Shape-Based Landmark Recognition for Autonomous Mobility Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for automating tasks in construction sites require constant human supervision, are prone to navigation errors, and have limited mobility in tight spaces, making them inefficient for precise tasks like marking layouts on a worksite floor.
Innovation Solution
A mobility platform equipped with passive landmarks and a sensor system that uses laser rangefinders and cameras to navigate and perform tasks autonomously, allowing precise localization and operation based on shape recognition and distance measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If beaconed navigation systems are used, then navigation capability is provided, but system complexity and cost increase due to requiring external powered equipment
Solution Approach 1:
The patent extracts the navigation functionality from external beaconed systems and implements it using passive landmarks that are part of the existing worksite environment. The mobility platform carries its own active sensors (laser rangefinders) to detect these passive landmarks, eliminating the need for external powered navigational equipment while maintaining navigation capability.
Solution Approach 2:
The patent introduces passive landmarks as intermediary objects that mediate between the mobility platform and the worksite environment. These landmarks serve as reference points for navigation without requiring active communication or power, simplifying the overall system while enabling reliable position determination through shape-based recognition and distance measurements.
2Measurement precision
If external position determination sensors like GPS are used, then position determination is achieved, but system complexity increases
Solution Approach 1:
The mobility platform performs self-positioning by using its own active laser rangefinders to measure distances to passive landmarks. The system determines its position autonomously through shape-based recognition of landmark features and geometric calculations, without requiring external GPS infrastructure or additional complex sensing equipment.
3Extent of automation
If conventional automation systems are used, then task automation is achieved, but navigation errors occur and mobility in tight spaces is limited
Solution Approach 1:
The patent transitions from traditional 2D planar navigation to 3D spatial navigation by utilizing the vertical dimension and three-dimensional shapes of landmarks. The laser rangefinders measure distances in three-dimensional space, and the shape-based recognition system processes 3D geometric data, enabling more accurate position determination and better navigation in tight and complex worksite environments.
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 high-precision autonomous navigation and task execution, such as marking layouts, with increased construction productivity by overcoming limitations of previous automation efforts.
Implementation Method 1
a first laser rangefinder disposed on the chassis at a first location
Implementation Method 2
sweep the first passive landmark with the first laser rangefinder to collect a first plurality of distance measurements
Data Source
AI summary
A mobility platform is configured to execute one or more tasks in a worksite including a passive landmark. A mobility platform may include a first laser rangefinder and at least one processor configured to sweep the first passive landmark with the first laser rangefinder to collect a first plurality of distance measurements for a first plurality of yaw angles, fit a first shape to the first plurality of distance measurements based on a predetermined shape of the first passive landmark, and determine a position of a geometric center of the first passive landmark relative to the first location of the first laser rangefinder based on the fit first shape.