How Do We Fail? Stress Testing Perception in Autonomous Vehicles

• URL: http://arxiv.org/abs/2203.14155v1
• Date: Sat, 26 Mar 2022 20:48:09 GMT
• Title: How Do We Fail? Stress Testing Perception in Autonomous Vehicles
• Authors: Harrison Delecki, Masha Itkina, Bernard Lange, Ransalu Senanayake, Mykel J. Kochenderfer
• Abstract summary: This paper presents a method for characterizing failures of LiDAR-based perception systems for autonomous vehicles in adverse weather conditions. We develop a methodology based in reinforcement learning to find likely failures in object tracking and trajectory prediction due to sequences of disturbances.
• Score: 40.19326157052966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous vehicles (AVs) rely on environment perception and behavior prediction to reason about agents in their surroundings. These perception systems must be robust to adverse weather such as rain, fog, and snow. However, validation of these systems is challenging due to their complexity and dependence on observation histories. This paper presents a method for characterizing failures of LiDAR-based perception systems for AVs in adverse weather conditions. We develop a methodology based in reinforcement learning to find likely failures in object tracking and trajectory prediction due to sequences of disturbances. We apply disturbances using a physics-based data augmentation technique for simulating LiDAR point clouds in adverse weather conditions. Experiments performed across a wide range of driving scenarios from a real-world driving dataset show that our proposed approach finds high likelihood failures with smaller input disturbances compared to baselines while remaining computationally tractable. Identified failures can inform future development of robust perception systems for AVs.

Related papers

• Robust ADAS: Enhancing Robustness of Machine Learning-based Advanced Driver Assistance Systems for Adverse Weather [5.383130566626935]
  This paper employs a Denoising Deep Neural Network as a preprocessing step to transform adverse weather images into clear weather images. It improves driver visualization, which is critical for safe navigation in adverse weather conditions.
  arXiv  Detail & Related papers  (2024-07-02T18:03:52Z)
• Acceleration method for generating perception failure scenarios based on editing Markov process [0.0]
  This study proposes an accelerated generation method for perception failure scenarios tailored to the underground parking garage environment. The method generates an intelligent testing environment with a high density of perception failure scenarios. It edits the Markov process within the perception failure scenario data to increase the density of critical information in the training data.
  arXiv  Detail & Related papers  (2024-07-01T05:33:48Z)
• OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising [49.86409475232849]
  Trajectory prediction is fundamental in computer vision and autonomous driving. Existing approaches in this field often assume precise and complete observational data. We present a novel method for out-of-sight trajectory prediction that leverages a vision-positioning technique.
  arXiv  Detail & Related papers  (2024-04-02T18:30:29Z)
• Survey on LiDAR Perception in Adverse Weather Conditions [6.317642241067219]
  The active LiDAR sensor is able to create an accurate 3D representation of a scene. The LiDAR's performance change under adverse weather conditions like fog, snow or rain. We address topics such as the availability of appropriate data, raw point cloud processing and denoising, robust perception algorithms and sensor fusion to mitigate adverse weather induced shortcomings.
  arXiv  Detail & Related papers  (2023-04-13T07:45:23Z)
• Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction [50.79827516897913]
  We introduce an interpretable paradigm for trajectory prediction that distributes the uncertainty among semantic concepts. We validate our approach on real-world autonomous driving data, demonstrating superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-16T06:28:20Z)
• Ranking-Based Physics-Informed Line Failure Detection in Power Grids [66.0797334582536]
  Real-time and accurate detecting of potential line failures is the first step to mitigating the extreme weather impact and activating emergency controls. Power balance equations nonlinearity, increased uncertainty in generation during extreme events, and lack of grid observability compromise the efficiency of traditional data-driven failure detection methods. This paper proposes a Physics-InformEd Line failure Detector (FIELD) that leverages grid topology information to reduce sample and time complexities and improve localization accuracy.
  arXiv  Detail & Related papers  (2022-08-31T18:19:25Z)
• A Benchmark for Spray from Nearby Cutting Vehicles [7.767933159959353]
  This publication presents a testing methodology for disturbances from spray. It introduces a novel lightweight and spray setup alongside an evaluation scheme to assess the disturbances caused by spray. In a common scenario of a closely cutting vehicle, it is visible that the distortions are severely affecting the perception stack up to four seconds.
  arXiv  Detail & Related papers  (2021-08-24T15:40:09Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)
• Towards robust sensing for Autonomous Vehicles: An adversarial perspective [82.83630604517249]
  It is of primary importance that the resulting decisions are robust to perturbations. Adversarial perturbations are purposefully crafted alterations of the environment or of the sensory measurements. A careful evaluation of the vulnerabilities of their sensing system(s) is necessary in order to build and deploy safer systems.
  arXiv  Detail & Related papers  (2020-07-14T05:25:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.