Object criticality for safer navigation
Not on the map. Why?
Abstract (arXiv)
Object detection in autonomous driving consists in perceiving and locating instances of objects in multi-dimensional data, such as images or lidar scans. Very recently, multiple works are proposing to evaluate object detectors by measuring their ability to detect the objects that are most likely to interfere with the driving task. Detectors are then ranked according to their ability to detect the most relevant objects, rather than the highest number of objects. However there is little evidence so far that the relevance of predicted object may contribute to the safety and reliability improvement of the driving task. This position paper elaborates on a strategy, together with partial results, to i) configure and deploy object detectors that successfully extract knowledge on object relevance, and ii) use such knowledge to improve the trajectory planning task. We show that, given an object detector, filtering objects based on their relevance, in combination with the traditional confidence threshold, reduces the risk of missing relevant objects, decreases the likelihood of dangerous trajectories, and improves the quality of trajectories in general.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 25 Apr 2024.
Builds on
20 of 29 references.
References · 20
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
- 2020Designing Network Design Spacescited by 954
- 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
- 2021Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillationcited by 131
- 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
- 2023Motion Planning for Autonomous Driving: The State of the Art and Future Perspectivescited by 112
- 2019A Survey of Deep Learning-based Object Detectioncited by 106
- 2018Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detectioncited by 82
- 2020SSN: Shape Signature Networks for Multi-class Object Detection from Point Cloudscited by 74
8 more
- 2020Learning to Evaluate Perception Models Using Planner-Centric Metricscited by 49
- 2019Learning an Uncertainty-Aware Object Detector for Autonomous Drivingcited by 34
- 2023On Offline Evaluation of 3D Object Detection for Autonomous Drivingcited by 11
- 2021Risk Ranked Recall: Collision Safety Metric for Object Detection Systems in Autonomous Vehiclescited by 10
- 2020Safety-Aware Hardening of 3D Object Detection Neural Network Systemscited by 9
- 2022Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measurescited by 8
- 2022Interaction-Dynamics-Aware Perception Zones for Obstacle Detection Safety Evaluationcited by 5
- 2022Verifiable Obstacle Detectioncited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.