Skip to content
RobothecaBeta
Log in

Ultra-Fusion

  • Software
  • Navigation and mapping
  • Framework

Ultra-Fusion is a tightly coupled multi-sensor SLAM framework for intelligent transportation systems, built to stay accurate when sensors degrade or timing and calibration drift.

Source on GitHub: github.com/sjtuyinjie/Ultra-Fusion (opens in a new tab). Facts read at commit 9235a96 (opens in a new tab).

Licenses

Code
MIT (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 9235a96 (opens in a new tab), on 22 Oct 2026.

Commercial use
Yes

What it does

  • Runs WIO, VIO, LIO and LVIO modes within one configurable sliding-window optimizer, with optional wheel and GNSS fusion.
  • Supports online calibration to handle spatiotemporal miscalibration between sensors.
  • Provides ROS1 Noetic and ROS2 Humble runtimes that share the same YAML-driven uf_node workflow.
  • Includes Ultra-Fusion-Omni, a multi-camera LVIO setup for 360-degree vision plus LiDAR rigs.
  • Ships pre-built binaries and profiles for the M3DGR, M2DGR-Plus, MARS-LVIG, KAIST and GrandTour benchmarks.
  • Source code is not yet released; the repository currently provides executable binaries and demos.

Written by Robotheca from the project's README (opens in a new tab) at commit 9235a96.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
Ubuntu 20.04 with ROS1 Noetic, or Ubuntu 22.04 with ROS2 Humble; Docker is recommended. Compatible sensors include LiDAR, cameras, IMU, wheel odometry and GNSS. No specific computer, GPU or memory requirements are stated.

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
29 Aug 2026 on main
Latest release
Ultra-Fusion ROS1 Noetic v0.1.3 (18 Jul 2026)

Checked on GitHub on 22 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.