Abstract:
This paper proposes a method for reducing false warnings at road intersections, which uses a novel multi model rule based approach for long term trajectory predictions (1...Show MoreMetadata
Abstract:
This paper proposes a method for reducing false warnings at road intersections, which uses a novel multi model rule based approach for long term trajectory predictions (1s–3s) and incorporates road crossing angle as additional input from the environment. Two major contributions to the field of collision warning have resulted from this research. First, an 8-state variable vehicle motion model is expanded from CTRA model and incorporates yaw-acceleration and acceleration-gradient as additional input variables. Second, a set of motion models are selected based on vehicle maneuver mode and turning phases. The crucial component is the incorporating road crossing angle in the switching logic. The system is tested using simulated and real world data and is shown to reduce false warnings by reducing long term trajectory prediction errors.
Published in: 2014 IEEE Intelligent Vehicles Symposium Proceedings
Date of Conference: 08-11 June 2014
Date Added to IEEE Xplore: 17 July 2014
Electronic ISBN:978-1-4799-3638-0
Print ISSN: 1931-0587