vita-epfl/social-nce

[ICCV] Social NCE: Contrastive Learning of Socially-aware Motion Representations

44
/ 100
Emerging

This project helps improve how robots and autonomous vehicles navigate safely through crowded spaces. It takes observed trajectories of people or objects and produces a model that predicts future movements, significantly reducing the likelihood of collisions. This is ideal for roboticists, autonomous vehicle engineers, or anyone developing systems that operate in close proximity to humans or other dynamic obstacles.

166 stars. No commits in the last 6 months.

Use this if you need to train robust motion models for autonomous agents that can predict and avoid collisions in dense, dynamic environments.

Not ideal if your application doesn't involve motion forecasting in crowded or interactive settings.

robotics autonomous-navigation collision-avoidance crowd-simulation path-planning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

166

Forks

25

Language

Python

License

BSD-2-Clause

Last pushed

Jul 10, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vita-epfl/social-nce"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.