Development of Point-cloud Processing Algorithm for Self-Driving Challenges

Abstract

The paper proposes an own-developed point-cloud processing algorithm which was developed for the Autonomous Urban Concept competition organized by Shell. The approach does not intend to solve general-purpose object recognition and tracking, although the methodologies presented can be used as general solutions. Our approach will be presented in comprehensive manner, the challenges and solutions will be detailed. Also, the dysfunctional ideas will be listed, and alternative workarounds will be presented as recommendations too. As verification of the algorithm, both simulation and real-world measurements will be presented. For the sake of research and open source, we share datasets and necessary information publicly.