Autonomous Vehicles’ Turning Motion Planning for Conflict Areas at Mixed-Flow Intersections
- 25 November 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 5 (2) , 204-216
Abstract
An essential task for autonomous vehicles (AVs) is turning at mixed-flow intersections which need to interact with motorized, non-motorized and pedestrian flow simultaneously. In order to handle the multi-interaction environment and uncertainty in perception detection, this paper proposes a hierarchical framework dividing the highly-related driving process into decision, plan and action layers. The decision layer firstly employs logit model combined with Bayes‛ theorem to make discrete choice about whether to turn. Then, the plan layer initializes the local trajectory to the selected waypoints considering the location of the interacting objects by distance potential field. Next, the action layer adjusts the local trajectory and calculates the control parameters of the AV under the impact of the artificial potential field. Finally, feedback is triggered to adjust the decision and trajectory plan when the collision risk increases due to the unexpected behavior of other objects. Furthermore, extend Kalman filter is used to tackle the sensor data noise of AVs. The proposed model is tested at two intersections and the results show the travel time doesn't show statistical significant difference with vehicles that driven by human being. Meanwhile, the AVs have better performance in the aspects of safety and comfort than manually driving.Keywords
Funding Information
- National Key Research and Development Program of China Stem Cell and Translational Research (2018YFB1600505)
- National Natural Science Foundation of China (U1764261)
This publication has 38 references indexed in Scilit:
- Differentiating between Left-Turn Gap and Lag Acceptance at Unsignalized Intersections as a Function of the Site CharacteristicsJournal of Transportation Engineering, 2012
- Autonomous vehicles control in the VisLab Intercontinental Autonomous ChallengeAnnual Reviews in Control, 2012
- Sampling-based algorithms for optimal motion planningThe International Journal of Robotics Research, 2011
- Methodologies for Aggregating Indicators of Traffic ConflictTransportation Research Record: Journal of the Transportation Research Board, 2011
- Analysis of Naturalistic Driving Event DataTransportation Research Record: Journal of the Transportation Research Board, 2011
- Planning under Uncertainty for Robotic Tasks with Mixed ObservabilityThe International Journal of Robotics Research, 2010
- Path Planning for Autonomous Vehicles in Unknown Semi-structured EnvironmentsThe International Journal of Robotics Research, 2010
- Analysis of Driver Behavior in Dilemma Zones at Signalized IntersectionsTransportation Research Record: Journal of the Transportation Research Board, 2007
- Tracking with debiased consistent converted measurements versus EKFIEEE Transactions on Aerospace and Electronic Systems, 1993
- Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systemsIEEE Transactions on Automatic Control, 1979