Framework and method for controlling a robotic system using a distributed computer network
A robotic system for performing an autonomous task includes a humanoid robot having a plurality of compliant robotic joints, actuators, and other integrated system devices that are controllable in response to control data from various control points, and having sensors for measuring feedback data at the control points. The system includes a multi-level distributed control framework (DCF) for controlling the integrated system components over multiple high-speed communication networks. The DCF has a plurality of first controllers each embedded in a respective one of the integrated system components, e.g., the robotic joints, a second controller coordinating the components via the first controllers, and a third controller for transmitting a signal commanding performance of the autonomous task to the second controller. The DCF virtually centralizes all of the control data and the feedback data in a single location to facilitate control of the robot across the multiple communication networks.
1. A robotic system operable for performing an autonomous task, the robotic system comprising:
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 including the plurality of joints; and
a multi-level distributed control framework (DCF) adapted for controlling the integrated system components over multiple high-speed communication networks, including a backplane, the DCF including:
a plurality of first controllers each configured as a joint controller operable for processing the measured feedback data within a corresponding one of the integrated system components, such that each of the first controllers controls a single degree of freedom (DOF) of the robot, wherein each of the plurality of joint controllers is embedded in the humanoid robot in close proximity to a respective one of the robotic joints;
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 first controllers to command performance of the 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, thereby commanding performance of the autonomous task;
wherein the DCF centralizes and abstracts 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 humanoid robot across the multiple high-speed communication networks.
2. The robotic system of claim 1 , wherein at least one of the robotic joints includes a servo motor, and wherein the control and feedback data includes a positional value of the servo motor.
3. The robotic system of claim 1 , wherein the multiple high-speed networks include each of: an Ethernet network, the backplane, and a multipoint low-voltage differential signaling (M-LVDS) bus.
4. The robotic system of claim 1 , wherein each of the plurality of first controllers includes a printed circuit board assembly (PCBA) controlling one degree of freedom (DOF) of a corresponding one of the robotic joints.
5. The robotic system of claim 1 , wherein the second controller includes a communications module adapted for interfacing with each of the plurality of first controllers.
6. The robotic system of claim 1 , further comprising a plurality of network communication managers (NCM), wherein at least one NCM is connected to each of the high-speed communication networks and adapted to coordinate and prioritize communication between the networks.
7. 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.
8. The DCF of claim 7 , further comprising a plurality of network communication managers (NCM), wherein an NCM is connected to each of the networks and adapted to coordinate and prioritize communication between the networks.
9. The DCF of claim 8 , wherein each NCM is configured to revert control of the robot to a safe state in response to a predetermined event.
10. The DCF of claim 9 , including a plurality of command modules connected to each of the high-speed networks, and adapted for controlling a designated function of the robot, wherein the predetermined event occurs when one of the command modules is disconnected.
11. The DCF of claim 10 , wherein the plurality of command modules includes at least one of: a haptic sensing module, a vision sensing module, a user interface module, a task planning module, a tele-operation module, reasoning module, and a learning module.
12. The DCF of claim 10 , wherein at least some of the first controllers are configured as printed circuit board assemblies that are embedded in a respective one of the robotic joints, and that are adapted for controlling the motion of a corresponding one of the joints.
13. The DCF of claim 7 , wherein the plurality of different high-speed communication networks include at least one of: an Ethernet network, the backplane, and an multipoint low-voltage differential signaling (M-LVDS) bus.
14. The DCF of claim 7 , wherein each of the plurality of first controllers include a printed circuit board assembly (PCBA) controlling the single degree of freedom (DOF) of a corresponding one of the robotic joints.
15. The DCF of claim 7 , wherein the second controller includes a communications module adapted for interfacing with each of the plurality of first controllers.
16. 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.
17. The method of claim 16 , wherein embedding each of a plurality of first controllers in a respective one of the plurality of integrated system components includes embedding a printed circuit board assembly (PCBA) in each of the robotic joints.