Verifiable Obstacle Detection
Not on the map. Why?
Abstract (arXiv)
Perception of obstacles remains a critical safety concern for autonomous vehicles. Real-world collisions have shown that the autonomy faults leading to fatal collisions originate from obstacle existence detection. Open source autonomous driving implementations show a perception pipeline with complex interdependent Deep Neural Networks. These networks are not fully verifiable, making them unsuitable for safety-critical tasks. In this work, we present a safety verification of an existing LiDAR based classical obstacle detection algorithm. We establish strict bounds on the capabilities of this obstacle detection algorithm. Given safety standards, such bounds allow for determining LiDAR sensor properties that would reliably satisfy the standards. Such analysis has as yet been unattainable for neural network based perception systems. We provide a rigorous analysis of the obstacle detection system with empirical results based on real-world sensor data.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 105 references that are in the map. First posted on arXiv 30 Aug 2022.
Builds on
26 of 105 references.
References · 26
- 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
- 2016Safety Verification of Deep Neural Networkscited by 263
- 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
- 2019Algorithms for Verifying Deep Neural Networkscited by 221
- 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
- 2020Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systemscited by 100
- 2020Verification of Deep Convolutional Neural Networks Using ImageStarscited by 75
- 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 63
- 2021Introduction to Neural Network Verificationcited by 63
14 more
- 2021A Review of Formal Methods applied to Machine Learningcited by 33
- 2020Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Taskscited by 31
- 2016Engineering Safety in Machine Learningcited by 24
- 2019Weather Influence and Classification with Automotive Lidar Sensorscited by 24
- 2021Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attackscited by 24
- 2020Unsupervised Object Detection with LiDAR Cluescited by 22
- 2022Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillationcited by 19
- 2021Adversarial Attacks on Camera-LiDAR Models for 3D Car Detectioncited by 16
- 2018Occlusion-Aware Risk Assessment for Autonomous Driving in Urban Environmentscited by 13
- 2020DeepDyve: Dynamic Verification for Deep Neural Networkscited by 12
- 2021Risk Ranked Recall: Collision Safety Metric for Object Detection Systems in Autonomous Vehiclescited by 10
- 2020Ethical Decision Making During Automated Vehicle Crashescited by 6
- 2021LiDAR Cluster First and Camera Inference Later: A New Perspective Towards Autonomous Drivingcited by 4
- 2018Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detectioncited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 0; 2026: 1.
3 papers.