Grasp Execution: - Githubissues

UM-ARM-Lab / conq_python

Python library and example scripts for Conq, our Boston Dynamics Spot

MIT License

3 stars 2 forks source link

Grasp Execution: #47

Open JemuelStanley47 opened 5 months ago

JemuelStanley47 commented 5 months ago

Initial tests:

[x] Correct transform (depth sensor to body frame)
[x] Get filtered point cloud (.npy -> .npy -> filtered.pcd)
[x] Store .pcd in data/PCD/
[x] Run docker container with modified GPD code (no visualization, output 5 grasp poses)
[ ] Get grasp pose, and perform 90 degree about z-axis (Need fixing)
[x] Execute arm grasp by running script scripts/perform_grasp.py

JemuelStanley47 commented 5 months ago

Observations during test grasp execution:

1) Hand-frame orientation = Body Frame orientation : Ideal grasp pose frame is +-90 about gripper-axis

[ ] Rotate gripper-axis rather than performing transformation on grasp pose 2) Gripper/Tool frame is currently at the tip of the gripper. Offset along gripper_z axis would make grasping easier
[ ] Set tool frame offset 3) Gripper padding makes it tough to grasp (less contact area) 4) Robot doesn't exactly reach commanded pose (compared with transforms from snapshot) -> (Separate issue)
[ ] Need a controller : Steady state(PID)
[x] Explore impedance control #51 5) Gripper dimensions on GPD
[ ] Modify gripper dimensions on gpd/cfg/eig_config

JemuelStanley47 commented 5 months ago

Compute pre-grasp orientation

[ ] Theoretically achieve the target orientation, along a fixed offset along the gripper pose z-axis
[ ] Pre-grasp orientation should also be optimized/ modified(for simplicity) by best-view point selection #50

JemuelStanley47 commented 5 months ago

Observed that the gripper's 'claw' motion can't exactly be assumed to be 'parallel' as the upper-jaw length > lower-jaw.

JemuelStanley47 commented 4 months ago

GPD requires camera_orientation: 0,0,0, so grasp poses won't be filtered according to approach axis if the point cloud is transformed from sensor frame -> body frame. The modifications required: 1) Get inference from sensor-frame / hand-frame 2) Transform grasp candidates to body frame 3) Execute grasp (might need post-processing for gripper angle orientation)