Trajectron and Trajectron-plus-plus
Trajectron++ is a direct successor that extends the original Trajectron framework with improved trajectory forecasting capabilities, making the original largely obsolete for new projects.
About Trajectron
StanfordASL/Trajectron
Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs" by Boris Ivanovic and Marco Pavone.
This project helps researchers and engineers predict the movement of multiple interacting agents, like pedestrians or vehicles, in dynamic environments. It takes in historical trajectory data from various scenes and outputs probable future paths for each agent. This is designed for robotics researchers, urban planners, or anyone studying multi-agent systems.
About Trajectron-plus-plus
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).
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.
Scores updated daily from GitHub, PyPI, and npm data. How scores work