diff --git a/examples/10_use_so100.md b/examples/10_use_so100.md index ffadb1f3ee..405e80ec08 100644 --- a/examples/10_use_so100.md +++ b/examples/10_use_so100.md @@ -123,22 +123,22 @@ Follow step 4 of the [assembly video](https://www.youtube.com/watch?v=FioA2oeFZ5 Next, you'll need to calibrate your SO-100 robot to ensure that the leader and follower arms have the same position values when they are in the same physical position. This calibration is essential because it allows a neural network trained on one SO-100 robot to work on another. -**Auto-calibration of follower arm** -Follow step 5 of the [assembly video](https://www.youtube.com/watch?v=FioA2oeFZ5I) which illustrates the auto-calibration of the follower arm. You first need to manually move your follower arm to this initial position: +**Manual calibration of follower arm** +/!\ Contrarily to step 6 of the [assembly video](https://www.youtube.com/watch?v=FioA2oeFZ5I) which illustrates the auto calibration, we will actually do manual calibration of follower for now. -
-
|
|
|
+
+Make sure both arms are connected and run this script to launch manual calibration:
```bash
python lerobot/scripts/control_robot.py calibrate \
- --robot-path lerobot/configs/robot/so100.yaml \
+ --robot-path lerobot/configs/robot/moss.yaml \
--robot-overrides '~cameras' --arms main_follower
```
-Note: You can't run auto-calibration for the leader arm, since we removed the gears. Thus, you will need to manually calibrate the leader arm. It's less precise than auto-calibration, but precision is not as critical for the leader arm.
-
**Manual calibration of leader arm**
Follow step 6 of the [assembly video](https://www.youtube.com/watch?v=FioA2oeFZ5I) which illustrates the manual calibration. You will need to move the leader arm to these positions sequentially:
diff --git a/examples/11_use_moss.md b/examples/11_use_moss.md
index 4286fb8bc2..4ccbb93db3 100644
--- a/examples/11_use_moss.md
+++ b/examples/11_use_moss.md
@@ -123,22 +123,22 @@ Follow step 4 of the [assembly video](https://www.youtube.com/watch?v=DA91NJOtMi
Next, you'll need to calibrate your Moss v1 robot to ensure that the leader and follower arms have the same position values when they are in the same physical position. This calibration is essential because it allows a neural network trained on one Moss v1 robot to work on another.
-**Auto-calibration of follower arm**
-Follow step 5 of the [assembly video](https://www.youtube.com/watch?v=DA91NJOtMic) which illustrates the auto-calibration of the follower arm. You first need to manually move your follower arm to this initial position:
+**Manual calibration of follower arm**
+/!\ Contrarily to step 6 of the [assembly video](https://www.youtube.com/watch?v=DA91NJOtMic) which illustrates the auto calibration, we will actually do manual calibration of follower for now.
-
-
|
|
|
+
+Make sure both arms are connected and run this script to launch manual calibration:
```bash
python lerobot/scripts/control_robot.py calibrate \
--robot-path lerobot/configs/robot/moss.yaml \
--robot-overrides '~cameras' --arms main_follower
```
-Note: You can't run auto-calibration for the leader arm, since we removed the gears. Thus, you will need to manually calibrate the leader arm. It's less precise than auto-calibration, but precision is not as critical for the leader arm.
-
**Manual calibration of leader arm**
Follow step 6 of the [assembly video](https://www.youtube.com/watch?v=DA91NJOtMic) which illustrates the manual calibration. You will need to move the leader arm to these positions sequentially:
diff --git a/lerobot/common/robot_devices/robots/manipulator.py b/lerobot/common/robot_devices/robots/manipulator.py
index 2c358cb924..a20d5aed83 100644
--- a/lerobot/common/robot_devices/robots/manipulator.py
+++ b/lerobot/common/robot_devices/robots/manipulator.py
@@ -338,17 +338,10 @@ def load_or_run_calibration_(name, arm, arm_type):
elif self.robot_type in ["so100", "moss"]:
from lerobot.common.robot_devices.robots.feetech_calibration import (
- run_arm_auto_calibration,
run_arm_manual_calibration,
)
- # TODO(rcadene): better way to handle mocking + test run_arm_auto_calibration
- if arm_type == "leader" or arm.mock:
- calibration = run_arm_manual_calibration(arm, self.robot_type, name, arm_type)
- elif arm_type == "follower":
- calibration = run_arm_auto_calibration(arm, self.robot_type, name, arm_type)
- else:
- raise ValueError(arm_type)
+ calibration = run_arm_manual_calibration(arm, self.robot_type, name, arm_type)
print(f"Calibration is done! Saving calibration file '{arm_calib_path}'")
arm_calib_path.parent.mkdir(parents=True, exist_ok=True)
diff --git a/media/moss/follower_rest.webp b/media/moss/follower_rest.webp
new file mode 100644
index 0000000000..f0dba18bd7
Binary files /dev/null and b/media/moss/follower_rest.webp differ
diff --git a/media/moss/follower_rotated.webp b/media/moss/follower_rotated.webp
new file mode 100644
index 0000000000..23d5aa9c1b
Binary files /dev/null and b/media/moss/follower_rotated.webp differ
diff --git a/media/moss/follower_zero.webp b/media/moss/follower_zero.webp
new file mode 100644
index 0000000000..10ef83704f
Binary files /dev/null and b/media/moss/follower_zero.webp differ
diff --git a/media/so100/follower_rest.webp b/media/so100/follower_rest.webp
new file mode 100644
index 0000000000..971fbc6842
Binary files /dev/null and b/media/so100/follower_rest.webp differ
diff --git a/media/so100/follower_rotated.webp b/media/so100/follower_rotated.webp
new file mode 100644
index 0000000000..b13d7d7d57
Binary files /dev/null and b/media/so100/follower_rotated.webp differ
diff --git a/media/so100/follower_zero.webp b/media/so100/follower_zero.webp
new file mode 100644
index 0000000000..411a555454
Binary files /dev/null and b/media/so100/follower_zero.webp differ