Mixed-Reality Robot Boundary Setting Using Hand Gestures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic systems lack an efficient method for restricting robot operations within specific boundaries in real space, relying on complex simulation and control systems that are costly and difficult to implement.
Innovation Solution
An electronic device with an imaging section, recognition section, and display controller associates virtual space coordinates with real space coordinates, allowing users to set virtual areas through gestures, which correspond to restricted operation zones for robots, using a head-mounted display to visualize and control these boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If complex simulation and control systems are used to restrict robot operations, then the reliability of robot operation restriction is improved, but the device complexity increases and ease of operation deteriorates
Solution Approach 1:
The patent creates a virtual space that is a simplified copy of the real physical space, where boundary areas are represented as virtual regions. Instead of using complex simulation systems, the patent uses a head-mounted display to show virtual boundary areas that correspond to restricted zones in real space. The robot control device receives simple coordinate information from the head-mounted display and enforces restrictions based on this virtual representation, avoiding the need for complex real-time simulation while maintaining reliable operation restriction.
2Reliability
If complex simulation and control systems are used to restrict robot operations, then the reliability of robot operation restriction is improved, but the ease of operation deteriorates
Solution Approach 1:
The head-mounted display performs self-service by automatically capturing images of the real space, generating three-dimensional coordinates, and creating virtual boundary areas without requiring manual configuration. The system uses the head-mounted display's own imaging section to capture the environment, automatically processes the images to generate spatial coordinates, and enables users to set boundary areas through simple gestures. This eliminates the need for complex manual system configuration while ensuring reliable robot operation restriction.
Solution Approach 2:
The patent replaces complex mechanical simulation and control systems with an optical and computational approach. Instead of using physical sensors and complex control algorithms to define and enforce boundary areas, the system uses the head-mounted display's imaging section to capture visual information, processes images computationally to generate virtual coordinates, and transmits this information to the robot control device. This substitution of mechanical systems with optical-computational methods simplifies operation while maintaining reliability.
3Manufacturing precision
If traditional methods are used to set boundary areas, then the manufacturing precision of boundary definition is improved, but the ease of manufacture deteriorates
Solution Approach 1:
The patent creates a virtual copy of the physical boundary areas in a three-dimensional virtual space. The head-mounted display captures images of the real environment, generates accurate three-dimensional coordinates of the captured space, and creates virtual boundary areas that precisely correspond to the physical boundaries. This virtual copying approach achieves high manufacturing precision in boundary definition while greatly simplifying the ease of manufacture, as users can define boundaries by simple gestures in the virtual space rather than through complex physical measurement and configuration processes.
Data Source
AI summary
An electronic device associates coordinates of a virtual space with coordinates of a real space. The electronic device includes an imaging section, a recognition section, a first setting section, and a display controller. The imaging section captures an image or respective images of a hand and a robot in the real space to generate a captured image of the hand and the robot. The recognition section recognizes a gesture represented by a motion of the hand based on the captured image. The first setting section sets the robot in the virtual space based on coordinates of the hand in the virtual space when it is recognized that the gesture corresponds to a first gesture. The display controller controls display of the robot so that the robot is visible to the human eye.