RLBench
RLBench copied to clipboard
stepjam
A large-scale benchmark and learning environment.
Thanks for your great work. I want to change the existing task and save it. But I met some problems. After duplicating/copying the task and renaming it, I can't open...
Thanks for your great work! In `rlbench.action_modes.arm_action_modes.py`, `class EndEffectorPoseViaPlanning`, in the `self.action` function, it calls `scene.robot.arm.get_path` to generate a path from current pose to the target pose. The returned path...
Hi! Thanks for the great work! I would like to point out a bug in dataset_generator.py that may happen while saving joint_velocities which generates duplicate frames with exactly the same...
When collecting demo, i can get the one-channel mask image. It seems like each mask value corresponding to a specific object. But how I can I find the correspondence map,...
when I running "python task_builder.py",I got those error: ############################################### Traceback (most recent call last): File "task_builder.py", line 289, in scene = Scene(pr, robot, obs_config) File "/home/xbh/RLBench/tools/../rlbench/backend/scene.py", line 50, in __init__...
Hi, I've tried changing the arm in swap_arm.py from "sawyer" to "jaco" and "mico", but both result in the following error: python swap_arm.py Reset Episode Traceback (most recent call last):...
Hi, thanks for this excellent work! I want to generate some data to train an imitation learning model and evaluating in this environment. I read the codes and notice that...
#201 describes how to export the URDFs for the robots. However, these URDFs are missing the IK tip. Step 4 says 'In the generated urdf file, manually convert Pandatip from...
Is this a bug or am I missing something? Thanks for your help! Task:  Replay of collected Demonstration: https://github.com/user-attachments/assets/62860321-d509-418a-91da-c87586367251
