Abstract

Occupancy grid mapping is an important component in a road scene understanding for autonomous driving. It can encapsulate data from heterogeneous sensor sources like radars, LiDARs, cameras and ultrasonics. At the core of occupancy grid (OG) generation, there is usually an inverse sensor model (ISM), which infers the occupancy representation from the sensor readings. Traditional ISMs are characterized by a very rigid structure, suited only for one sensor type, and specific occupancy grid representation. This paper proposes a novel ISM framework, which offers a separation between free and occupied space, supporting both Bayesian and Dempster-Shafer OG representations. The framework is especially useful when dealing with multiple different sensors where custom or preselected probability distribution can be applied. The presented ISM architecture is modular and flexible, which is described in an illustrative example of application customized for different detection sources.

Full Text

Published Version

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.