Autonomous navigation in an orchard for harvesting
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 have hindered the integration of advanced automation technologies, leading to inefficient and labor-intensive harvesting methods with high fruit and tree damage.
Innovation Solution
An autonomous harvester equipped with advanced sensory and navigational technology, capable of capturing high-resolution spatial information, determining emergence and shake points, and autonomously navigating between trees to minimize damage while adapting to varying orchard 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 fruit/tree damage is high
Solution Approach 1:
The autonomous harvester performs self-localization using low-fidelity satellite imagery and high-resolution onboard sensors to automatically determine its position and navigate through the orchard without human intervention. The system independently identifies tree features, calculates navigation paths, and executes harvesting operations autonomously
Solution Approach 2:
The patent replaces manual mechanical harvesting operations with an autonomous system that uses computer vision (monocular cameras), GPS satellite imagery processing, and automated control algorithms to navigate and harvest fruit, substituting human labor and basic mechanical equipment with sophisticated automated systems
2Productivity
If advanced automation technologies are integrated into orchard harvesting, then harvesting efficiency improves, but adaptability to irregular tree spacing and varying tree sizes deteriorates
Solution Approach 1:
The navigation system dynamically adapts to varying orchard conditions by processing real-time high-resolution spatial information from onboard sensors and satellite imagery. The system continuously recalculates emergence points, shake points, and navigation paths based on actual tree positions and characteristics, allowing flexible adaptation to irregular spacing and varying tree sizes
Solution Approach 2:
The system changes navigation parameters (minimum distance, maximum distance, path coordinates) based on detected tree characteristics including size, spacing, and position. The autonomous harvester adjusts its operational parameters dynamically according to the specific orchard layout and tree variations encountered
3Measurement precision
If high-resolution spatial information is captured and processed, then navigation precision improves, but computational requirements and system complexity increase
Solution Approach 1:
The system segments the localization process into two distinct levels: low-fidelity satellite imagery provides coarse positioning and orchard layout, while high-resolution onboard monocular cameras capture detailed spatial information for precise tree-level navigation. This hierarchical segmentation allows the system to achieve high precision without overwhelming computational requirements at any single processing stage
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.