Robot Pose Control via Indistinguishable Point Subsets

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for controlling robots are limited by requiring manipulation of control devices, which are often non-intuitive and lack sufficient degrees of freedom, making them difficult to use quickly and efficiently.

Innovation Solution

A system that determines robot commands based on the pose of an object by separating indistinguishable points into subsets to represent robot commands, allowing for intuitive and efficient control without the need for direct manipulation of control devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If control devices (joystick, keyboard, model) are used to control robots, then the robot can execute commands, but the control interface becomes complex and requires high degree of training

Engineering Contradiction:

Improvecommand set coverageVSAvoiduser training requirement

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system creates a virtual model (copy) of the robot in the user's environment and uses the user's natural pose in this virtual model to control the real robot. This eliminates the need for complex control devices while maintaining full command coverage, as the user simply positions their body or virtual avatar to issue commands.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces mechanical control devices (joysticks, keyboards, physical models) with a pose-based control system that uses computer vision and virtual reality technologies. The user's body pose or virtual avatar pose is captured and translated into robot commands, substituting mechanical interfaces with optical and computational systems.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If control devices are used to select robot commands, then commands can be issued, but the control process is not quick and intuitive

Engineering Contradiction:

Improvecommand issuance speedVSAvoidcontrol intuitiveness

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system allows the user to control the robot using their own body as the control interface. The user's natural movements and poses directly translate to robot commands without requiring learning of artificial control schemes. This self-service approach makes control both quick and intuitive, as the user leverages their own embodied knowledge.

Inventive Principle:

Principle #25Self-service

3Adaptability or versatility

If a high number of degrees of freedom is required for the control interface, then sophisticated robot commands can be executed, but the control device complexity increases

Engineering Contradiction:

Improvedegrees of freedomVSAvoidcontrol device structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The user's body serves as a universal control interface that can express multiple degrees of freedom through natural movement. Rather than designing a complex control device with multiple independent controls, the system uses the user's entire body pose (position, orientation, gestures) as a multi-functional input source, naturally providing high degrees of freedom without additional complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS7664571B2Controlling a robot using pose

Publication Date: 2010.02.16 HONDA MOTOR CO LTD

AI summary

Systems and methods are presented that enable robot commands to be determined based on the pose of an object. A method is described for determining the orientation and pose of an object using indistinguishable points. The resolution of the pose detection is based on the robot'command vocabulary. A system is described for controlling a robot by pose detection using unlabelled points.