Vision-Based Autonomous Navigation Without Boundary Wires

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous grounds maintenance machines face challenges in navigating within predefined boundaries without relying on costly and cumbersome boundary wires, especially due to limited computing resources and battery life.

Innovation Solution

The implementation of a method for autonomous machine navigation that utilizes a vision system and non-vision-based sensors to define and maintain boundaries, allowing the machine to correct its position and orientation, and involves a training mode to generate a three-dimensional point cloud for navigation, enabling efficient operation within a work region.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If boundary wires are used to define work region boundaries, then navigation reliability is improved, but device complexity and installation cost increase

Engineering Contradiction:
Improvenavigation reliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical boundary wire system with a vision-based navigation system. The autonomous machine uses cameras and image processing algorithms to detect and track boundary features (such as fences, hedges, or marked lines) in the environment, substituting the physical wire boundary with optical sensing and computational vision to achieve boundary definition and navigation.

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

Solution Approach 2:

The vision system creates a digital representation or map of the work region boundaries based on visual data. The machine captures images of boundary features, processes them to identify boundary locations and orientations, and uses this copied spatial information to navigate without physical wires, effectively replacing the physical boundary wire with a digital boundary model.

Inventive Principle:
Principle #26Copying

2Measurement precision

If sophisticated navigation systems are implemented, then navigation precision is improved, but computing resource consumption increases

Engineering Contradiction:
Improvenavigation precisionVSAvoidbattery life
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The vision system operates periodically rather than continuously. The machine captures images at specific intervals or at key navigation decision points, processes these images to update its position and boundary information, and then navigates using the accumulated data. This periodic operation reduces computational load and energy consumption compared to continuous high-frequency processing, while maintaining adequate navigation precision.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system performs preliminary image capture and processing during periods when the machine is stationary or moving slowly, such as during charging cycles or between work tasks. By pre-processing visual data and building boundary models in advance, the system reduces the computational burden during active work periods, thereby conserving battery life while maintaining navigation precision.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3833176B1Autonomous machine navigation and training using vision system
Publication Date: 2024.06.12 THE TORO COMPANY
  • EP3833176B1 patent drawingFigure 1
  • EP3833176B1 patent drawingFigure 2A
  • EP3833176B1 patent drawingFigure 2B

AI summary

Autonomous machine navigation techniques may generate a three-dimensional point cloud that represents at least a work region based on feature data and matching data. Pose data associated with points of the three-dimensional point cloud may be generated that represents poses of an autonomous machine. A boundary may be determined using the pose data for subsequent navigation of the autonomous machine in the work region. Non-vision-based sensor data may be used to determine a pose. The pose may be updated based on the vision-based pose data. The autonomous machine may be navigated within the boundary of the work region based on the updated pose. The three-dimensional point cloud may be generated based on data captured during a touring phase. Boundaries may be generated based on data captured during a mapping phase.