UditBhaskar19/GRAPH_NEURAL_NETWORK_FOR_RADAR_PERCEPTION

Multi-task learning using message passing graph neural network for radar based perception functions

35
/ 100
Emerging

This project helps automotive engineers and perception system developers improve how radar sensors detect and classify objects for autonomous driving. It takes raw radar point cloud measurements as input and uses deep learning to transform them, making it easier to identify distinct objects like cars, pedestrians, and large vehicles, even in complex or cluttered scenes. The output includes categorized objects, predictions for their movement, and enhanced clustering.

Use this if you are working on Advanced Driver Assistance Systems (ADAS) or autonomous driving and need to enhance the accuracy of radar-based object detection, classification, and tracking, particularly in challenging environmental conditions where traditional clustering struggles.

Not ideal if your application does not involve automotive radar perception, or if you need a simpler, rule-based object detection system where deep learning complexity is undesirable.

autonomous-driving ADAS radar-perception object-detection sensor-fusion
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Jupyter Notebook

License

Last pushed

Feb 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/UditBhaskar19/GRAPH_NEURAL_NETWORK_FOR_RADAR_PERCEPTION"

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