02 / Cancellation without a successor
The robot moves about 0.56 m, then stops. No replacement task is sent.
A harness for embodied intelligence
From intent to action.
Back with evidence.
Building the execution foundation between agents, robot skills and the physical world. So every action can inform what comes next.
Experimental · C++17 · Software + simulation
01 / Cancel. Close. Hand off.ACTUAL SIMULATION · EXCERPT
A moves, then is cancelled. After native closure, fresh stillness and a ready replacement context, Harness settles A and admits B. Green: A's path. Blue: B's path. B moves about 1.18 m; its final receipt remains pending.
Read the evidence ↗Stopped. Still not settled.
ONE RUN, DISTINCT FACTSA stop is one part of the story.
The native action is cancelled, its work and drive close, and fresh observations confirm stillness. A's output is not delivered.
Without a ready successor context, this example keeps settlement pending and refuses another admission. The handoff run above supplies those additional facts.
Silent RViz recordings from Gazebo / ROS 2 Humble. Startup is trimmed and the image cropped for readability; playback speed is unchanged. These are scripted scenarios, not manual robot controls or physical safety guarantees.
Full uncut videos, receipts & reproduction ↗A decision is only the beginning.
EXECUTE / OBSERVE / CONTINUERun with authority.
Keep a request separate from permission to execute. Carry that permission to the backend's submission boundary.
Keep the facts.
Know which action produced a result. Distinguish cancellation requests, native outcomes and work that still needs to settle.
Make the next move.
Give callers a basis for continuing, replacing or recovering work—and, over time, improving their skills from experience.
Built toward a broader loop.
Agents choose intent. Skills act. The world returns evidence. Robot Harness aims to connect these steps across navigation, manipulation and learned behaviors.
Task strategy and learning belong with callers; native robot stacks retain control and device protection.
Explore the architecture ↗Grounded in what runs today.
Execution authority, guarded results, local workers, dependent tasks and limited Host recovery. Experimental Nav2 work includes sequential navigation, moving cancellation, goal replacement and bounded loss isolation with an independent drive path.
Early-stage software and simulation: no physical-robot integration or hard stop guarantee. Learning backends and self-improvement remain future work.
Current scope & validation ↗Begin with one runnable example
Small first steps.
Room to grow.
Build and run the software example with a C++17 compiler and CMake. No model or robot required.
Setup, commands & troubleshooting ↗git clone https://github.com/xiao-yang25/robot-harness.git
cd robot-harness
cmake -S . -B build
cmake --build build --parallel 2
./build/robot_harness_normal_executionTwo results: 29 and 61. Then explore dependent tasks and cancellation.
Follow the work. Shape what comes next.
Try an example, report a failure or bring a concrete integration.
Contributing & licensing status ↗