Vision-Guided Robotic Lawn Edger for Wire-Free Boundary Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robotic lawn edgers and mowers rely on guide wires or markers to determine boundaries for tasks like edging and mowing, which limits their flexibility and autonomy, and face challenges with self-positioning accuracy due to drift issues from IMU-based systems.
Innovation Solution
A motorized wheeled chassis equipped with computer vision and deep learning capabilities, using image and depth data from cameras to determine alignment and position corrections, allowing for boundary detection and task performance without guide wires, and addressing self-positioning drift through algorithms like ICP and ORB feature selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If guide wires or markers are used to determine boundaries, then the robotic system can perform lawn edging and mowing tasks, but the system loses flexibility and autonomy
Solution Approach 1:
The patent replaces mechanical guide wires and physical markers with computer vision-based boundary detection. The system uses cameras to capture images and deep learning algorithms to identify boundaries, replacing the need for physical guidance infrastructure and enabling autonomous operation without external guides.
Solution Approach 2:
The robotic system performs self-positioning and self-navigation by detecting boundaries and features in its environment using onboard sensors and processing algorithms. The system determines its own location and orientation without external guidance, making the system self-sufficient and autonomous.
2Measurement precision
If IMU-based self-positioning is used, then the robotic system can navigate autonomously, but drift issues reduce positioning accuracy
Solution Approach 1:
The system uses computer vision to continuously detect boundaries and environmental features, providing feedback to correct positioning drift. By comparing detected features with expected positions, the system can identify and compensate for drift accumulation, maintaining long-term positioning accuracy.
Solution Approach 2:
The patent combines IMU-based inertial navigation with computer vision-based feature detection and boundary following. This fusion of multiple positioning methods allows the system to leverage the short-term accuracy of IMU while using vision feedback to correct long-term drift, achieving both precision and reliability.
3Extent of automation
If computer vision and deep learning are implemented without guide wires, then autonomy and flexibility improve, but system complexity increases
Solution Approach 1:
The patent replaces complex mechanical guidance systems (guide wires, physical markers, external infrastructure) with software-based computer vision and deep learning algorithms. This substitution reduces mechanical complexity while achieving equivalent or superior functionality through intelligent processing.
4Measurement precision
If additional sensor data and neural networks are used for self-positioning correction, then positioning accuracy improves, but computational requirements and processing time increase
Solution Approach 1:
The system pre-trains deep learning models on simulated and real-world data before deployment. This preliminary training allows the neural network to quickly process real-time sensor data during operation, reducing inference time while maintaining high accuracy in boundary and feature detection.
Data Source
AI summary
An autonomous vehicle for performing gardening tasks, the vehicle including a motorized wheeled chassis with at least one motor providing power to a plurality of wheels, at least one rotating wheel attached to the motorized wheeled chassis, a line or blade extending from the rotating wheel configured to perform a selected gardening task, at least one of a downward-facing camera or an outward-facing camera, and a processor configured to control processing related to determining a position of the motorized wheeled chassis, driving the at least one motor to move one or more of the plurality of wheels, rotating the at least one rotating wheel when the selected gardening task is performed, and correcting a path of the motorized wheeled chassis based on one or more images obtained from the at least one of the downward-facing camera or the outward-facing camera.