skip to main content


Title: Transporting Children in Autonomous Vehicles: An Exploratory Study
Objective: Identify factors that impact parents’ decisions about allowing an unaccompanied child to ride in an autonomous vehicle (AV). Background: AVs are being tested in several U.S. cit-ies and on highways in multiple states. Meanwhile, suburban parents are using ride sharing services to shuttle children from school to extracurricular activities. Parents may soon be able to hire AVs to transport children. Method: Nineteen parents of 8- to 16-year-old children, and some of their children, rode in a driving simulator in autonomous mode, then were interviewed. Parents also participated in focus groups. Topics included minimum age for solo child passengers, types of trips unaccompanied children might take, and vehicle features needed to support child passengers. Results: Parents would require two-way audio communication and prefer video feeds of vehicle interiors, seat belt checks, automatic locking, secure passenger identification, and remote access to vehicle information. Parents cited convenience as the greatest benefit and fear that AVs could not pro-ect passengers during unplanned trip interruptions as their greatest concern. Conclusion: Manufacturers have an opportunity to design family-friendly AVs from the outset, rather than retro-fit them to be safe for child passengers. More research, especially usability studies where families interact with technology prototypes, is needed to understand how AV design impacts child passengers. Application: Potential applications of this research include not only designing vehicles that can be used to safely transport children, seniors who no longer drive, and individuals with disabilities but also developing regulations, policies, and societal infrastructure to support safe child transport via AVs  more » « less
Award ID(s):
1741306
NSF-PAR ID:
10205321
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Human factors
Volume:
62
Issue:
2
ISSN:
0018-7208
Page Range / eLocation ID:
278-287
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Autonomous Vehicle (AV) technology has the potential to significantly improve driver safety. Unfortunately, driver could be reluctant to ride with AVs due to the lack of trust and acceptance of AV’s driving styles. The present study investigated the impact of driver’s driving style (aggressive/defensive) and the designed driving styles of AVs (aggressive/defensive) on driver’s trust, acceptance, and take-over behavior in fully autonomous vehicles. Thirty-two participants were classified into two groups based on their driving styles using the Aggressive Driving Scale and experienced twelve scenarios in either an aggressive AV or a defensive AV. Results revealed that drivers’ trust, acceptance, and takeover frequency were significantly influenced by the interaction effects between AV’s driving style and driver’s driving style. The findings implied that driver’s individual differences should be considered in the design of AV’s driving styles to enhance driver’s trust and acceptance of AVs and reduce undesired take over behaviors. 
    more » « less
  2. Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale lidar data. Surprisingly, although semantic class labels naturally follow a long-tailed distribution, contemporary benchmarks focus on only a few common classes (e.g., pedestrian and car) and neglect many rare classes in-the-tail (e.g., debris and stroller). However, AVs must still detect rare classes to ensure safe operation. Moreover, semantic classes are often organized within a hierarchy, e.g., tail classes such as child and construction-worker are arguably subclasses of pedestrian. However, such hierarchical relationships are often ignored, which may lead to misleading estimates of performance and missed opportunities for algorithmic innovation. We address these challenges by formally studying the problem of Long-Tailed 3D Detection (LT3D), which evaluates on all classes, including those in-the-tail. We evaluate and innovate upon popular 3D detection codebases, such as CenterPoint and PointPillars, adapting them for LT3D. We develop hierarchical losses that promote feature sharing across common-vs-rare classes, as well as improved detection metrics that award partial credit to "reasonable" mistakes respecting the hierarchy (e.g., mistaking a child for an adult). Finally, we point out that fine-grained tail class accuracy is particularly improved via multimodal fusion of RGB images with LiDAR; simply put, small fine-grained classes are challenging to identify from sparse (lidar) geometry alone, suggesting that multimodal cues are crucial to long-tailed 3D detection. Our modifications improve accuracy by 5% AP on average for all classes, and dramatically improve AP for rare classes (e.g., stroller AP improves from 3.6 to 31.6)! Our code is available at this https URL. 
    more » « less
  3. Self-driving autonomous vehicles (AVs) have recently gained popularity as a research topic. The safety of AVs is exceptionally important as failure in the design of an AV could lead to catastrophic consequences. AV systems are highly heterogeneous with many different and complex components, so it is difficult to perform end-to-end testing. One solution to this dilemma is to evaluate AVs using simulated racing competition. In this thesis, we present a simulated autonomous racing competition, Generalized RAcing Intelligence Competition (GRAIC). To compete in GRAIC, participants need to submit their controller files which are deployed on a racing ego-vehicle on different race tracks. To evaluate the submitted controller, we also developed a testing pipeline, Autonomous System Operations (AutOps). AutOps is an automated, scalable, and fair testing pipeline developed using software engineering techniques such as continuous integration, containerization, and serverless computing. In order to evaluate the submitted controller in non-trivial circumstances, we populate the race tracks with scenarios, which are pre-defined traffic situations commonly seen in the real road. We present a dynamic scenario testing strategy that generates new scenarios based on results of the ego-vehicle passing through previous scenarios. 
    more » « less
  4. Autonomous vehicles (AV), one of the transportation industry’s biggest innovations of the past few decades, bring the promise of safer roads and significantly lower vehicle-related fatalities. While many studies have found largely positive consumer opinions regarding operating and owning such a vehicle, older adults (55+) tend to express concerns about the safety and operational risks of a vehicle with unknown capabilities. To investigate how older adults and AVs may interact, we conducted an improv- style enactment-based participatory design pilot study. We found that initial concerns about trust and safety can be diminished through training and repetitive successful vehicle operation. Additionally, our participants provided insights into the AV design considerations, needs, and interactions for older adults. These findings add to the collective body of autonomous vehicle research by demonstrating that the needs of this growing population, who may benefit significantly from access to AVs, should be considered by manufacturers. 
    more » « less
  5. Trajectory prediction is a critical component for autonomous vehicles (AVs) to perform safe planning and navigation. However, few studies have analyzed the adversarial robustness of trajectory prediction or investigated whether the worst-case prediction can still lead to safe planning. To bridge this gap, we study the adversarial robustness of trajectory prediction models by proposing a new adversarial attack that perturbs normal vehicle trajectories to maximize the prediction error. Our experiments on three models and three datasets show that the adversarial prediction increases the prediction error by more than 150%. Our case studies show that if an adversary drives a vehicle close to the target AV following the adversarial trajectory, the AV may make an inaccurate prediction and even make unsafe driving decisions. We also explore possible mitigation techniques via data augmentation and trajectory smoothing. 
    more » « less