Self-Driving Cars and Driver Alertness

• URL: http://arxiv.org/abs/2107.14036v1
• Date: Tue, 20 Jul 2021 23:55:44 GMT
• Title: Self-Driving Cars and Driver Alertness
• Authors: Nguyen H Tran and Abhaya C Nayak
• Abstract summary: Poor alertness while controlling self-driving cars could hinder the drivers' ability to intervene during unpredictable situations. We make some recommendations for various stakeholders, such as researchers, drivers, industry and policy makers.
• Score: 16.00431760297241
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent years have seen growing interest in the development of self-driving vehicles that promise (or threaten) to replace human drivers with intelligent software. However, current self-driving cars still require human supervision and prompt takeover of control when necessary. Poor alertness while controlling self-driving cars could hinder the drivers' ability to intervene during unpredictable situations, thus increasing the risk of avoidable accidents. In this paper we examine the key factors that contribute to drivers' poor alertness, and the potential solutions that have been proposed to address them. Based on this examination we make some recommendations for various stakeholders, such as researchers, drivers, industry and policy makers.

Related papers

• 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)
• Considering Human Factors in Risk Maps for Robust and Foresighted Driver Warning [1.4699455652461728]
  We propose a warning system that uses human states in the form of driver errors. The system consists of a behavior planner Risk Maps which directly changes its prediction of the surrounding driving situation. In different simulations of a dynamic lane change and intersection scenarios, we show how the driver's behavior plan can become unsafe.
  arXiv  Detail & Related papers  (2023-06-06T16:39:58Z)
• Infrastructure-based End-to-End Learning and Prevention of Driver Failure [68.0478623315416]
  FailureNet is a recurrent neural network trained end-to-end on trajectories of both nominal and reckless drivers in a scaled miniature city. It can accurately identify control failures, upstream perception errors, and speeding drivers, distinguishing them from nominal driving. Compared to speed or frequency-based predictors, FailureNet's recurrent neural network structure provides improved predictive power, yielding upwards of 84% accuracy when deployed on hardware.
  arXiv  Detail & Related papers  (2023-03-21T22:55:51Z)
• FBLNet: FeedBack Loop Network for Driver Attention Prediction [75.83518507463226]
  Nonobjective driving experience is difficult to model. In this paper, we propose a FeedBack Loop Network (FBLNet) which attempts to model the driving experience accumulation procedure. Under the guidance of the incremental knowledge, our model fuses the CNN feature and Transformer feature that are extracted from the input image to predict driver attention.
  arXiv  Detail & Related papers  (2022-12-05T08:25:09Z)
• Drivers' attention detection: a systematic literature review [62.997667081978825]
  Many factors can contribute to distractions while driving, since objects or events to physiological conditions, as drowsiness and fatigue, do not allow the driver to stay attentive. The technological progress allowed the development and application of many solutions to detect the attention in real situations. Our work presents a Systematic Literature Review of the methods and criteria used to detect attention of drivers at the wheel.
  arXiv  Detail & Related papers  (2022-04-06T11:36:40Z)
• Adversarial Deep Reinforcement Learning for Trustworthy Autonomous Driving Policies [5.254093731341154]
  We show that adversarial examples can be used to help autonomous cars improve their deep reinforcement learning policies. By using a high fidelity urban driving simulation environment and vision-based driving agents, we demonstrate that the autonomous cars retrained using the adversary player noticeably increase the performance of their driving policies.
  arXiv  Detail & Related papers  (2021-12-22T15:00:16Z)
• Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving [104.32241082170044]
  We study a new task, safety-aware motion prediction with unseen vehicles for autonomous driving. Unlike the existing trajectory prediction task for seen vehicles, we aim at predicting an occupancy map. Our approach is the first one that can predict the existence of unseen vehicles in most cases.
  arXiv  Detail & Related papers  (2021-09-03T13:33:33Z)
• Behavioral Research and Practical Models of Drivers' Attention [21.70169149901781]
  This report covers the literature on changes in drivers' visual attention due to factors, internal and external to the driver. It links cross-disciplinary theoretical and behavioral research on driver's attention to practical solutions. This report is based on over 175 behavioral studies, nearly 100 practical papers, 20 datasets, and over 70 surveys published since 2010.
  arXiv  Detail & Related papers  (2021-04-12T17:42:04Z)
• DeepTake: Prediction of Driver Takeover Behavior using Multimodal Data [17.156611944404883]
  We present DeepTake, a novel deep neural network-based framework that predicts multiple aspects of takeover behavior. Using features from vehicle data, driver biometrics, and subjective measurements, DeepTake predicts the driver's intention, time, and quality of takeover. Results show that DeepTake reliably predicts the takeover intention, time, and quality, with an accuracy of 96%, 93%, and 83%, respectively.
  arXiv  Detail & Related papers  (2020-12-31T04:24:46Z)
• Emergent Road Rules In Multi-Agent Driving Environments [84.82583370858391]
  We analyze what ingredients in driving environments cause the emergence of road rules. We find that two crucial factors are noisy perception and agents' spatial density. Our results add empirical support for the social road rules that countries worldwide have agreed on for safe, efficient driving.
  arXiv  Detail & Related papers  (2020-11-21T09:43:50Z)
• Affordable Modular Autonomous Vehicle Development Platform [0.0]
  1.25 million people die annually from road accidents and Africa has the highest rate of road fatalities. Financial constraints prevent viable experimentation and research into self-driving technology in Africa. This paper describes the design of RollE, an affordable modular autonomous vehicle development platform.
  arXiv  Detail & Related papers  (2020-06-20T22:51:48Z)

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.