Abstract
Grid-based perception techniques in the automotive sector based on fusing information from different sensors and their robust perceptions of the environment are proliferating in the industry. However, one of the main drawbacks of these techniques is the traditionally prohibitive, high computing performance that is required for embedded automotive systems. In this work, the capabilities of new computing architectures that embed these algorithms are assessed in a real car. The paper compares two ad hoc optimized designs of the Bayesian Occupancy Filter; one for General Purpose Graphics Processing Unit (GPGPU) and the other for Field-Programmable Gate Array (FPGA). The resulting implementations are compared in terms of development effort, accuracy and performance, using datasets from a realistic simulator and from a real automated vehicle.
Highlights
Intelligent vehicle technology is advancing at a vertiginous pace
The SMX is the architectural block around which General Purpose Graphics Processing Unit (GPGPU) scalability is built
The accuracy of each implementation was calculated as the mismatch between the results obtained with the reference Matlab code running the simulated dataset and the results offered by the corresponding GPGPU or Field-Programmable Gate Array (FPGA) version
Summary
Intelligent vehicle technology is advancing at a vertiginous pace. The complexity of some highly uncertain and dynamic urban driving scenarios still hampers the deployment of fully automated vehicles. One of the most important challenges in those scenarios is the accurate perception of static and moving objects, to properly understand the spatio-temporal relationship between the subject vehicle and the relevant entities. In well structured driving environments, such as highways, the types of static and dynamic objects are modeled and tracked using geometrical models and their parameters. Urban driving scenarios are so heterogeneous and unpredictable that they are extremely complex to manage under a feature-based perception paradigm. The associated tracking methodology raises the classic problem of object association and state estimation, which are highly coupled
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
