Key points are not available for this paper at this time.
Situational awareness on road networks, defined with respect to perception of adverse road conditions (e.g., potholes) in addition to motorists, pedestrians and other artifacts that are crucial to enabling autonomous driving functionality, is a critical requirement for a multitude of applications in intelligent transportation systems where an increasing number of autonomous vehicles are expected to be present. For instance, ride comfort, which is adversely affected by road anomalies, is a much more pronounced concern for autonomous vehicles where humans are driven (most likely as a paid service) compared to traditional automobiles (being driven by humans). Towards developing efficient and cost-effective solutions for generating timely road situational awareness data, this paper describes a target-tracking formulation that exploits ubiquitous sensing and processing capabilities in modern automobiles. The problem formulation presented in this paper is fundamentally different to the traditional target tracking as voluntarily participating motor-vehicles are used as mobile sensors for detection and tracking in comparison to sensors that actively detect and track targets. A simplified example on initial detection and tracking the evolution of potholes is utilized for illustration of the proposed concept.
Garg et al. (Thu,) studied this question.