Real-Time Inter-Vehicle Data Fusion Based on a New Metric for Evidence Distance in Autonomous Vehicle Systems

Safety is a major concern for autonomous vehicle driving. The autonomous vehicles relying solely on ego-vehicle sensors have limitations in dealing with collisions. The risk can be reduced by communicating with other vehicles sharing sensed information. In this paper, we study a real-time multisource data fusion scheme based on Dempster-Shafer theory of evidence (DS) through cooperative vehicle-to-vehicle (V2V) communications. The classical DS can produce erroneous outputs when confidences are highly conflicting. In particular, a false negative error on object detection may lead to serious accidents. We propose a novel metric to measure distance between confidences on the collected data taking the asymmetry in the importance of sensed events into account. Based on the proposed distance, we consider the weighted DS combination in order to fuse multiple confidences. The proposed scheme is simple, and enables the vehicles to combine confidences in real-time. From real-world experiments, we show that it is feasible to lower the false negative rate by the proposed data fusion scheme, and to avoid accidents using the proposed collision warning system.