StanfordASL/Trajectron-plus-plus

Code accompanying the ECCV 2020 paper "Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data" by Tim Salzmann*, Boris Ivanovic*, Punarjay Chakravarty, and Marco Pavone (* denotes equal contribution).

51
/ 100
Established

This project helps self-driving car engineers and robotics researchers predict the future paths of pedestrians, cyclists, and vehicles. It takes in historical movement data and environmental context, then outputs dynamically-feasible trajectory forecasts. The end user is typically a robotics engineer or researcher working on autonomous systems.

791 stars. No commits in the last 6 months.

Use this if you need to accurately forecast the movements of multiple interacting agents like cars and pedestrians in complex environments for autonomous driving or robotics applications.

Not ideal if you're looking for a simple, off-the-shelf solution without diving into model training and dataset preparation.

autonomous-driving robotics motion-prediction pedestrian-behavior vehicle-dynamics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

791

Forks

214

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/StanfordASL/Trajectron-plus-plus"

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