models compute an action for a robot based on the states of its surrounding obstacles, including other robots in the system. They always assume that the number of obstacles is fixed and the obtained obstacles’ states are reliable. However, in the real world, a multi-robot system may suffer from various attacks, such as remote control attacks and network attacks, that cause wrong positions of the surrounding obstacles received by a robot. In this paper, we propose a robust motion planning method <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> , integrating a denoising autoencoder (DAE) with DRL models, to mitigate such position deception attacks in environments with a different number of obstacles. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> shows the following two advantages. First, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> can be applied in benign and attacked scenarios and thus does not require any detector. It learns an encoder and a decoder to approximate the accurate positions of the obstacles, no matter under attack or not. Second, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> applies an LSTM (Long Short-Term Memory)-based DRL model to deal with a variable number of obstacles in the environment. It is worth noting that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> is method-agnostic and can be easily implemented in state-of-the-art motion planning methods. Comprehensive experiments show that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> can mitigate position deception attacks and guarantee safe motion. We also demonstrate the effectiveness and generalization of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DAE-Crit-LSTM</monospace> .