baijiuyang/collision-avoidance2

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1546 stars · 121 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A computational modeling framework for pedestrian moving-obstacle avoidance behavior, implementing Fajen-style steering and Cohen-style avoidance models with ODE simulation and model fitting via SciPy optimization. It also includes VR experiment scripts for data collection and Jupyter notebooks for data import, simulation, and analysis.

Use cases

• simulate pedestrian steering and obstacle avoidance trajectories with ODEs
• fit approach and avoidance models to human movement data
• analyze VR experiment data on moving obstacle avoidance
• compare alternative steering and evasion model variants
• visualize simulated and observed walking trajectories
• run cross-validated model fitting pipelines

When to choose

• you study human locomotion, steering, or obstacle avoidance behavior
• you need dynamical systems models of goal approach and obstacle evasion
• you want to replicate or extend the Bai movObst2 VR experiments
• you need SciPy-based optimization for fitting behavioral models

When to avoid

• you need a general-purpose robotics collision avoidance planner
• you want a ready-made real-time navigation system
• you need a maintained library with a formal license for production use
• your work is unrelated to pedestrian locomotion research

Facets

library · maturity active

simulation machine-learning data-science math data-visualization simulation robotics data-science python cross-platform pedestrian-modeling dynamical-systems ode-simulation model-fitting virtual-reality behavioral-science jupyter-notebooks research

Member repositories

For agents

markdown · JSON · MCP: product_card(name="baijiuyang/collision-avoidance2")