MuJoCo obstacle clearance: a point path is not a body path

01 / QUESTION

Six contact trajectories compare direct, edge and clearance paths while separating geometry from controller tracking.

METHOD

Freeze protocol and source before execution, save raw records, then independently recompute metrics and verify hashes.

RESULT

Two clearance routes pass without contact; four direct/edge routes contact the obstacle and fail.

OBSERVATIONS

Two clearance routes pass without contact; four direct/edge routes contact the obstacle and fail.

CONCLUSION

Conclusions are limited to the stated variables and acceptance criteria, retaining failures and unverified scope.

LIMITATIONS

Teaching-scale fixed conditions, not online model quality, production throughput or hardware safety. The complete assistant and VL01 remain unfinished.

REPRODUCE

The article provides a pinned revision, environment, runner and independent audit commands.

1. Engineering cases

   MuJoCo obstacle clearance: a point path is not a body path

   Six contact trajectories compare direct, edge and clearance paths while separating geometry from controller tracking.

   2026-10-079 MINPublished
2. PROJECT / 003

   Hohoo Embodied Experiments

   Two MuJoCo teaching scenes—pick-and-place and planar force control—record contracts, tuning, clearance and delayed-feedback outcomes, including failures.

   2026-09-28Experiment
3. Engineering cases

   A second MuJoCo scene: why does the actuator overshoot?

   Compare mass and PD damping in a planar force-controlled actuator, separating target crossing from stable completion.

   2026-10-079 MINPublished