How to Evaluate Proving Grounds for Self-Driving? A Quantitative Approach
Authors:
- Rui ChenRCRui Chen
- Mansur AriefMAMansur Arief
- Weiyang ZhangWZWeiyang Zhang
- Ding ZhaoDZDing Zhao
Preprint
Abstract
Proving ground has been a critical component in testing and validation for Connected and Automated Vehicles (CAV). Although quite a few world-class testing facilities have been under construction over the years, the evaluation of proving grounds themselves as testing approaches has rarely been studied. In this paper, we investigate the effectiveness of CAV proving grounds by its capability to recreate real-world traffic scenarios. We extract typical use cases from naturalistic driving events leveraging non-parametric Bayesian learning techniques. Then, we contribute to a generative sample-based optimization approach to assess the compatibility between traffic scenarios and proving ground road structure. We evaluate the effectiveness of our approach with three CAV testing facilities: Mcity, Almono (Uber ATG), and Kcity. Experiments show that our approach is effective in evaluating the capability of a given CAV proving ground to accommodate real-world driving scenarios.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Understanding V2V Driving Scenarios Through Traffic PrimitivesIEEE Transactions on Intelligent Transportation Systems, 2020
- Clustering of Driving Encounter Scenarios Using Connected Vehicle TrajectoriesIEEE Transactions on Intelligent Vehicles, 2020
- Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric ApproachesIEEE Transactions on Intelligent Transportation Systems, 2018
- Artificial intelligence test: a case study of intelligent vehiclesArtificial Intelligence Review, 2018
- Extracting Traffic Primitives Directly From Naturalistically Logged Data for Self-Driving ApplicationsIEEE Robotics and Automation Letters, 2018
- Intelligence Testing for Autonomous Vehicles: A New ApproachIEEE Transactions on Intelligent Vehicles, 2016
- The European New Car Assessment Programme: A historical reviewChinese Journal of Traumatology, 2016
- Task-Specific Performance Evaluation of UGVs: Case Studies at the IVFCIEEE Transactions on Intelligent Transportation Systems, 2014
- Tracking human motion using auxiliary particle filters and iterated likelihood weightingImage and Vision Computing, 2006
- Simultaneous localization and mapping: part IIEEE Robotics & Automation Magazine, 2006