Robotic Grass Detection Using Edge and Frequency Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic vehicles, such as robotic mowers, are unable to effectively detect the presence of grass based on various forms of data, limiting their utility and functionality in yard maintenance tasks.
Innovation Solution
A robotic vehicle equipped with a positioning module, detection module, and mapping module, along with a sensor network that includes sensors like GPS, cameras, and 2.5D sensors, to collect and process data for identifying grass by measuring edge data and frequency patterns, enabling accurate detection and classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If robotic vehicles use basic sensors for navigation, then device complexity is reduced, but grass detection capability is insufficient
Solution Approach 1:
The patent combines multiple sensor types (cameras, 2.5D sensors, GPS) into an integrated sensor network that works together to detect grass. The camera captures 2D images while the 2.5D sensor provides depth information, and their data is merged to enable accurate grass detection without requiring full 3D LiDAR systems.
Solution Approach 2:
The patent transitions from 2D camera images to 2.5D depth-enhanced images by incorporating elevation data from the 2.5D sensor. This dimensional enhancement allows the system to detect grass structure and texture more accurately without the complexity of complete 3D spatial mapping.
2Manufacturing precision
If robotic vehicles use simple navigation systems, then device complexity is lower, but coverage accuracy and systematic traversal are compromised
Solution Approach 1:
The patent implements a feedback mechanism where the robotic vehicle continuously compares its actual position with the planned path using GPS and mapping module data. When deviations are detected, the system adjusts the vehicle's trajectory to maintain accurate coverage patterns, ensuring systematic traversal of the entire area.
Solution Approach 2:
The mapping module creates a preliminary map of the service area before the robotic vehicle begins operation. This pre-established spatial framework allows the vehicle to plan its traversal path in advance and maintain accurate coverage without requiring complex real-time decision-making algorithms.
3Adaptability or versatility
If robotic vehicles lack object classification capability, then device complexity is reduced, but functionality for different surface types is limited
Solution Approach 1:
The patent utilizes color and spectral information from the camera to identify and classify different surface types including grass, pavement, and soil. By analyzing color patterns and spectral characteristics, the system can distinguish between different materials and adjust its operation accordingly without requiring complex material analysis sensors.
Solution Approach 2:
The patent applies partial classification by focusing on identifying the most relevant surface types for the vehicle's function (primarily grass detection for mowing operations). Rather than attempting to classify all possible materials, the system concentrates processing power on detecting and categorizing grass versus non-grass surfaces, achieving practical versatility without excessive complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A robotic vehicle may be configured to incorporate multiple sensors to make the robotic vehicle capable of detecting grass by measuring edge data and/or frequency data. In this regard, in some cases, the robotic vehicle may include an onboard positioning module, a detection module, and a mapping module that may work together to give the robotic vehicle a comprehensive understanding of its current location and of the features or objects located in its environment. Moreover, the robotic vehicle may include sensors that enable the modules to collect and process data that can be used to identify grass on a parcel on which the robotic vehicle operates.