Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation
| Date | Stars |
|---|---|
| 2026-07-24 | 720 |
| 2026-07-25 | 722 |
| 2026-07-28 | 722 |
| 2026-07-30 | 722 |
| 2026-08-06 | 722 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
# Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation for Intelligent Transportation Systems <div align="center"> [](https://sjtuyinjie.github.io/ultrafusion-web/) [](https://huggingface.co/TianYihong/Ultra-Fusion) [](https://arxiv.org/abs/2606.21223) [](https://github.com/sjtuyinjie/M3DGR) [](https://www.youtube.com/watch?v=ekzD9ovd1SQ) [](#5-license--acknowledgements) [](#ros1-vs-ros2--which-to-choose) [](docs/ros2_humble_m3dgr.md) [](#31-fusion-modes) [](#42-cross-platform-results) </div> **Core contributors:** [Yihong Tian](https://github.com/maotian123), [Junjie Zhang](https://github.com/Zjj587), [Liuyang Li](https://github.com/Lurvelly), and [Jie Yin](https://sjtuyinjie.github.io/)* --- Ultra-Fusion is a tightly-coupled multi-sensor SLAM framework for intelligent transportation systems (ITS). It targets real-world deployment where **sensor degradation** (poor illumination, LiDAR degeneracy, wheel slippage, GNSS outage) and **spatiotemporal miscalibration** are common. Within one configurable optimization framework, Ultra-Fusion supports **WIO, VIO, LIO, and LVIO**, with optional wheel/GNSS fusion and online calibration. **Available releases:** - **v0.1.0 (ROS1 Noetic)** — pre-built binaries to reproduce the paper benchmarks ([§2.1–2.2](#21-m3dgr-ros1)). - **v0.1.1 Ultra-Fusion-Omni (UFO) on ROS1 Noetic** — omnidirectional multi-camera LVIO for 360° vision + LiDAR; D360 as example ([§2.4](#24-ultra-fusion-omni-ufo), [walkthrough](docs/visual_life_d360.md)). - **v0.1.2 (ROS1 Noetic)** — improves runtime reliability and performance and adds flag-gated map PCD export ([release notes](docs/releases/v0.1.2.md)). - **v0.1.3 (ROS1 Noetic)** — retains v0.1.2 functionality and improves D360/UFO multi-camera replay stability ([release notes](docs/releases/v0.1.3.md)). - **v0.2.0 (ROS2 Humble)** — same `uf_node` + YAML workflow on Ubuntu 22.04 ([§2.3](#23-ros2-humble-runtime)). - **v0.2.1 (ROS2 Humble)** — fixes the ROS2 Humble runtime for M3DGR VIO/VIWO and validates LVWIO in the public ROS2 Docker runtime. - **v0.2.2 (ROS2 Humble)** — brings the latest estimator improvements and the same opt-in map PCD workflow to ROS2 ([release notes](docs/releases/v0.2.2.md)). Latest Debian assets: | Runtime | Asset | SHA256 | | --- | --- | --- | | ROS1 Noetic | `ultrafusion_0.1.3_amd64.deb` | `fe3c74d999a4f6bcf4d11be4c70e67aa48586c3b5cda2af37b521f8e37c8a84c` | | ROS2 Humble | `ultrafusion-ros2_0.2.2_amd64.deb` | `243f88fa5e3d87fcd96a2b02c8561fca4d5e56419ab72ec0a3a731b0ea34cccc` | More demos and releases are on the way — stay tuned. ## Contents - [Overview](#overview) - [Our Goal](#our-goal) - [Method Overview](#method-overview) - [Why Ultra-Fusion](#why-ultra-fusion) - [Benchmarks and Findings](#benchmarks-and-findings) - [1. Prerequisites & Installation](#1-prerequisites--installation) - [ROS1 vs ROS2 — which to choose?](#ros1-vs-ros2--which-to-choose) - [Docker installation (recommended)](#docker-installation-recommended-) - [Native installation](#native-installation) - [Installed files](#installed-files) - [2. Run on Benchmarks & Your Device](#2-run-on-benchmarks--your-device) - [2.1 M3DGR (ROS1)](#21-m3dgr-ros1) - [2.2 Other datasets (ROS1)](#22-other-datase
Excerpt of 38,243 characters
Read on GitHub
Jie Yin · Shanghai Jiao Tong University · China
59
16
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0329dddb11886350, topic:slam, desc:slam, readme:slam