Robotic Lawn Mower Visual Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic lawn mowers struggle to recognize and differentiate various obstacles, especially flat ones like smartphones or hoses, due to limitations in existing sensor technologies, and lack user customization options for improving visual obstacle detection.
Innovation Solution
A robotic lawn mower equipped with a camera and a classifier module that allows user input for adapting and customizing obstacle recognition, enabling the classification of obstacles into different classes and assigning specific behaviors based on user-defined characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If bump and sonar sensors are used to detect obstacles, then large obstacles can be reliably detected, but flat obstacles like smartphones or hoses are not recognized and may be damaged
Solution Approach 1:
The patent replaces mechanical bump sensors and sonar sensors with a camera-based visual detection system. The camera captures images of obstacles, and image processing algorithms analyze the visual data to identify and classify obstacles, thereby detecting flat obstacles that mechanical and acoustic sensors cannot recognize.
Solution Approach 2:
The patent changes the detection parameter from mechanical contact or acoustic wave reflection to optical image capture. By using a camera to capture visual information and analyzing pixel data, the system can detect obstacles with varying surface properties, including flat obstacles that reflect little acoustic energy or make no mechanical contact.
2Measurement precision
If a classifier module with pre-provided obstacle samples is used, then the mower can distinguish between grass and known obstacles, but any obstacle not provided beforehand may be miss-evaluated
Solution Approach 1:
The patent implements a feedback mechanism where the user can review detected obstacles through a mobile application and provide corrections or additional information. This user feedback is used to update and refine the classifier module, enabling the system to learn from actual operating conditions and improve its ability to recognize both known and unknown obstacle types.
Solution Approach 2:
The patent performs preliminary classification of obstacles using the classifier module before final user confirmation. This preliminary action filters and pre-processes obstacle detection, presenting only relevant or uncertain cases to the user for review, thereby efficiently combining automated classification with human judgment.
3Ease of operation
If the classifier module cannot be influenced by a user, then the system remains simple to operate, but the mower cannot recognize different classes of obstacles or trigger different behaviors
Solution Approach 1:
The patent introduces a mobile application as an intermediary between the user and the classifier module. The mobile app provides a user-friendly interface for reviewing detected obstacles, classifying them into different categories, and defining desired mower behaviors. This intermediary layer simplifies the user interaction while enabling sophisticated customization capabilities.
Solution Approach 2:
The patent makes the classifier module dynamic and adaptable through user input. The system evolves from a static pre-programmed classifier to a dynamic system that can be customized and retrained by users based on their specific needs and operating conditions, allowing different behaviors for different obstacle classes.
Data Source
AI summary
The present invention proposes a profound user-mower interaction, which enables the user to teach a robotic lawn mower for improving its visual obstacle detection. The main idea of the invention is that the user can show some typical obstacles from his garden to the mower. This will increases the performance of the visual obstacle detection. In the simplest scenario the user just places the mower in front of an obstacle, and activates the learning mechanism of the classification means (module) of the mower. The increasing use of smart devices such as smart phones or tablets enables also more elaborated learning. For example, the mower can send the input image to the smart device, and the user can provide a detailed annotation of the image. This will drastically improve the learning, because the mower is provided with ground truth information.