Add lab desk objects, AprilTag bottle picking, and clean up lab_sim#512
Add lab desk objects, AprilTag bottle picking, and clean up lab_sim#512davetcoleman wants to merge 8 commits intomainfrom
Conversation
ff401c8 to
4cee822
Compare
17e3dc9 to
f06197a
Compare
b621d9c to
6c53a30
Compare
|
This is failing CI for both integration testing and pre-commit. Please confirm the objectives in lab_sim still run successfully and that the new assets don't introduce any unexpected behaviors (ungraspable objects due to collisions, collisions with new objects due to waypoints, confusing input to ML prompts, poor friction coefficient for new objects). As our flagship config, I wouldn't want to introduce a whole bunch of unpickable objects or add complexity that would make the product look poorly functional. Please also monitor the change in CPU usage, there are a lot of additional free joints that would significantly increase the CPU load and I want to make sure it's not a huge jump. I noticed some of the free joints (like the alligator) are not even reachable, and would be better as fixed joints. When this PR is tested and ready for review, please add a story to track your work on the project board |
a3d0b64 to
456c578
Compare
|
@nbbrooks merged the last blocker PR (of several) to this late yesterday, so can we merge this now? |
eb6eccb to
3de8f92
Compare
|
@rlpratt12 can you remove your "requested changes" block? @davetcoleman am I missing a countertop texture? or is that a followup pr?
|
|
My laptop is having performance issues and I'm seeing a 50% grasp success rate. simplescreenrecorder-2026-03-13_08.44.45.mp4This could be any number of things
I am concerned people in training will run into this, but I don't have a good grasp on the success rate for the current set of objectives. I suspect the EGL rendering will vastly improve this by taking off CPU load. |
|
I wasn't able to get ML working on my GPU so I haven't tested the ML objectives, but I've updated the PR summary to include a list of objectives and whether they still run successfully or not. I've made some easy fixes, but some of the objectives require larger efforts to fix (new ICP/registration examples, update/remove/replace hardcoded pick and place objectives, shift pose-based paths so they dont collide with new desk location). My latest changes are pushed, but I'd like someone else to confirm the failing objectives are now passing for them as well |
This is the texture Claude gave me for the countertop, and I was actually happy with it. You're hoping for a non-checkerboard black pattern? How about we leave that for future work.
This is why I had added ForceSuccess, and I had tuned the gripper config further, and I had changed the close amount to be less than the full close distance. But those changes were asked to be reverted through the review process thus far.
I don't see your fixes in this PR's force push history, are you sure you pushed them @MikeWrock ? |
Let's separate out physical grasping success concerns from |
Passing Objectives (per @harrison-bcr's test)Application - Advanced Examples
Application - Basic Examples
Application - ML (GPU Recommended)
Grasping
MuJoCo Simulation
Perception - 3D Point Cloud
Perception - Scene Constraints
Training Examples
Vector Handling
Visualization
|
Can you replace the boring square (which is barely a "CAD Part") with one of the other objects on the table? Perhaps the microscope on the left? Or something else that is more interesting than a cube, please?
How about you just delete this objective? we have plenty of other P&P examples now
How about we delete this one too? The other FAILs - do you see a path to fix them? Thanks for working on this! |
Hi @davetcoleman . Saw this comment after I put some fixes.
For the remaining FAILS, I am still going through each failed ones and trying to have a fix for it. |
Yes I think it would be much more interesting to change it
Great
I like keeping it if you can, but should we remove "Blocks" from the name? What is it stacking? I really want to get rid of kids blocks from the examples |
|
@harrison-bcr how is this coming along? Are you blocked by anything? |
|
@harrison-bcr be sure to pull in latest changes, such as this one: #549 (comment) |
Hey @nbbrooks , I just finished updating this tracker.
|
Just to be sure @davetcoleman, does this mean I should pull rebase changes from |
Yea I think that makes sense What if we merge this and move these 3 issues as separate bug issues?
I dont know what this is
If these are the old ML things, these have never really worked in the tutorials - they dont put bounding boxes correctly on anything. I think we should just delete them since @griswaldbrooks has much better new ones merged in. Good issue for a new thread.
I don't think my changes would have affected anything here, but good thing to discuss with @bkanator in a new thread |
… up lab_sim Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…and waypoint management
…ect XML files for improved accuracy
…gister_cad_part, and register_cad_part_subtree XML files for improved accuracy and consistency
…king and waypoint management
19a3e58 to
d3b8b43
Compare
|
Rebased on |

Summary
TODO
Dependencies
Note: I would love to get rid of picknik_accessories repo for good, merging it into this repo. With the advent of AI, we dont need to maintain a reusable set of MuJoCo assets for our customers. The vision was to make this into a sharable library I think. In a future PR, I think we should get rid of this repo because it causes a lot of problems trying to keep changes to moveit_pro, example_ws, and picknik_accessories in sync.
Passing Objectives (per @MikeWrock's test)
Application - Advanced Examples
Application - Basic Examples
Application - ML (GPU Recommended)
Application - MPC Examples
Grasping
Motion - Execute
Motion - Planning
MuJoCo Simulation
Perception - 3D Point Cloud
Perception - Planning Scene
Perception - Scene Constraints
Training Examples
User Input
Vector Handling
Visualization