Orchard Mobile Machine Localization Using Tree Trunk Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In environments with high-density tree distributions, such as vineyards or orchards, the distribution of tree leaves changes significantly with seasons, making it difficult to maintain accurate positioning using GNSS, and existing SLAM technologies face challenges in enabling autonomous or automatic steering of mobile machines.
Innovation Solution
A mobile machine equipped with sensors to detect the distribution of tree trunks, a storage for environment map data, and a localization processor to estimate its position by matching detected trunks with stored map data, allowing continuous use of environment maps despite seasonal changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If SLAM is used for autonomous movement in high-density tree environments, then positioning can be achieved without GNSS, but the changing distribution of tree leaves with seasons makes it impossible to continue using past maps
Solution Approach 1:
The patent segments the tree structure into two parts: leaves (which change seasonally) and trunks (which remain stable). By focusing localization on trunk detection rather than overall tree appearance, the system maintains map reusability across seasons while achieving reliable positioning in high-density tree environments where GNSS fails.
Solution Approach 2:
The patent applies local quality by selectively using trunk features rather than entire tree features for localization. The trunk portion of the tree is identified as the stable, reliable feature for matching with pre-generated maps, while ignoring the variable leaf portions that change with seasons.
2Extent of automation
If GNSS is used for positioning, then autonomous steering can be implemented, but accurate positioning cannot be maintained in high-density tree environments due to canopy obstruction
Solution Approach 1:
The patent introduces trunk distribution maps as an intermediary between the mobile machine and the environment for localization. Instead of relying on GNSS signals that are blocked by canopies, the system uses pre-generated maps of trunk positions as a mediator to determine the machine's location through sensor data matching.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate autonomous movement and automatic steering of mobile machines in environments where GNSS is unreliable by focusing on the less seasonally changing trunk distribution, maintaining map accuracy over time.
Implementation Method 1
one or more LiDAR sensors that repeatedly output sensor data indicating a distribution of objects in a surrounding environment of the mobile machine
Data Source
AI summary
A mobile machine movable between multiple rows of trees includes one or more sensors to output sensor data indicating a distribution of objects in a surrounding environment of the mobile machine, a storage to store environment map data indicating a distribution of trunks of the multiple rows of trees, a localization processor, and a controller to control movement of the mobile machine in accordance with a position of the mobile machine estimated by the localization processor. The localization processor is configured or programmed detect the trunks of the rows of trees in the surrounding environment of the mobile machine based on the sensor data that is repeatedly output from the one or more sensors while the mobile machine is moving, and perform matching between the detected trunks of the rows of trees and the environment map data to estimate a position of the mobile machine.