Feat/lite biped deploy - #10
Merged
Merged
Conversation
… masses Extend the robot_assets generator and the lite_biped variant to produce a MuJoCo deploy/sim asset for the biped locomotion stack: - urdf_to_mjcf: add a floating base, IMU site + accel/gyro/quat/vel/pos sensors, and foot-contact patching (foot bodies condim=3 + friction/priority, others condim=1), all opt-in per variant via cad/physics.json. - urdf_to_xacro: emit a base_imu ros2_control sensor block (sim only). - lite_biped/cad: physics.json (option matched to mjlab: timestep 0.005, pyramidal cone, impratio 1, iterations 10/20; + freejoint/imu/contact) and a new ros2_control.json (legs + imu). - lite_biped/mjcf: regenerated lite_biped.xml + hand-authored lite_biped_scene.xml (floor + light + `home` standing keyframe at base z=0.80). - Link masses/inertias now the measured 3D-printed-part values (pelvis 2.1, total ~11.48 kg), incorporating Lite-Description 479ed5e -- matches the training asset (was outdated CAD masses ~18.5 kg). Regenerated urdf/xacro/mjcf; 1415 generator tests pass. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019QrgD2S2yba6bDj4wzGWeB
… mount - ros2_control.json: real leg CAN ids from a live bus scan (left can2 31-37, right can3 41-47), buses can2/can3, and commissioned joint directions (5 flipped to -1: left_hip_pitch/knee_pitch/ankle_roll, right_ankle_pitch/ ankle_roll -- verified in the viewer against the physical robot). - ankle_yaw limit +/-45deg -> +/-90deg from the updated CAD export (matches the real hardware range). Regenerated urdf/mjcf/xacro from the export's robot.pkl. - IMU: the new CAD adds an `imu` link at the real mount (pelvis+0.08); kept it and moved the sim imu_site + base sensors there (physics.json imu.pos) so the sim IMU sits where the real one is. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019QrgD2S2yba6bDj4wzGWeB
…merged inputs main landed the measured masses (479ed5e) + an IMU frame at pelvis+0.08 (ff02069, with re-exported meshes) in parallel; this branch had the same masses+IMU plus ankle_yaw +/-90deg, the real leg CAN map/directions, and the full sim-deploy generation. Resolution: took main's re-exported meshes + URDF geometry, re-applied ankle_yaw +/-90deg, and regenerated mjcf/xacro from that URDF + this branch's cad/ (physics.json imu@0.08 + freejoint + contacts; ros2_control.json real CAN 31-37/41-47 + 5 flipped directions). Kept ros2_control.json/.xacro + lite_biped_scene.xml (branch-only). Verified: mjcf loads (nbody 17), ankle_yaw +/-1.5708, imu_site z=0.08, pelvis mass 2.1; 1418 generator tests pass. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019QrgD2S2yba6bDj4wzGWeB
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.