"Getting Started Using in Python" Examples Not Working

[tylerlum]

Small documentation issues for the getting started that could be improved here, since it doesn't "just work" as it is currently written: https://curobo.org/get_started/2a_python_examples.html

Forward Kinematics

Given example code:

# Third Party
import torch

# cuRobo
from curobo.cuda_robot_model.cuda_robot_model import CudaRobotModel, CudaRobotModelConfig
from curobo.types.base import TensorDeviceType
from curobo.types.robot import RobotConfig
from curobo.util_file import get_robot_path, join_path, load_yaml

# convenience function to store tensor type and device
tensor_args = TensorDeviceType()

# this example loads urdf from a configuration file, you can also load from path directly
# load a urdf, the base frame and the end-effector frame:
config_file = load_yaml(join_path(get_robot_path(), "franka.yml"))

urdf_file = config_file["robot_cfg"]["kinematics"][
    "urdf_path"
]  # Send global path starting with "/"
base_link = config_file["robot_cfg"]["kinematics"]["base_link"]
ee_link = config_file["robot_cfg"]["kinematics"]["ee_link"]

# Generate robot configuration from  urdf path, base frame, end effector frame

robot_cfg = RobotConfig.from_basic(urdf_file, base_link, ee_link, tensor_args)

kin_model = CudaRobotModel(robot_cfg.kinematics)

# compute forward kinematics:
# torch random sampling might give values out of joint limits
q = torch.rand((10, kin_model.get_dof()), **vars(tensor_args))
out = kin_model.get_state(q)

Error:

  File "test_fk.py", line 20, in <module>
    q = torch.rand((10, kin_model.get_dof()), **vars(tensor_args))
TypeError: rand() received an invalid combination of arguments - got (tuple, collision_distance_dtype=torch.dtype, collision_gradient_dtype=torch.dtype, collision_geometry_dtype=torch.dtype, dtype=torch.dtype, device=torch.device), but expected one of:
 * (tuple of ints size, *, torch.Generator generator, tuple of names names, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, torch.Generator generator, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, tuple of names names, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)

Required change:

Replace this:

q = torch.rand((10, kin_model.get_dof()), **vars(tensor_args))

With this:

q = torch.rand((10, kin_model.get_dof()), **(tensor_args.as_torch_dict()))

Should make this change to all examples with var(tensor_args) used in this way (there's another one in forward kinematics)

Collision Checking

Example:

# Third Party
import torch
# cuRobo
from curobo.types.base import TensorDeviceType
from curobo.wrap.model.robot_world import RobotWorld, RobotWorldConfig

robot_file = "franka.yml"

# create a world from a dictionary of objects
# cuboid: {} # dictionary of objects that are cuboids
# mesh: {} # dictionary of objects that are meshes
world_config = {
    "cuboid": {
        "table": {"dims": [2, 2, 0.2], "pose": [0.4, 0.0, -0.1, 1, 0, 0, 0]},
        "cube_1": {"dims": [0.1, 0.1, 0.2], "pose": [0.4, 0.0, 0.5, 1, 0, 0, 0]},
    },
    "mesh": {
        "scene": {
            "pose": [1.5, 0.080, 1.6, 0.043, -0.471, 0.284, 0.834],
            "file_path": "scene/nvblox/srl_ur10_bins.obj",
        }
    },
}
tensor_args = TensorDeviceType()
config = RobotWorldConfig.load_from_config(robot_file, world_file,
                                          collision_activation_distance=0.0)
curobo_fn = RobotWorld(config)

Error:

    config = RobotWorldConfig.load_from_config(robot_file, world_file,
NameError: name 'world_file' is not defined

Simply need to change world_file to world_cfg

Motion Generation

Example:

# cuRobo
from curobo.types.math import Pose
from curobo.types.robot import JointState
from curobo.wrap.reacher.motion_gen import MotionGen, MotionGenConfig, MotionGenPlanConfig

world_config = {
    "mesh": {
        "base_scene": {
            "pose": [10.5, 0.080, 1.6, 0.043, -0.471, 0.284, 0.834],
            "file_path": "scene/nvblox/srl_ur10_bins.obj",
        },
    },
    "cuboid": {
        "table": {
            "dims": [5.0, 5.0, 0.2],  # x, y, z
            "pose": [0.0, 0.0, -0.1, 1, 0, 0, 0.0],  # x, y, z, qw, qx, qy, qz
        },
    },
}

motion_gen_config = MotionGenConfig.load_from_robot_config(
    "ur5e.yml",
    world_config,
    interpolation_dt=0.01,
)
motion_gen = MotionGen(motion_gen_config)
motion_gen.warmup()

retract_cfg = motion_gen.get_retract_config()

state = motion_gen.rollout_fn.compute_kinematics(
    JointState.from_position(retract_cfg.view(1, -1))
)

goal_pose = Pose.from_list([-0.4, 0.0, 0.4, 1.0, 0.0, 0.0, 0.0])  # x, y, z, qw, qx, qy, qz
start_state = JointState.from_position(
    torch.zeros(1, 6).cuda(),
    joint_names=[
        "shoulder_pan_joint",
        "shoulder_lift_joint",
        "elbow_joint",
        "wrist_1_joint",
        "wrist_2_joint",
        "wrist_3_joint",
    ],
)

result = motion_gen.plan_single(start_state, goal_pose, MotionGenPlanConfig(max_attempts=1))
traj = result.get_interpolated_plan()  # result.optimized_dt has the dt between timesteps
print("Trajectory Generated: ", result.success)

Error:

  File "test_motion_gen.py", line 37, in <module>
    torch.zeros(1, 6).cuda(),
NameError: name 'torch' is not defined

Need to add import torch at the top

Also

traj = result.get_interpolated_plan()  # result.optimized_dt has the dt between timesteps

I believe this is a bit misleading. The dt in traj is now not result.optimized_dt, but result.interpolation_dt.

1. cuRobo installation mode (choose from [python, isaac sim, docker python, docker isaac sim]): python
2. python version: Python 3.8.19
3. Isaac Sim version (if using): Not used

---

Issue Details

[balakumar-s]

Thanks! we will fix this

[balakumar-s]

Fixed