Deep Learning Based Data Fusion for Sensor Fault Diagnosis and Tolerance in Autonomous Vehicles

作     者：Huihui Pan Weichao Sun Qiming Sun Huijun Gao Huihui Pan;Weichao Sun;Qiming Sun;Huijun Gao

作者机构：Research Institute of Intelligent Control and SystemsHarbin Institute of TechnologyHarbin 150001China The Ningbo Institute of Intelligent Equipment Technology Co.LtdNingbo 315200China 

出 版 物：《Chinese Journal of Mechanical Engineering》 (中国机械工程学报（英文版）)

年 卷 期：2021年第34卷第3期

页      面：158-168页

核心收录：

学科分类：082304[工学-载运工具运用工程] 08[工学] 0823[工学-交通运输工程] 

基　　金：Supported by the National Natural Science Foundation of China(Grant U1964201,Grant 61790562 and Grant 61803120) by the Fundamental Research Fundsfor the Central Universities 

主　　题：Autonomous vehicles Fault diagnosis and tolerance Object detection Data fusion 

摘      要：Environmental perception is one of the key technologies to realize autonomous *** vehicles are often equipped with multiple sensors to form a multi-source environmental perception *** sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term *** this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is *** introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of *** the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data *** show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of *** fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.