tnkr-robot-dk1 0.3.1

Tnkr Studio robot driver for the TRLC DK1 arm (vendored from robot-learning-co/trlc-dk1, Apache-2.0, with a packaging fix).

An Open Source Dev Kit for AI-native Robotics

by The Robot Learning Company

Demo

CAD

TRLC-DK1 v0.3.0 Follower CAD

TRLC-DK1 v0.2.0 Leader CAD

Copyright 2025-2026 The Robot Learning Company UG (haftungsbeschränkt). All rights reserved.

Installation

git clone https://github.com/robot-learning-co/trlc-dk1.git
uv venv
uv pip install -e .

This repo uses LeRobot's plugin conventions to be automatically detected by a LeRobot installation in the same Python environment.

Examples

Use LeRobot's CLI to identify your teleop, robot, and camera ports:

uv run lerobot-find-port
uv run lerobot-find-cameras

Example I: Single Arm Teleoperation

uv run lerobot-teleoperate \
    --robot.type=dk1_follower \
    --robot.port=/dev/ttyACM0 \
    --teleop.type=dk1_leader \
    --teleop.port=/dev/ttyACM1 \
    --robot.cameras="{ 
        context: {type: opencv, index_or_path: 0, width: 960, height: 540, fps: 60}, 
        wrist: {type: opencv, index_or_path: 1, width: 960, height: 540, fps: 60, rotation: 180}
      }" \
    --display_data=true

Example II: Bimanual Recording

uv run lerobot-record \
    --robot.type=bi_dk1_follower \
    --robot.right_arm_port=/dev/ttyACM0 \
    --robot.left_arm_port=/dev/ttyACM1 \
    --teleop.type=bi_dk1_leader \
    --teleop.right_arm_port=/dev/ttyACM2 \
    --teleop.left_arm_port=/dev/ttyACM3 \
    --robot.cameras="{ 
        head: {type: opencv, index_or_path: /dev/video0, width: 960, height: 540, fps: 60},
        right_wrist: {type: opencv, index_or_path: /dev/video2, width: 960, height: 540, fps: 60, rotation: 180},
        left_wrist: {type: opencv, index_or_path: /dev/video4, width: 960, height: 540, fps: 60, rotation: 180},
      }" \
    --dataset.repo_id=$USER/my_test_dataset \
    --dataset.push_to_hub=false \
    --dataset.num_episodes=3 \
    --dataset.episode_time_s=30 \
    --dataset.reset_time_s=20 \
    --dataset.single_task="Test the LeRobot recording pipeling."

URDF

The follower arm URDF with visual (GLB) and collision (STL) meshes is available in urdf/follower/.

Acknowledgements

• GELLO by Philipp Wu et al.
• Low-Cost Robot Arm by Alexander Koch
• LeRobot by HuggingFace, Inc.
• SO-100 by TheRobotStudio
• OpenArm by Enactic, Inc.