Onboard Distributed Computing for Real-Time Humanoid Robots
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional humanoid robots lack sufficient on-board computing power to perform complex tasks in real-time due to reliance on external computing resources, leading to time delays and inefficiencies.
Innovation Solution
Implementing an Advanced Distributed Computing Hardware (ADCH) system with on-board processors, such as NVIDIA® AGX series modules, enabling parallel processing and peer-to-peer communication among multiple processors to handle data-intensive tasks autonomously.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If conventional humanoid robots use external computing systems for complex tasks, then computing power is sufficient, but time delays occur due to communication between robot and external systems
Solution Approach 1:
The patent extracts the computing function from external systems and embeds it directly into the robot by integrating a computer with processing units into the robot's body. This allows the robot to perform complex computations locally without communicating with external computing systems, thereby eliminating communication delays while maintaining sufficient computing power.
Solution Approach 2:
The patent introduces a communication unit as an intermediary between the sensor unit, actuator unit, and processing units. This communication unit manages data flow and coordination between components, enabling efficient real-time processing within the robot while avoiding the need for external system communication.
2Device complexity
If conventional humanoid robots use general purpose microprocessors for processing, then system simplicity is maintained, but processing speed is limited due to sequential processing
Solution Approach 1:
The patent segments the processing function into multiple specialized processing units (first processing unit, second processing unit, etc.) that can operate in parallel. Each processing unit handles specific tasks simultaneously, transforming the system from simple sequential processing to complex parallel processing while dramatically increasing processing speed.
Solution Approach 2:
The patent transitions from one-dimensional sequential processing to multi-dimensional parallel processing by introducing multiple processing units that operate simultaneously. This dimensional change in processing architecture allows the system to handle multiple data streams and computations concurrently, exponentially increasing processing capacity.
3Extent of automation
If humanoid robots integrate more computing power onboard, then autonomy and real-time performance improve, but device size and complexity increase
Solution Approach 1:
The patent designs processing units and communication units that serve multiple functions simultaneously. The processing units handle sensor data, control actuators, and manage communication between components, while the communication unit coordinates data flow across all system components. This multi-functionality reduces the need for separate dedicated components, managing complexity while enhancing autonomy.
4Speed
If humanoid robots integrate more computing power onboard, then real-time performance improves, but the physical size of the robot increases
Solution Approach 1:
The patent merges the computer with processing units directly into the robot's body structure, combining computational components with the physical chassis. This integration eliminates the need for separate external computing equipment, allowing high-speed real-time processing without proportionally increasing the robot's overall volume.
Data Source
AI summary
A coordinated control system designed with a small form factor that can be located within a robot or an automated inline manufacturing system, comprising: an on board advanced distributed control hardware configured with artificial intelligence enabled processors incorporated within a System on Module (SOM) board, each SOM comprising four processors or nodes; interfaced with a cameras, motors, general purpose I/O through I2C expander, audio interface, Internet, wireless communication such as WiFi and Bluetooth to send and receive commands and any other data; electrically connected to a plurality of sensors for perceiving the environment and collecting data from infrared, tactile, proximity and other types of sensors; an external host flashing computer dedicated for uploading/downloading firmware, cloning and configuration setup; a non-volatile memory for storing control algorithms, configuration files and other essential data; a HDMI based user interface for robot operation, training and setup; USB C or Ethernet based internal star network for high-speed communication bypassing the standard PCI bus interface bus; an Ethernet switch board enabling multiple boards to access the Ethernet for both internal communication within the star network as well as external Internet access.