Framework and method for controlling a robotic system using a distributed computer network

A distributed control framework (DCF) for motion control of a humanoid robot having a plurality of integrated system components including a plurality of compliant robotic joints, actuators adapted for moving the robotic joints, and sensors adapted for measuring feedback data of the integrated system components, the DCF comprising:

• a plurality of different high-speed communication networks including a backplane;
• a plurality of first controllers each embedded as a joint controller in the robot in close proximity to a respective one of the robotic joints and configured for processing the measured feedback data from a corresponding one of the integrated system components, wherein each joint controller controls a single degree of freedom (DOF) of the robot;
• a second controller in the form of a brainstem having a plurality of modules connected to the backplane, wherein the brainstem, via the modules, provides reactive commands to the joint controllers to command a performance of an autonomous task in response to top-level commands, and prioritizes actions of the robot for the autonomous task by assigning a required communications speed to each of the actions;
• and
• a third controller in the form of a system commander that is adapted for transmitting the top-level commands to the second controller as a signal commanding performance of the autonomous task to the second controller;
• wherein the DCF abstracts and centralizes control data to, and the feedback data from, the integrated system components in a single location such that access to the centralized control data is provided only at the system commander to facilitate control of the humanoid robot across the high-speed communication networks.

A method of controlling motion of a humanoid robot having a plurality of integrated system components including a plurality of compliant robotic joints, actuators adapted for moving the robotic joints via control data, and sensors adapted for measuring feedback data of the integrated system components, the method comprising:

• embedding each of a plurality of first controllers in a respective one of the plurality of integrated system components such that each of the first controllers acts as a joint controller which controls a single degree of freedom (DOF) of the robot;
• coordinating a function of the integrated system components using a second controller in the form of a brainstem, wherein the second controller is in communication with each of the plurality of first controllers and includes a plurality of modules each connected to the backplane, wherein the brainstem, via the modules, provides reactive commands to the first controllers to command performance of an autonomous task in response to top-level commands, and prioritizes actions of the robot for the autonomous task by assigning a required communications speed to each of the actions;
• commanding execution of an autonomous task by transmitting the top-level commands, as a signal, to the second controller from a third controller in the form of a system commander;
• and
• centralizing and abstracting control data to, and the feedback data from, the integrated system components in a single logical location such that access to the centralized control data is provided only via the system commander to facilitate control of the robot across multiple communication networks.