An Intention-aware and Online Driving Style Estimation Based Personalized Autonomous Driving Strategy
- PDF / 1,378,177 Bytes
- 16 Pages / 595 x 842 pts (A4) Page_size
- 18 Downloads / 204 Views
ght © 2020 KSAE/ 11810 pISSN 12299138/ eISSN 19763832
AN INTENTION-AWARE AND ONLINE DRIVING STYLE ESTIMATION BASED PERSONALIZED AUTONOMOUS DRIVING STRATEGY Bohua Sun1), Weiwen Deng1, 2)*, Jian Wu1), Yaxin Li1) and Jinsong Wang3) State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, China Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing 100191, China 3) Electrical & Control System Research Lab, GM R&D Center, 30565 William Durant Blvd., Warren, MI 48092-2031, USA 1)
2)
(Received 6 August 2019; Revised 20 December 2019; Accepted 11 February 2020) ABSTRACTAutonomous vehicles are aiming at improving driving safety and comfort. They need to perform socially accepted behaviors in complex urban scenarios including human-driven vehicles with uncertain intentions. What’s more, understanding human drivers’ driving styles that make the systems more human-like or personalized is the key to improve the system performance, in particular, the acceptance and adaption of autonomous vehicles to human passengers. In this study, a personalized intention-aware autonomous driving strategy is proposed. An online driving style identification is proposed based on double-level Multi-dimension Gaussian Hidden Markov Process (MGHMP) with arbitration mechanism and evaluated in field test. A Mixed Observable Markov Decision Process (MOMDP) is built to model the general personalized intention-aware framework. A human-like policy generation mechanism is used to generate the possible candidates to overcome the difficulty in solving MOMDP. The index of surrounding vehicles’ intention of the upper-level MGHMP is updated during each prediction time step. The weighting factors of the reward function are configured with the identification result of lower-level MGHMP. The personalized intention-aware autonomous driving strategy is evaluated on a Real-Time Intelligent Simulation Platform. Results show that the proposed strategy can achieve the online identification accuracy above 95 % and for personalized autonomous driving in scenarios mixed with human-driven vehicles with uncertain intentions. KEY WORDS : Autonomous Vehicle, Driving style, Online Identification, Intention-aware, MOMDP
1. INTRODUCTION
for driving styles are established in a variety of ways, which consist of vehicle states, human factors and their statistical characteristics (Guyonvarch et al., 2018; Martinez et al., 2018). What’s more, context awareness subsystem consisting maneuver classification and vehicle type is added to evaluate driving style (Bejani and Ghatee, 2018). The essence for driving style is the personalized decision-making process, which has great advantages in perceiving and dealing with complex, dynamic and interactive environments (Li et al., 2018a). The data-driven humanlike algorithms based on the artificial intelligence generalize to unpredictable situations and reasons in a timely manner about the interactions with many traffic participants and need to reach human-leve
Data Loading...
