CHENGY12/CausalHTP
The official PyTorch code implementation of "Human Trajectory Prediction via Counterfactual Analysis" in ICCV 2021.
This project helps improve the accuracy of predicting where people will move next in crowded environments. It takes existing trajectory prediction models and enhances them to provide more reliable future path forecasts, even when the observation conditions change. Researchers, urban planners, or robotics engineers working on autonomous systems would use this to get better human movement predictions.
No commits in the last 6 months.
Use this if you need to improve the robustness and accuracy of existing human trajectory prediction models, especially in environments where biases from the surrounding context might skew predictions.
Not ideal if you are looking for a complete, out-of-the-box human trajectory prediction system without needing to integrate it with an existing baseline model.
Stars
76
Forks
14
Language
Python
License
—
Category
Last pushed
Jul 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CHENGY12/CausalHTP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
StanfordASL/Trajectron
Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic...
StanfordASL/Trajectron-plus-plus
Code accompanying the ECCV 2020 paper "Trajectron++: Dynamically-Feasible Trajectory Forecasting...
agrimgupta92/sgan
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks",...
uber-research/LaneGCN
[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting
Psychic-DL/Awesome-Traffic-Agent-Trajectory-Prediction
This is a list of papers related to traffic agent trajectory prediction.