Multi-Sensor Robotic Mower Mapping Without Boundary Wires
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic lawn care vehicles are limited by the need for boundary wires for navigation and lack comprehensive methods to ensure accurate area servicing, with existing positioning technologies being inaccurate and time-consuming to set up.
Innovation Solution
A robotic lawn care vehicle equipped with multiple sensors, including GPS, cameras, and inertial navigation, that uses a vehicle positioning module, detection module, and mapping module to generate accurate maps and navigate without boundary wires, allowing for autonomous operation and precise area coverage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If boundary wire is used for navigation, then the robotic mower can operate autonomously within defined area, but the setup becomes time-consuming and difficult
Solution Approach 1:
The patent removes the boundary wire component from the system, replacing it with GPS reception means that allow the robotic mower to determine its position and operate autonomously without physical boundary constraints. This extraction eliminates the time-consuming wire-laying process while maintaining autonomous operation capability.
Solution Approach 2:
The patent replaces the mechanical boundary wire system with an electronic GPS-based positioning system. Instead of using physical wires to define boundaries, the system uses satellite-based location data to determine the robotic mower's position and navigate autonomously, significantly reducing setup time and complexity.
2Measurement precision
If traditional positioning equipment is used, then the robotic mower can determine its location, but the accuracy is insufficient for precise area servicing
Solution Approach 1:
The patent combines multiple positioning and detection systems including GPS reception means, inertial navigation means, and optical detection means into an integrated positioning system. This fusion of multiple sensing modalities compensates for the limitations of individual systems and achieves the high positioning accuracy required for reliable area servicing.
Solution Approach 2:
The robotic mower employs a multi-functional sensing system that can perform both coarse positioning via GPS and fine positioning through inertial measurement and optical feature detection. This universal system adapts its precision level based on environmental conditions and operational requirements, ensuring reliable area servicing across diverse scenarios.
3Measurement precision
If multiple sensors are integrated for accurate mapping, then the robotic mower can generate reliable maps and navigate without boundary wires, but the device complexity increases
Solution Approach 1:
The patent divides the complex sensing system into distinct functional modules: GPS reception means for global positioning, inertial navigation means for local position tracking, optical detection means for feature recognition, and mapping means for environment representation. This segmentation allows each module to be optimized independently while working together to achieve high mapping accuracy.
Solution Approach 2:
The patent introduces a central control system that acts as an intermediary, integrating data from multiple sensors and coordinating their operations. This mediator processes information from GPS, inertial sensors, and optical detectors, fusing the data to produce accurate position estimates and generate reliable maps, thereby managing system complexity through centralized coordination.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for recording data from at least one sensor of a robotic vehicle responsive to the robotic vehicle transiting a portion of a parcel and determining a confidence score associated with the recorded data for each of a plurality of potential detection events. The confidence score may correspond to a probability that the recorded data corresponds to an object or feature. The method may further include generating map data comprising one or more objects or features correlated to potential detection events based at least in part on the confidence score of the respective objects or features.