
We didn’t find a product being promoted in this video. Its hook, format and structure below still show why it took off.
Browse products winning on TikTokRoboParty built a humanoid robot in 4 months. Now, the full project is open source. Meet ROBOTO ORIGIN, a 1.25 m tall, 34 kg humanoid designed for dynamic movement and reinforcement learning research. Here are the technical details: • 23 degrees of freedom (DoF): Multiple controlled joints coordinate whole-body movement. • 120 Nm peak joint torque: The leg actuators deliver high torque for dynamic motions. • 48 V, 15 Ah battery: Provides onboard electrical power. • Open hardware: Mechanical CAD files, PCB designs and the bill of materials are available. • Control software: The repository includes firmware, motor control and ROS 2 integration. • Robot simulation: URDF and MJCF models support work across simulation environments. • Reinforcement learning: The training stack includes Isaac Lab and RSL-RL, with workflows involving MuJoCo. The robot can walk, run and jump. As someone interested in robotics engineering, I find the combination of mechanical design, low-level control and reinforcement learning worth exploring. Having access to the hardware files and training code gives developers a chance to study the full system, from its physical structure to its learned movements. Reproducing it still requires sourcing components, assembling the robot and tuning the control system. GitHub: https://github.com/Roboparty/roboto_origin Would you build one yourself?
Promotes 1 product. Create free account to see more.
Outliers and viral hits: their videos on Overshot, all time.