A robot performing an isolated skill is only part of a real-world application. It also needs to move to the right location, execute the right task, and continue to the next work area as part of a repeatable workflow.
This video introduces Mission Canvas. It lets you define waypoints on a map, specify their order, and connect a Task to each location so navigation and robot actions can be executed as a single Mission.
The relationship with our previous Action Canvas video is straightforward. Action Canvas defines what the robot should do within a work area. Mission Canvas extends that workflow by defining where the robot should go and what it should do there.
Tasks can include deterministic robot actions as well as AI and VLA-based behaviors. This makes it possible to take reusable robot skills and compose them into workflows that span multiple locations in a real environment.
The two videos together show the progression from building individual robot tasks to deploying them as a mobile, repeatable Mission.
Everything shown here is available as open source. We are also providing the code, tutorial videos, and technical documentation so developers can reproduce the workflow, modify it, and build on top of it.
Mission Canvas: https://youtu.be/IVd_n3n2zkw
Action Canvas: https://youtu.be/jRcUuwxFk_Y
Code: GitHub - ROBOTIS-GIT/cyclo_intelligence: cyclo_intelligence · GitHub
Docs: Autonomy Studio | ROBOTIS Docs