Comparability of Automated Vehicle Crash Databases

• URL: http://arxiv.org/abs/2308.00645v1
• Date: Tue, 1 Aug 2023 16:23:06 GMT
• Title: Comparability of Automated Vehicle Crash Databases
• Authors: Noah Goodall
• Abstract summary: Regulators and developers compare automated vehicle crash rates to baseline, human-driven crash rates. Crash rates among databases may be directly comparable only with significant filtering and normalization, if at all.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Advanced driving assistance systems are available on many late-model vehicles, and automated driving systems are testing on public roads. Regulators and developers continue to assess the safety of these vehicles by comparing automated vehicle crash rates to baseline, human-driven crash rates. While there are several widely-cited automated vehicle and conventional vehicle crash databases, these databases have different underlying assumptions and inclusion criteria. Crash rates among databases may be directly comparable only with significant filtering and normalization, if at all. This paper reviews current automated vehicle and baseline human-driven crash databases and evaluates their comparability. Recommendations are presented to improve their comparability, both in terms of normalization and contextualization, as well as additional data fields that can be incorporated into existing databases. These findings may assist researchers, regulators, and automated vehicle developers attempting to evaluate the safety of driving automation systems.

Related papers

• Traffic and Safety Rule Compliance of Humans in Diverse Driving Situations [48.924085579865334]
  Analyzing human data is crucial for developing autonomous systems that replicate safe driving practices. This paper presents a comparative evaluation of human compliance with traffic and safety rules across multiple trajectory prediction datasets.
  arXiv  Detail & Related papers  (2024-11-04T09:21:00Z)
• Methods to Estimate Advanced Driver Assistance System Penetration Rates in the United States [0.0]
  This paper examines methods to estimate the proportion of vehicles equipped with advanced driver assistance systems (ADAS) in the United States. In 2022, between 8% and 25% of vehicles were equipped with various ADAS features, though actual usage rates were lower due to driver deactivation. Study proposes strategies to enhance estimates, including analyzing crash data, expanding event data recorder capabilities, conducting naturalistic driving studies, and collaborating with manufacturers to determine installation rates.
  arXiv  Detail & Related papers  (2024-08-01T17:17:33Z)
• Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers? [60.51287814584477]
  This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs. We develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios.
  arXiv  Detail & Related papers  (2024-05-14T09:42:21Z)
• A Bayesian Approach for Prioritising Driving Behaviour Investigations in Telematic Auto Insurance Policies [0.6249768559720121]
  We make use of trip GPS and accelerometer data, augmented by geospatial information, to train an imperfect classifier for delivery driving on a per-trip basis. A posterior probability is converted to a priority score, which was used to select the most valuable candidates for manual investigation. The approach has achieved a significant improvement in efficiency of human resource allocation compared to manual searching.
  arXiv  Detail & Related papers  (2024-04-22T15:26:24Z)
• Automated Automotive Radar Calibration With Intelligent Vehicles [73.15674960230625]
  We present an approach for automated and geo-referenced calibration of automotive radar sensors. Our method does not require external modifications of a vehicle and instead uses the location data obtained from automated vehicles. Our evaluation on data from a real testing site shows that our method can correctly calibrate infrastructure sensors in an automated manner.
  arXiv  Detail & Related papers  (2023-06-23T07:01:10Z)
• A model for traffic incident prediction using emergency braking data [77.34726150561087]
  We address the fundamental problem of data scarcity in road traffic accident prediction by training our model on emergency braking events instead of accidents. We present a prototype implementing a traffic incident prediction model for Germany based on emergency braking data from Mercedes-Benz vehicles.
  arXiv  Detail & Related papers  (2021-02-12T18:17:12Z)
• Out-of-Distribution Detection for Automotive Perception [58.34808836642603]
  Neural networks (NNs) are widely used for object classification in autonomous driving. NNs can fail on input data not well represented by the training dataset, known as out-of-distribution (OOD) data. This paper presents a method for determining whether inputs are OOD, which does not require OOD data during training and does not increase the computational cost of inference.
  arXiv  Detail & Related papers  (2020-11-03T01:46:35Z)
• Ethical Decision Making During Automated Vehicle Crashes [0.0]
  Automated vehicles are expected to crash occasionally, even when all sensors, vehicle control components, and algorithms function perfectly. This study investigates automated vehicle crashing and concludes the following: (1) automated vehicles will almost certainly crash, (2) an automated vehicle's decisions preceding certain crashes will have a moral component, and (3) there is no obvious way to effectively encode complex human morals in software.
  arXiv  Detail & Related papers  (2020-10-30T14:58:17Z)
• Self-awareness in Intelligent Vehicles: Experience Based Abnormality Detection [4.721146043492144]
  This paper introduces a novel method to detect abnormalities based on internal cross-correlation parameters of the vehicle. It is possible to train a Dynamic Bayesian Network (DBN) model to automatically evaluate and detect when the vehicle is potentially misbehaving.
  arXiv  Detail & Related papers  (2020-10-28T16:08:54Z)
• Interpretable Safety Validation for Autonomous Vehicles [44.44006029119672]
  This work describes an approach for finding interpretable failures of an autonomous system. The failures are described by signal temporal logic expressions that can be understood by a human.
  arXiv  Detail & Related papers  (2020-04-14T21:11:43Z)

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.