Collision avoidance refers to the set of mechanisms and strategies by which individual agents or pedestrians in a simulated or real crowd environment detect and resolve potential spatial conflicts to prevent overlap or physical contact with other agents and obstacles. It is a fundamental problem in crowd simulation and modeling because realistic, safe, and efficient crowd dynamics depend on agents being able to navigate shared spaces without interpenetration, directly impacting the plausibility and applicability of simulated scenarios for safety planning, animation, and robotics. Key variants include rule-based approaches that apply fixed behavioral heuristics, force-based methods such as the Social Force Model that treat avoidance as repulsive potential fields, and velocity-based techniques like Reciprocal Velocity Obstacles (RVO) that compute collision-free velocities by reasoning over the space of feasible motions, with data-driven methods increasingly learning avoidance behaviors directly from observed pedestrian trajectories.
Source Papers
- A review on crowd simulation and modeling ↗ — A review on crowd simulation and modeling
- Data collection methods for studying pedestrian behaviour: A systematic review ↗ — Data collection methods for studying pedestrian behaviour: A
- Data-driven Crowd Modeling Techniques: A Survey ↗ — Data-driven Crowd Modeling Techniques: A Survey
- Dimensionless numbers reveal distinct regimes in the structure and dynamics of pedestrian crowds ↗ — Dimensionless numbers reveal distinct regimes in the structu
- Physics of Human Crowds ↗ — Physics of Human Crowds
- Social force models for pedestrian traffic – state of the art ↗ — Social force models for pedestrian traffic – state of the ar
- State-of-the-art crowd motion simulation models ↗ — State-of-the-art crowd motion simulation models