Accident Prevention with Predictive Instantaneous Crowdsourcing
Training machine learning algorithms to avoid traffic accidents can be challenging because the rare occurrence of such events leads to the insufficiency of training data. The authors introduce the idea of applying instantaneous crowdsourcing to augment autonomous vehicles with collective human cognitive capability within super-human reaction time. However, because the instantaneous crowdsourcing system must prefetch possible futures in order to generate tasks, in complex real-world problems the authors would need to hire implausibly many workers to support this approach. In this work, the authors propose that predicting dangerous futures from crowd-worker input can help resolve this problem. In a formative study to inform the design of crowd prediction workflows, the authors found there are two main challenges: (1) false positives, which can initiate instantaneous crowdsourcing more than necessary, and (2) handling a large number of futures with multiple candidate objects in the scene.
- Record URL:
-
Supplemental Notes:
- © 2019 John Joon Young Chung et al.
-
Corporate Authors:
University of Michigan, Ann Arbor
Ann Arbor, MI United States 48109Center for Connected and Automated Transportation
University of Michigan Transportation Research Institute
Ann Arbor, MI United States 48109Department of Transportation
1200 New Jersey Avenue, SE
Washington, DC United States 20590 -
Authors:
- Chung, John Joon Young
- Recker, Nicholas
- Banovic, Nikola
- Xiao, Fuhu
- Barnes, Kammeran
- Lasecki, Walter S
- Publication Date: 2019
Language
- English
Media Info
- Media Type: Digital/other
- Features: Figures; References;
- Pagination: 5p
Subject/Index Terms
- TRT Terms: Autonomous vehicles; Crash avoidance systems; Crowdsourcing; Human machine systems; Machine learning
- Subject Areas: Data and Information Technology; Highways; Safety and Human Factors; Vehicles and Equipment;
Filing Info
- Accession Number: 01833344
- Record Type: Publication
- Files: TRIS, ATRI, USDOT
- Created Date: Jan 21 2022 4:47PM