Research on the Behavioral Dynamics Motion Planning Method of the Human-Vehicle Social Force Model

Area of Science:

• Robotics and Autonomous Systems
• Traffic Engineering and Safety

Background:

• Autonomous vehicle navigation in urban environments requires sophisticated motion planning, especially in mixed traffic with pedestrians.
• Existing models like the social force model (SFM) and behavioral dynamics model (BDM) have limitations in handling complex human-vehicle interactions.

Purpose of the Study:

• To develop an advanced human-vehicle interaction motion planning model for autonomous vehicles at complex intersections.
• To enhance pedestrian and vehicle motion planning capabilities for safer coexistence in hybrid traffic scenarios.

Main Methods:

• Established baseline motion planning for pedestrians (using SFM) and vehicles (using BDM).
• Introduced a human-vehicle interaction force and incorporated virtual forces into both SFM and BDM, creating improved models.
• Validated the model through simulation of interactive motion planning trajectories in diverse urban intersection scenarios.

Main Results:

• The improved models effectively addressed limitations of single-model approaches, enabling multibody motion planning.
• Simulated trajectories demonstrated successful avoidance of overlapping or crossing paths between pedestrians and autonomous vehicles.
• The model proved effective in preventing collisions in various complex intersection scenarios.

Conclusions:

• The proposed enhanced social force model and behavioral dynamics model provide a robust framework for human-vehicle interaction motion planning.
• This research offers significant support for the development of safer and more efficient autonomous vehicle systems in urban environments.