SORBET: A Framework to Evaluate the Robustness of LiDAR 3D Object Detection and Its Impacts on Autonomous Driving
Modern autonomous driving systems (ADS) require real-time input from multiple sensors to make time-sensitive decisions using multiple deep neural network systems. This makes the correctness of those decisions crucial to the adoption of ADS as errors can cause significant loss. Sensors such as LiDAR for obstacle detections are sensitive to environmental changes and built-in inaccuracies and may fluctuate over time (i.e., frame to frame). While there has been extensive work to test ADS, it remains unclear whether the current ADS are robust against very subtle changes in LiDAR output data (i.e., point cloud data). In this work, we study the impact of the built-in inaccuracies in LiDAR sensors on LiDAR-3D obstacle detection models (i.e., deep neural network models) to provide insight into how they can impact the obstacle detection module (i.e., robustness) and by extension the trajectory prediction module (i.e., how the robustness of obstacle detection would impact on autonomous driving).
We propose a framework SORBET, that applies subtle perturbations to LiDAR data, evaluates the robustness of LiDAR-3D obstacle detection, and further assesses the impacts on the trajectory prediction module and ADS.
We applied SORBET to evaluate the robustness of five classic LiDAR-3D obstacle detection models, including one from an industry-grade Level 4 ADS (Baidu’s Apollo). Furthermore, we studied how the changes in the obstacle detection results would negatively impact trajectory prediction and ADS in a cascading fashion. Our evaluation highlights the importance of testing the robustness of LiDAR-3D obstacle detection models against subtle perturbations. We find that even very subtle changes in point cloud data (i.e., removing two points) may introduce a non-trivial decrease in the detection performance. Furthermore, we find that such a negative impact will further propagate to impact other modules in ADS, which may endanger the safety of ADS.
Wed 17 JulDisplayed time zone: Brasilia, Distrito Federal, Brazil change
10:30 - 11:00 | |||
10:30 30mPoster | MicroSensor: Towards an Extensible Tool for the Static Analysis of Microservices Systems in Continuous Integration Posters Edson Soares Instituto Atlantico & State University of Ceara (UECE), Matheus Paixao State University of Ceará, Allysson Allex Araújo Federal University of Cariri | ||
10:30 30mPoster | SORBET: A Framework to Evaluate the Robustness of LiDAR 3D Object Detection and Its Impacts on Autonomous Driving Posters | ||
10:30 30mPoster | An Analysis of the Costs and Benefits of Autocomplete in IDEs Posters Shaokang Jiang University of California, San Diego, Michael Coblenz University of California, San Diego | ||
10:30 30mPoster | Go the Extra Mile: Fixing Propagated Error-Handling Bugs Posters Haoran Liu National University of Defense Technology, Zhouyang Jia National University of Defense Technology, Huiping Zhou National University of Defense Technology, Haifang Zhou National University of Defense Technology, Shanshan Li National University of Defense Technology | ||
10:30 30mPoster | Hybrid Regression Test Selection by Synergizing File and Method Call Dependences Posters Luyao Liu College of Computer, National University of Defense Technology, Guofeng Zhang College of Computer, National University of Defense Technology, Zhenbang Chen College of Computer, National University of Defense Technology, Ji Wang School of Computer, National University of Defense Technology, China | ||
10:30 30mPoster | Do Large Language Models Generate Similar Codes from Mutated Prompts?: A Case Study of Gemini Pro Posters DOI Pre-print Media Attached File Attached | ||
10:30 30mPoster | Towards Realistic SATD Identification Through Machine Learning Models: Ongoing Research and Preliminary Results Posters Eliakim Gama State University of Ceará, Matheus Paixao State University of Ceará, Mariela I. Cortés State University of Ceará, Lucas Monteiro State University of Ceará DOI Pre-print | ||
10:30 30mPoster | Building Software Engineering Capacity through a University Open Source Program Office Posters | ||
10:30 30mPoster | Inferring Natural Preconditions via Program Transformation Posters | ||
10:30 30mPoster | RFNIT: Robotic Framework for Non-Invasive Testing Posters Davi Simoes Freitas Centro de Informática at Universidade Federal de Pernambuco, Breno Miranda Centro de Informática at Universidade Federal de Pernambuco, Juliano Iyoda Centro de Informática at Universidade Federal de Pernambuco |
This room is conjoined with the Foyer to provide additional space for the coffee break, and hold poster presentations throughout the event.