Robot Teaching With 3D Scanning and Mixed-Reality Guidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Programming industrial robotics requires a rare combination of skills and knowledge, including industrial processes, programming, and robotics, making it challenging to achieve ease of use and highly accurate robot-motion commands with a consistent user experience.

Innovation Solution

A system and method utilizing 3D scanning and mixed reality, combined with machine learning and auto-tuning, to streamline the teaching process for robot programming, incorporating a robot with a jointed arm, a scanner, a user interface, and augmented or virtual reality for interactive programming.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional robot programming methods are used, then programming accuracy can be achieved, but the complexity of operation and skill requirements increase significantly

Engineering Contradiction:
Improveprogramming accuracyVSAvoidoperation complexity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent introduces mixed reality interfaces and 3D scanning technology as intermediary tools between the user and the robot programming system. These intermediaries translate complex programming tasks into intuitive visual interactions, allowing users to program robot motions by interacting with virtual representations of the workspace and robot, thereby maintaining programming accuracy while significantly reducing operation complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical teaching methods (manual robot movement and coordinate measurement) with optical and computational systems. 3D scanners capture workspace geometry, mixed reality displays provide visual feedback, and automated algorithms generate motion commands, substituting manual mechanical operations with automated digital processes that are both accurate and easier to operate

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If comprehensive robot programming capabilities are provided, then industrial process coverage improves, but the system complexity and learning curve increase

Engineering Contradiction:
Improveindustrial process coverageVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal programming interface that can handle multiple industrial processes (welding, material removal, painting, etc.) through a single mixed reality system. The same visual interface and interaction methods work across different process types, allowing the system to be highly adaptable without requiring separate programming systems for each industrial application, thus maintaining versatility while reducing perceived complexity

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent segments the complex programming task into distinct visual components displayed in mixed reality (workspace geometry, robot positions, motion paths, process parameters). By dividing the programming interface into manageable visual segments that can be configured independently and then integrated automatically, the system provides comprehensive process coverage while keeping each interaction simple and the overall system manageable

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12583104B2System and method for teaching a robot program
Publication Date: 2026.03.24 SCALABLE ROBOTICS INC
  • US12583104B2 patent drawing
  • US12583104B2 patent drawing
  • US12583104B2 patent drawing

AI summary

A system and method for teaching a robot program based on user input. In some embodiments, poses of a posing device manipulated by a user are captured and analyzed. In some embodiments, robot instructions are determined by a machine-learning algorithm that is trained on data concerning previously executed instructions evaluated by a user. In some embodiments, a user-selected process type defines workpiece geometry types for guiding the creation of robot instructions. In some embodiments, an augmented- or virtual-reality user interface is provided for obtaining user input.