# ucla-mobility/OpenCDA

A generalized framework for prototyping full-stack cooperative driving automation applications under CARLA+SUMO.

Repository: https://github.com/ucla-mobility/OpenCDA
Canonical: https://ross.abutalabs.com/products/opencda
Language: Python
License: NOASSERTION
License Family: other
Topics: autonomous-driving, cooperative-driving-automation, simulation, connected-and-automated-vehicles, automated-driving-systems
Last push: 2026-08-18T19:00:03+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 2052, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1162, forks 225 (observed 2026-08-28T04:03:49.632487+00:00)

## What it is
OpenCDA is an open-source Python framework for prototyping and evaluating full-stack cooperative driving automation (CDA) applications in a CARLA+SUMO co-simulation environment. It provides modular pipelines for perception, localization, planning, control, and V2X communication, along with benchmark scenarios and algorithms.

## Use cases
- simulate cooperative adaptive cruise control and platooning scenarios
- evaluate V2X communication between connected automated vehicles
- benchmark cooperative perception algorithms in CARLA and SUMO
- prototype full-stack autonomous driving pipelines in Python
- run co-simulation of traffic flow and vehicle dynamics
- test CDA features for USDOT CARMA research

## When to choose
- you need cooperative or V2X-enabled autonomous driving simulation, which single-vehicle simulators lack
- you want an all-Python full-stack CDA research platform with benchmarks
- you need CARLA and SUMO co-simulation integration

## When to avoid
- you only need simple single-vehicle autonomous driving simulation without cooperation
- you need real-time or hardware-in-the-loop deployment rather than simulation
- you require a commercially licensed or fully production-grade driving stack

## Facets
- artifact type: framework
- maturity: active
- function: simulation, machine-learning, computer-vision, robotics
- domain: autonomous-vehicles, simulation, robotics
- platform: python, cross-platform
- tags: autonomous-driving, carla, sumo, v2x, cooperative-driving, platooning, co-simulation, connected-automated-vehicles, perception, planning-control, research, linux, docker

## Member repositories
- ucla-mobility/OpenCDA (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:49.632487+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 2026-08-30T06:31:39.980762+00:00, confidence not recorded.
  - readme: https://github.com/ucla-mobility/OpenCDA (fetched 2026-08-28T04:03:49.632487+00:00, sha 5fa9f5d30280)
- Data as of 2026-08-30T08:39:29.467469+00:00.