hangX/lerobot
1
0
Fork 0
forked from tangger/lerobot
Code Pull Requests Activity

Reward classifier and training (#528)

Browse Source 
Co-authored-by: Daniel Ritchie <daniel@brainwavecollective.ai>
Co-authored-by: resolver101757 <kelster101757@hotmail.com>
Co-authored-by: Jannik Grothusen <56967823+J4nn1K@users.noreply.github.com>
Co-authored-by: Remi <re.cadene@gmail.com>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
This commit is contained in:
Yoel
2024-12-09 10:21:50 +01:00
committed by Michel Aractingi
parent b43ece8934
commit 4a7f85a6ec
10 changed files with 1131 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
lerobot/scripts/control_robot.py
View File

@@ -274,10 +274,12 @@ def record(
# Load pretrained policy
policy = None if cfg.policy is None else make_policy(cfg.policy, ds_meta=dataset.meta)
# Load pretrained policy
policy = None if cfg.policy is None else make_policy(cfg.policy, ds_meta=dataset.meta)
if not robot.is_connected:
robot.connect()
listener, events = init_keyboard_listener()
listener, events = init_keyboard_listener(assign_rewards=assign_rewards)
# Execute a few seconds without recording to:
# 1. teleoperate the robot to move it in starting position if no policy provided,