地址： https://huggingface.co/docs/lerobot/so101?assembly=Leader

一、飞特舵机选型

 分为标准版和大扭矩版
 标准版和大扭矩版主臂舵机相同：
 1.sts3215-c044   减速比1：191
 2.sts3215-c001   减速比1：345
 3.sts3215-c044   减速比1：191
 4.sts3215-c046   减速比1：147
 5.sts3215-c046   减速比1：147
 6.sts3215-c046   减速比1：147
 标准版从臂舵机：sts3215-c001   减速比1：345
 **大扭矩版从臂舵机：sts3215-c018   减速比1：345**
 标准版：1128元    大扭矩版1178元

二、结构件打印

结构件： 160元

三、其他物料

1.微雪舵机驱动板2个，53元
2.USB-C线2根
3.电源2个，7V4A+12V6A
4.木工夹4个
5.螺丝：2个

四、常用命令

sudo chmod 666 /dev/ttyACM*

lerobot-teleoperate
–robot.type=so101_follower
–robot.port=/dev/ttyACM0
–robot.id=my_awesome_follower_arm
–robot.cameras=“{ front: {type: opencv, index_or_path: 10, width: 640, height: 480, fps: 30}, side: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}”
–teleop.type=so101_leader
–teleop.port=/dev/ttyACM1
–teleop.id=my_awesome_leader_arm
–display_data=true

lerobot-record
–robot.type=so101_follower
–robot.port=/dev/ttyACM0
–robot.id=my_awesome_follower_arm
–robot.cameras=“{ front: {type: opencv, index_or_path: 10, width: 640, height: 480, fps: 30}, side: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}”
–teleop.type=so101_leader
–teleop.port=/dev/ttyACM1
–teleop.id=my_awesome_leader_arm
–display_data=true
–dataset.repo_id=seeedstudio123/test
–dataset.single_task=“Grab the black cube”
–dataset.push_to_hub=false

--------------------------------------------------------------训练act-------------------------------------------------------

lerobot-train
–dataset.repo_id=seeedstudio123/test
–policy.type=act
–output_dir=outputs/train/act_so101_test
–job_name=act_so101_test
–policy.device=cuda
–wandb.enable=false
–policy.push_to_hub=false
–steps=300000

--------------------------------------------------------------训练smolvla------------------------------------------------------
lerobot-train --policy.path=lerobot/smolvla_base --dataset.repo_id=seeedstudio123/test --batch_size=8 --steps=20000 --output_dir=outputs/train/my_smolvla --job_name=my_smolvla_training --policy.device=cuda --wandb.enable=false --policy.push_to_hub=false --rename_map=‘{“observation.images.front”: “observation.images.camera1”,“observation.images.side”: “observation.images.camera2”,“observation.images.front”: “observation.images.camera3”}’

-----------------------------------------------------------------------------------------推理act-------------------------------------------------------------------------------------

lerobot-record
–robot.type=so101_follower
–robot.port=/dev/ttyACM0
–robot.cameras=“{ front: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30, fourcc: “MJPG”}, side: {type: opencv, index_or_path: 2, width: 640, height: 480, fps: 30,fourcc: “MJPG”}}”
–robot.id=my_awesome_follower_arm
–display_data=false
–dataset.repo_id=seeed/eval_test123
–dataset.single_task=“Put lego brick into the transparent box”
–policy.path=outputs/train/act_so101_test/checkpoints/last/pretrained_model

---------------------------------------------------------------------------推理smolvla-------------------------------------------------------------------------------------

--------------------------------------------------------------------------问题点-----------------------------------------------------------------------------------------------

INFO 2025-10-25 17:31:27 t_record.py:341 No policy or teleoperator provided, skipping action generation.This is likely to happen when resetting the environment without a teleop device.The robot won’t be at its rest position at the start of the next episode.

lerobot-train
–config_path=outputs/train/smolvla_so101_test/checkpoints/last/pretrained_model/train_config.json
–resume=true