Abstract
Autonomous vehicles for the intention of human behavior of the estimated traffic participants and their interaction is the main problem in automatic driving system. Classical cognitive theory assumes that the behavior of human traffic participants is completely reasonable when studying estimation of intention and interaction. However, according to the quantum cognition and decision theory as well as practical traffic cases, human behavior including traffic behavior is often unreasonable, which violates classical cognition and decision theory. Based on the quantum cognitive theory, this paper studies the cognitive problem of pedestrian crossing. Through the case analysis, it is proved that the Quantum-like Bayesian (QLB) model can consider the reasonability of pedestrians when crossing the street compared with the classical probability model, being more consistent with the actual situation. The experiment of trajectory prediction proves that the QLB model can cover the edge events in interactive scenes compared with the data-driven Social-LSTM model, being more consistent with the real trajectory. This paper provides a new reference for the research on the cognitive problem of intention on bounded rational behavior of human traffic participants in autonomous driving.
Highlights
Autonomous vehicles for the intention of human behavior of the estimated traffic participants and their interaction is the main problem in automatic driving system
Spired by the success of the Long-Short Term Memory Network (LSTM) applied to different sequence prediction tasks, we extended it to human trajectory prediction
A model based on quantum cognitive theory is presented, which can take irrational behaviors and marginal events into account when judging whether pedestrians are crossing the street or not and when predicting pedestrian crossing trajectory
Summary
Autonomous vehicles for the intention of human behavior of the estimated traffic participants and their interaction is the main problem in automatic driving system. The “long tail” problem of autonomous driving includes various fragmented scenarios, extreme situations and unpredictable human behavior This is related to the unreasonable behavior intention and uncertainty[6], which needs to be studied by correct and effective cognitive and decision theory. Due to the high nonlinearity of vehicle and pedestrian behavior intention, movement trajectory and their interaction, as well as the diversity of human traffic participants, it is difficult for traditional model-driven machine learning methods to achieve satisfactory accuracy in intention estimation and behavior as well as trajectory prediction in the far future.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
