Neural‐network‐based event‐triggered adaptive security path following control of autonomous ground vehicles subject to abnormal actuator signal
Hongtao Sun, Pengfei Zhang, Chen Peng, Yajian Zhang
Abstract
Abstract The malicious physical attacks from both sensor and actuator sides make real threats to the security and safety of autonomous ground vehicles (AGVs). This paper focuses on the problem of neural‐network‐based event‐triggered adaptive security control (ET‐ASC) scheme for path following of AGVs subject to arbitrary abnormal actuator signal. First, we assume that an arbitrary abnormal signal is caused by arbitrary malicious attacks or disturbances from actuators. Then, radial basis function neural network (RBF‐NN) is used to reconstruct such abnormal actuator signal. Second, modelling issues on security path following control of AGVs with Sigmoid‐like ETC scheme are shown when the AGV is suffering from abnormal actuator signal. In what follows, an ET‐ASC scheme is developed to mitigate the adverse effects of abnormal actuator signal with the reconstructed abnormal signal based on a novel Sigmoid‐like event‐triggered communication scheme. By using the proposed RBF‐NN‐based ET‐ASC scheme, control performance can be guaranteed under arbitrary malicious actuator signal rather than such attacks following a specific probability distribution. Final, some simulation experiments are provided to verify the effectiveness of proposed ET‐ASC scheme.