In this work, we consider the safety-oriented performance of 3D object detectors in autonomous driving contexts. Specifically, despite impressive results shown by the mass literature, developers often find it hard to ensure the safe deployment of these learning-based perception models. Attributing the challenge to the lack of safety-oriented metrics, we hereby present uncompromising spatial constraints (USC), which characterize a simple yet important localization requirement demanding the predictions to fully cover the objects when seen from the autonomous vehicle. The constraints, as we formulate using the perspective and bird's-eye views, can be naturally reflected by quantitative measures, such that having an object detector with a higher score implies a lower risk of collision. Finally, beyond model evaluation, we incorporate the quantitative measures into common loss functions to enable safety-oriented fine-tuning for existing models. With experiments using the nuScenes dataset and a closed-loop simulation, our work demonstrates such considerations of safety notions at the perception level not only improve model performances beyond accuracy but also allow for a more direct linkage to actual system safety.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving


    Contributors:


    Publication date :

    2024-09-24


    Size :

    793529 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    RefineNet: Refining Object Detectors for Autonomous Driving

    Rajaram, Rakesh Nattoji / Ohn-Bar, Eshed / Trivedi, Mohan Manubhai | IEEE | 2016


    Peugeot 306 Cabriolet - an uncompromising open-top design

    Moon,L. / Peugeot,FR / Pininfarina,IT | Automotive engineering | 1994


    Robustness and Deployability of Deep Object Detectors in Autonomous Driving

    Adam, Ganesh / Chitalia, Vibhav / Simha, Namrata et al. | IEEE | 2019