Orchard Harvester Navigation Using Monocular Tree Triangulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Orchard harvesting technologies face challenges such as irregular tree spacing, varying tree sizes, complex canopy structures, low connectivity, and dusty environments, which hinder the integration of advanced automation technologies, leading to inefficient harvesting and increased fruit and tree damage.
Innovation Solution
An autonomous agricultural machine equipped with low-fidelity and high-resolution spatial information systems, capable of localizing tree positions, determining emergence and shake points, and navigating between minimum and maximum distances along tree rows, while adapting to low connectivity and dusty conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual labor and basic mechanical equipment are used for orchard harvesting, then labor flexibility is maintained, but harvesting efficiency is low and extensive post-harvest processing is required
Solution Approach 1:
The autonomous harvester performs self-navigation, self-localization, and self-adjustment of harvesting parameters without human intervention. The system uses onboard sensors to detect tree positions and automatically adjusts shaking parameters, eliminating the need for operators while maintaining operational autonomy throughout the harvesting process
Solution Approach 2:
The patent replaces manual mechanical operations with an autonomous system that uses computer vision for tree detection, GPS for navigation, and automated control systems for shaking parameters. This substitution of mechanical/manual systems with automated intelligence-driven systems resolves the contradiction by enabling high efficiency without requiring complex manual coordination
2Productivity
If advanced automation technologies are integrated into orchard harvesting, then harvesting efficiency improves, but damage to trees and fruits increases due to lack of sophistication in adaptation
Solution Approach 1:
The system applies different shaking parameters to different trees based on their individual characteristics detected by sensors. Each tree receives customized vibration frequency, amplitude, and duration tailored to its specific size, canopy density, and fruit load, preventing uniform over-shaking that would cause damage while maintaining efficiency
Solution Approach 2:
The autonomous harvester dynamically adjusts harvesting parameters including vibration frequency, amplitude, duration, and machine speed based on real-time sensor feedback about tree conditions. This continuous parameter optimization ensures efficient harvesting while preventing damage by adapting to each tree's specific state
3Measurement precision
If basic mechanical equipment is used, then device complexity is low, but precision required for effective fruit harvesting is insufficient leading to increased damage
Solution Approach 1:
The patent replaces basic mechanical positioning with sophisticated sensor systems including computer vision cameras for tree detection, GPS receivers for precise location tracking, and inertial measurement units for orientation. These sensing systems provide millimeter-level precision in tree localization and shaking point identification, far exceeding basic mechanical capabilities
Solution Approach 2:
The system introduces intermediate processing layers between sensing and actuation, including image processing algorithms that identify optimal shaking points on tree trunks, path planning software that navigates between trees, and control systems that translate sensor data into precise mechanical actions. These intermediaries enable high precision by breaking down the complex task into manageable computational steps
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
Enhances harvesting efficiency, reduces labor dependency, and minimizes fruit and tree damage by implementing precise navigation and sensing technologies tailored to orchard environments.
Implementation Method 1
accessing a low-fidelity image of an orchard including one or more tree rows; localizing, using the low-fidelity image, a position of an autonomous agricultural machine in a tree row
Implementation Method 2
capturing, using the autonomous agricultural machine, high-resolution spatial information of one or more trees in the tree row; triangulating positions of features in the orchard using a stream of monocular images
Implementation Method 3
determining, for each tree in the tree row, an emergence point and a shake point of the tree using the high-resolution spatial information
Implementation Method 4
autonomously navigating the autonomous agricultural machine such that the autonomous agricultural machine moves along the tree row between the minimum distance and the maximum distance for each tree
Data Source
AI summary
An autonomous harvesting machine for orchard operating environments is described. The autonomous harvesting machine uses machine vision techniques to identify and triangulate features in the operating environment using a stream of monocular images. For instance, the harvesting machine identifies and localizes a shake point of a tree by projecting virtual rays from the pose of the identification system to the identified emergence point feature. To harvest the fruit of trees in the orchard, the harvesting machine shakes the tree at the identified shake point. Additionally, the harvesting machine autonomously navigates through the orchard using a combination high resolution spatial information based on localized features and low resolution spatial information from accessed satellite images.