daeheepark/TrajSDE
[AAAI 2024] Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation
This project helps self-driving car engineers and researchers predict how vehicles or pedestrians will move in the future. It takes raw movement data from diverse urban environments, like those captured by nuScenes or Argoverse datasets, and generates more accurate future trajectory predictions. This is particularly useful for improving the safety and efficiency of autonomous systems navigating complex traffic scenarios.
No commits in the last 6 months.
Use this if you need to predict future movements of agents in autonomous driving scenarios and want your prediction models to perform well across different sensor setups and city environments.
Not ideal if you are looking for a general-purpose trajectory prediction tool outside of the autonomous driving domain or if you don't have access to nuScenes or Argoverse datasets.
Stars
20
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/daeheepark/TrajSDE"
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...
uber-research/LaneGCN
[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting
agrimgupta92/sgan
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks",...
devendrachaplot/Neural-SLAM
Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM"