Corpus ID: 233388051

Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data

@article{Rangesh2021AutonomousVT,
  title={Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data},
  author={Akshay Rangesh and Nachiket Deo and Ross Greer and Pujitha Gunaratne and Mohan Manubhai Trivedi},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.11489}
}
With increasing automation in passenger vehicles, the study of safe and smooth occupant-vehicle interaction and control transitions is key. In this study, we focus on the development of contextual, semantically meaningful representations of the driver state, which can then be used to determine the appropriate timing and conditions for transfer of control between driver and vehicle. To this end, we conduct a largescale real-world controlled data study where participants are instructed to take… Expand

Figures and Tables from this paper

Predicting Take-over Time for Autonomous Driving with Real-World Data: Robust Data Augmentation, Models, and Evaluation
TLDR
This work develops and train take-over time (TOT) models that operate sequentially on mid and high-level features produced by computer vision algorithms operating on different driver-facing camera views, showing models trained on the augmented dataset to outperform the initial dataset. Expand
Gaze Preserving CycleGANs for Eyeglass Removal & Persistent Gaze Estimation.
TLDR
The proposed Gaze Preserving CycleGAN (GPCycleGAN) is trained to preserve the driver's gaze while removing potential eyeglasses from face images through image-to-image translation using generative adversarial networks to pre-process images prior to gaze estimation. Expand

References

SHOWING 1-10 OF 23 REFERENCES
Transition of control in a partially automated vehicle: Effects of anticipation and non-driving-related task involvement
Abstract Vehicle automation is expected to improve traffic safety. However, previous research indicates that high levels of automation may bring about unintended consequences, specifically inExpand
Looking at Hands in Autonomous Vehicles: A ConvNet Approach Using Part Affinity Fields
TLDR
This article introduces a fast ConvNet approach, based on the work of original work of OpenPose by Cao, et al. for full body joint estimation, showing at least 95% detection performance on joint localization and arm-angle estimation. Expand
Multimodal Cue Combinations: A Possible Approach to Designing In-Vehicle Takeover Requests for Semi-autonomous Driving
TLDR
Findings indicate that trimodal combinations result in the shortest response time to takeover alerts, and may contribute to the development of theory regarding the design of takeover request alert systems within (semi) autonomous vehicles. Expand
Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness
TLDR
This article presents an extensive naturalistic driving dataset of drivers in a conditionally autonomous vehicle running on Californian freeways, and defines a metric for the driver's take-over readiness termed the ‘Observable Readiness Index (ORI)’ based on the ratings. Expand
Takeover Time in Highly Automated Vehicles: Noncritical Transitions to and From Manual Control
TLDR
It is found that drivers take longer to resume control when under no time pressure compared with that reported in the literature, and that drivers occupied by a secondary task exhibit larger variance and slower responses to requests to resumes control. Expand
Noncritical State Transitions During Conditionally Automated Driving on German Freeways: Effects of Non–Driving Related Tasks on Takeover Time and Takeover Quality
TLDR
Investigating the driver’s takeover performance when switching from working on different non–driving related tasks while driving with a conditionally automated driving function (SAE L3), which was simulated by a Wizard of Oz vehicle, to manual vehicle control under naturalistic driving conditions found timings found can be used to design comfortable and safe takeover concepts for automated vehicles. Expand
Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles
TLDR
This work introduces the novel domain-specific Drive&Act benchmark for fine-grained categorization of driver behavior, and provides challenging benchmarks by adopting prominent methods for video- and body pose-based action recognition. Expand
Age differences in the takeover of vehicle control and engagement in non-driving-related activities in simulated driving with conditional automation.
TLDR
It was found that both younger and older drivers engaged in various non-driving-related activities during the automated driving portion, with distinct preferences on the type of activity for each age group (i.e., while younger drivers mostly used an electronic device, older drivers tended to converse). Expand
On Performance Evaluation of Driver Hand Detection Algorithms: Challenges, Dataset, and Metrics
TLDR
An extensive, public, naturalistic videobased hand detection dataset in the automotive environment that highlights the challenges that may be observed in naturalistic driving settings, from different background complexities, illumination settings, users, and viewpoints is introduced. Expand
Driver Gaze Zone Estimation Using Convolutional Neural Networks: A General Framework and Ablative Analysis
TLDR
The authors' best performing model achieves an accuracy of 95.18% during cross-subject testing, outperforming current state-of-the-art techniques for this task, and demonstrates good generalization capabilities. Expand
...
1
2
3
...