# baijiuyang/collision-avoidance2

This repo is created to serve simulaion and analysis on the data collected in Jiuyang Bai's dissertation research.

Repository: https://github.com/baijiuyang/collision-avoidance2
Canonical: https://ross.abutalabs.com/products/collision-avoidance2
Language: Jupyter Notebook
License Family: other
Last push: 2026-07-03T05:12:03+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 90, release rhythm 35, longevity 100
- inputs: {"age_days": 2156, "days_push": 61, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1546, forks 121 (observed 2026-08-28T04:05:01.558654+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: simulation, machine-learning, data-science, math, data-visualization
- domain: simulation, robotics, data-science
- platform: python, cross-platform
- tags: pedestrian-modeling, dynamical-systems, ode-simulation, model-fitting, virtual-reality, behavioral-science, jupyter-notebooks, research

## Member repositories
- baijiuyang/collision-avoidance2 (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:01.558654+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:33.177028+00:00, confidence not recorded.
  - readme: https://github.com/baijiuyang/collision-avoidance2 (fetched 2026-08-28T04:05:01.558654+00:00, sha eb92f3a50142)
- Data as of 2026-08-30T08:39:29.467469+00:00.