Wrong collisions when using GPU pipeline

Omniverse Isaac Sim
,
1

Hi all,

In my research group we are working on simulating an omnidirectional base on Isaac Sim for RL training. So far I am experiencing issues when using GPU pipeline, in particular the robot seems to merge with the ground plane. Here is what happens:

GPU pipeline
GPU pipeline1206Ă—712 131 KB

When using CPU pipeline, the contact are computed correctly:

CPU pipeline690x408
CPU pipeline690x4081204Ă—712 104 KB

The model of the wheels comes from O3dyn, so nothing new.
Here is the script that I use to load the usd (Also in the attached zip)

from omni.isaac.kit import SimulationApp
import os
import torch

USE_GPU_PIPELINE = True
ASSET_PATH = "minimum_robot.usd"

def main():

    exp_path = os.environ["EXP_PATH"]
    simulation_app = SimulationApp({"headless": False, "enable_livestream": False}, 
                                   experience=f'{exp_path}/omni.isaac.sim.python.kit')
    from omni.isaac.core import World
    from omni.isaac.core.articulations import ArticulationView
    from omni.isaac.core.utils.stage import add_reference_to_stage
    import numpy as np
    from omni.isaac.core.objects import GroundPlane
    import omni.isaac.core.utils.prims as prim_utils

    sim_params =  {'gravity': [0.0, 0.0, -9.81], 
                'dt': 1.0/60.0, 
                'rendering_dt': 1.0/60.0,
                'substeps': 1, 
                'use_gpu_pipeline': USE_GPU_PIPELINE, 
                'add_ground_plane': False, 
                'add_distant_light': False, 
                'use_fabric': True, 
                'enable_scene_query_support': True, 
                'enable_cameras': False, 
                'disable_contact_processing': False, 
                'default_physics_material': {'static_friction': 1.0, 'dynamic_friction': 1.0, 'restitution': 0.0}, 
                'enable_viewport': True, 
                'sim_device': 'cuda:0', 
                'gpu_found_lost_aggregate_pairs_capacity': 11368, 
    }
 
    if sim_params["use_gpu_pipeline"]:
        sim_params["device"] = "cuda:0"
    else:
        sim_params["device"] = "cpu"

    my_world = World(stage_units_in_meters=1.0, sim_params=sim_params, 
                backend='torch', 
                device =sim_params["device"])

    prim_path = "/World/mobile_base"

    add_reference_to_stage(usd_path=ASSET_PATH, prim_path=prim_path)

    robot_view = ArticulationView(prim_paths_expr="/World/mobile_base/base_link", 
                                  translations=torch.tensor([0.0, 0.0, 0.1]).reshape(1,3).to(sim_params["device"]))
    my_world.scene.add(robot_view)

    plane = GroundPlane(prim_path="/World/GroundPlane", z_position=0)

    light_1 = prim_utils.create_prim(
        "/World/Light_1",
        "DistantLight",
        orientation=[0.65,0.27, 0.27, 0.65],
    )
    my_world.reset()

    while simulation_app.is_running():
        my_world.step(render=True)

    simulation_app.close()

if __name__ == "__main__":
    main()

So far the script is reproducible in isaac 2023.1.1, while in isaac4.2 or 4.1 the simulation is not even able to start.

I attach here this same script with the usd file:
GPU_collisions_issue_MRE.zip (7.4 MB)

My setup:

  • Ubuntu 20.04
  • RTX 4090
  • Driver 550.54.14
  • CUDA 12.4

I think the issue is something related with GPU buffers, I tried some tuning but I was not able to make it work. Also I think this is somewhat related to this issue.
We also tried removing the collision meshes (there are 5 spheres for each rollers) and use convex hull on the visual meshes of the rollers. This kinda works and the collision are goo, but the behaviour when the wheels move is way off, the robot vibrates and “jump” just too much.

Let me know if there is anything or any information that might be useful to solve this issue.

Thanks
Simone

1 Like
2

Could you please create a new topic for the issue you’re experiencing with running your script on version 4.2?

3

You can continue using this topic to track the issue. While we can’t provide fixes or debugging support for Isaac Sim 2023.1.1, we are better equipped to assist if you can reproduce the issue in version 4.2.

4

Done here

Thanks, Simone

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.