The idea behind collective perception is to improve vehicles' awareness about their surroundings. Every vehicle shares information describing its perceived environment by means of V2X communication. Similar to other information shared using V2X communication, collective perception information is potentially safety relevant, which means there is a need to assess the reliability and quality of received information before further processing. Transmitted information may have been forged by attackers or contain inconsistencies e.g. caused by malfunctions. This paper introduces a novel approach for estimating a belief that a pair of entities, e.g. two remote vehicles or the host vehicle and a remote vehicle, within a Vehicular ad hoc Network (VANET) are both trustworthy. The method updates the belief based on the consistency of the data that both entities provide. The evaluation shows that the proposed method is able to identify forged information.
29 December 2020 in IEEE Transactions on Intelligent Transportation Systems
The fusion of tracks with different state spaces is referred to as heterogeneous track-to-track fusion (HT2TF). In this paper, we present novel approaches for HT2TF using Covariance Intersection (CI). The underlying idea is to augment the low dimensional track. We investigate whether the augmentation approaches proposed for mode mixing in the Interacting Multiple Model (IMM) algorithm can also be employed for the CI. As the augmentation influences the CI optimization, we compare different optimization variants. Finally, we evaluate the presented approaches for collective perception.