TinkerV2

This repository has no parts list Robotheca can read yet.

How complete the published files are for rebuilding this robot, measured by Robotheca at commit 075e79c. It isn't a rating of the robot.

1. 13D and CAD files52 printable parts (STL, 3MF), 62 CAD source files.20/20
2. 2Robot descriptionA URDF with all its mesh files.15/15
3. 3Parts listNo parts list in the repository or linked.Most points to gain: Link to your parts list, or add it to the repository (a CSV or a Markdown table) with quantities, prices and where to buy each part.0/20
4. 4SoftwareCode in this repository, instructions to install or run it.Say which software framework it uses (ROS 2, LeRobot, Arduino…).10/15
5. 5DocumentationREADME of 7,287 characters with 3 pictures; 0 build steps.Split the build into at least 3 steps.10/15
6. 6Simulation4 simulation files (MuJoCo, Gazebo, Webots or Isaac).5/5
7. 7LicensesHardware: Apache-2.0; software: Apache-2.0.10/10

More guides

• OmniBotCtrl/OmniBotCtrl/README.md
• OmniBotTele/ESP32/README.mdin English

• Bipedal walking gait trained with reinforcement learning and transferred to a real robot (sim2real), described as closely matching the BDX style gait.
• Runs trained locomotion policies (TVM) on an onboard computer (Odroid C4).
• Locomotion with reinforcement learning is shown in the Ctrl package README, with real-robot performance demonstrated in an external video.
• Optional large language model voice interaction via installable Xiaozhi AI modules.
• Remote control handled by a separate ESP32-based remote with an LVGL display.

Found by Robotheca in the project's files at commit 075e79c, its robot.yaml and Robotheca's notes on its documents. Never guessed; Robotheca doesn't run the code.

• Ships trained model files: model_jitt.pt and 9 more

  In the project files: OmniBotCtrl/OmniBotCtrl/model_jitt.pt

• “Bipedal walking gait trained with reinforcement learning and transferred to a real robot (sim2real), described as closely matching the BDX style gait.”

  Robotheca's notes: What it can do

• “Locomotion with reinforcement learning is shown in the Ctrl package README, with real-robot performance demonstrated in an external video.”

  Robotheca's notes: What it can do

• “Optional large language model voice interaction via installable Xiaozhi AI modules.”

  Robotheca's notes: What it can do