Skip to content
RobothecaBeta
Log in

Khronos

  • Software
  • Navigation and mapping
  • Library

Khronos is an online metric-semantic SLAM system that tracks both short-term dynamics and long-term changes in dynamic environments, building a spatio-temporal map of the scene.

Made by MIT-SPARK, United States (checked on github.com/MIT-SPARK/Khronos/blob/HEAD/LICENSE (opens in a new tab)).

Source on GitHub: github.com/MIT-SPARK/Khronos (opens in a new tab). Facts read at commit 63faadd (opens in a new tab).

Licenses

Code
BSD-3-Clause (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit 63faadd (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Performs simultaneous mapping and localization while reasoning about short-term motion and long-term scene changes.
  • Detects both humans and inanimate objects, and compares short-term dynamics against observed human actions.
  • Detects long-term changes, such as objects being removed or placed, when the robot revisits an area.
  • Builds an incremental background mesh and generates object nodes during playback.
  • Can run on simulated datasets or real robot data, using ground-truth, pre-recorded or live segmentation labels.
  • Includes a ROS2 launch setup, an open-set segmentation option through semantic_inference, and a 4D map visualizer.

Written by Robotheca from the project's README (opens in a new tab) at commit 63faadd.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
Running semantic_inference without TensorRT is possible but limits segmentation to open-set only.

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
10 Nov 2025 on main
Latest release
None published on GitHub

Checked on GitHub on 16 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.