Abstract: A humanoid robot includes a first actuator, a second actuator, and a wire bundle interconnecting the two. The first actuator has a first side with a first printed circuit board (PCB) including a first PCB terminal having a first plurality of pins, and an opposed second side including an output portion, an actuator cover coupled to the output portion and having a wire bundle opening formed therein, and an actuator opening formed through an extent of the second side. The second actuator includes a second PCB with a second PCB terminal having a second plurality of pins, the first plurality being greater in number than the second plurality. The wire bundle includes end connectors coupled to the respective PCB terminals and a plurality of wires extending between them, the wires routed through the actuator opening and the wire bundle opening of the first actuator.

Abstract: The humanoid robot data collection system may include a wearable data collection apparatus, a computer, and a humanoid robot in data communication via a network. The wearable data collection apparatus worn by a human operator to control a robot for the purpose of collecting robot data. The wearable data collection apparatus generates pilot movement data based on various sensors contain in the wearable data collection apparatus, where the pilot movement data is used to generate robot control data and sends this control data to the robot in real-time. The wearable data collection apparatus includes a base mount, articulated arms extending from the base mount, sensors coupled to articulated arms, gloves with sensors coupled to the articulated arms, and a piloting control system operatively connected to the plurality of sensors.

Abstract: The present disclosure provides a humanoid robot system comprising a mechanical structure including a torso, two arms, and two legs providing at least 30 degrees of freedom, actuators coupled to the degrees of freedom, a sensor suite comprising at least one camera and proprioceptive sensors including joint encoders and an inertial measurement unit, a computing system comprising at least one processor and memory storing instructions which, when executed, implement a hierarchical bipedal action model including a Beta model configured to receive multimodal input data and generate a token sequence indicative of task intent and environmental state, and an Alpha model configured to condition on the token sequence and current robot pose data to output continuous action chunks comprising sequences of future target joint states over a finite horizon, and a low-level controller configured to convert the continuous action chunks into actuator control signals for execution.