ai4ce/DiscoNet
[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception
This project helps self-driving vehicle engineers improve how connected autonomous vehicles (V2X) perceive their surroundings. It takes raw sensor data from multiple vehicles and road-side units, processes it collaboratively, and outputs a more accurate and comprehensive understanding of the environment, such as 3D object detection, segmentation, and tracking. This allows autonomous systems to make better decisions on the road.
151 stars. No commits in the last 6 months.
Use this if you are developing or researching multi-agent perception systems for autonomous driving and need to enhance performance by enabling vehicles to collaboratively share and process sensor data efficiently.
Not ideal if you are working on single-vehicle perception systems or do not have access to multi-agent sensor data and V2X communication setups.
Stars
151
Forks
17
Language
—
License
MIT
Category
Last pushed
Sep 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ai4ce/DiscoNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AndreiBarsan/DynSLAM
Master's Thesis on Simultaneous Localization and Mapping in dynamic environments. Separately...
gradslam/gradslam
gradslam is an open source differentiable dense SLAM library for PyTorch
jbwang1997/OPUS
OPUS: Occupancy Prediction Using a Sparse Set
mchancan/deepseqslam
The Official Deep Learning Framework for Robot Place Learning
KwanWaiPang/Awesome-Transformer-based-SLAM
Paper Survey for Transformer-based SLAM