System and method for initializing a robot to autonomously travel a trained route

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robotic systems require exhaustive programming for specific environments, limiting their adaptability and efficiency, and often necessitate skilled technicians for operation, especially in navigating routes and determining positions within environments.

Innovation Solution

A robot system that utilizes a camera to capture images of initialization objects at different locations, an odometry unit to determine its position relative to these objects, and a controller to learn and navigate routes through user demonstration, enabling autonomous navigation with reduced programming and technician dependency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If robots are programmed with exhaustive coding for specific environments and routes, then they can navigate those environments effectively, but they become limited to those specific tasks and require significant programming time and skilled technicians

Engineering Contradiction:
Improvenavigation effectivenessVSAvoidenvironment adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system creates a simplified map copy of the environment that captures essential geometric features and landmarks. Instead of programming the robot with exhaustive environmental details, the system generates a representative map structure that the robot can use for navigation. This map copying approach allows the robot to navigate effectively while reducing programming requirements and enabling adaptation to new environments through map generation rather than reprogramming.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The navigation system is designed to be universally applicable across different environments by using generalizable map structures and landmark-based navigation. The same navigation algorithms and map representation methods can be applied to various environments without requiring environment-specific programming, enabling the robot to adapt to new locations while maintaining effective navigation performance.

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

2Adaptability or versatility

If robots are programmed with general capabilities for multiple tasks, then they can be useful in many different tasks, but they become slow and inefficient at any particular task

Engineering Contradiction:
Improvetask versatilityVSAvoidnavigation efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system performs preliminary actions by pre-processing environmental data to generate optimized navigation maps and identifying key landmarks before the robot begins navigation. This preliminary map generation and feature extraction allows the robot to execute navigation tasks efficiently without carrying the overhead of general-purpose processing during actual navigation, achieving both versatility through map reusability and efficiency through optimized navigation paths.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If conventional systems require users to program starting locations, then robots can navigate routes, but the initialization process becomes time-consuming and lacks robustness

Engineering Contradiction:
Improveroute navigationVSAvoidinitialization time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The robot performs self-initialization by automatically detecting landmarks and determining its own starting position in the environment without requiring user programming of starting locations. The system uses onboard sensors to identify landmarks and compute initial position autonomously, eliminating the time-consuming manual initialization process while maintaining reliable route navigation through automatic position determination.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3455686B1System and method for initializing a robot to autonomously travel a trained route
Publication Date: 2026.01.14 BRAIN CORP
  • EP3455686B1 patent drawingFigure 1A
  • EP3455686B1 patent drawingFigure 1B
  • EP3455686B1 patent drawingFigure 1C

AI summary

Systems and methods for initializing a robot to autonomously travel a route are disclosed. In some exemplary implementations, a robot can detect an initialization object and then determine its position relative to that initialization object. The robot can then learn a route by user demonstration, where the robot associates actions along that route with positions relative to the initialization object. The robot can later detect the initialization object again and determine its position relative to that initialization object. The robot can then autonomously navigate the learned route, performing actions associated with positions relative to the initialization object.