Subsurface Reflection Navigation for Boundary-Wire-Free Autonomy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous grounds maintenance machines face challenges in navigating within predefined work regions without relying on costly and cumbersome boundary wires, due to limited computing resources and battery life.
Innovation Solution
The method involves determining the current pose of the machine using non-vision-based sensors and updating it with vision-based data from ground-penetrating radar to navigate within a work region, training the machine to record touring images and generate a 3D point cloud for boundary definition, and using sensor fusion for navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If boundary wires are used to define work region boundaries, then navigation reliability is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces the mechanical boundary wire system with a vision-based navigation system using ground-penetrating radar and image processing. The autonomous machine captures images of subsurface objects (reflections from buried boundaries) and processes them to determine navigation boundaries, eliminating the need for physical boundary wires and their associated detection mechanisms.
Solution Approach 2:
The patent introduces ground-penetrating radar as an intermediary between the autonomous machine and the work region boundaries. The radar penetrates the ground to detect subsurface objects and reflections, providing indirect information about boundaries without requiring surface-mounted wires or markers.
2Measurement precision
If sophisticated navigation systems are implemented, then navigation precision is improved, but computing resource consumption increases
Solution Approach 1:
The patent performs computationally intensive image processing and 3D point cloud generation in advance, during idle periods when the machine is charging or not actively navigating. Pre-computed navigation maps and boundary information are stored for quick reference during operation, reducing real-time computing demands while maintaining high navigation precision.
Solution Approach 2:
The system alternates between capturing high-resolution images during navigation and processing them during idle periods. This periodic pattern allows the machine to accumulate image data over time and process it batch-wise, reducing peak computing resource consumption while achieving precise navigation through accumulated information.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables robust and efficient autonomous navigation within work regions without boundary wires, utilizing limited computing resources and extending battery life by processing images offline and complementing non-vision-based navigation with vision-based updates.
Implementation Method 1
autonomous machine navigation using reflections from subsurface objects
Data Source
AI summary
Autonomous machine navigation involves determining a current pose of an autonomous machine based on non-vision-based pose data captured by one or more non-vision-based sensors of the autonomous machine. The pose represents one or both of a position and an orientation of the autonomous machine in a work region defined by one or more boundaries. Pose data is determined based on a return signal received in response to a wireless signal transmitted to a surface or subsurface object that passively provides the return signal. The return signal is identifiable with the object. The current pose is updated based on the pose data to correct or localize the current pose and to provide an updated pose of the autonomous machine in the work region.