Mobile Robot Localization Using Shelf Planes and Corner Edges
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile automation apparatuses in complex environments, such as retail facilities, face navigational accuracy issues due to location tracking noise and error, which impede their ability to perform tasks like data capture effectively.
Innovation Solution
The apparatus employs depth sensors to capture and process depth measurements, selecting a primary subset, corner candidates, and generating corner edges and shelf planes to update its localization, thereby improving navigational accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the apparatus uses standard location tracking methods to navigate, then it can move through the environment, but localization errors accumulate and reduce navigational accuracy
Solution Approach 1:
The system continuously captures images of the environment, detects navigational structures (shelves, pillars, signs), and uses these detections to correct and update the apparatus's localization estimate in real-time, creating a feedback loop that maintains accuracy despite accumulated errors from standard tracking methods
Solution Approach 2:
The patent replaces reliance on mechanical/physical location tracking systems (which accumulate errors) with vision-based localization using image processing and deep learning to detect environmental features and calculate precise position and orientation
2Measurement precision
If the apparatus captures and processes all depth measurements to improve localization accuracy, then navigational precision improves, but computational complexity and processing time increase
Solution Approach 1:
The system segments the depth measurements by selecting only those points that fall within detected navigational structures (shelves, pillars, signs) rather than processing all depth data, reducing computational complexity while maintaining localization accuracy by focusing on relevant features
Solution Approach 2:
The system extracts and selects specific subsets of depth measurements that are most useful for localization (points on navigational structures) and discards irrelevant data, reducing processing complexity while preserving the information needed for accurate localization
Data Source
AI summary
A method of mobile automation apparatus localization in a navigation controller includes: controlling a depth sensor to capture a plurality of depth measurements corresponding to an area containing a navigational structure; selecting a primary subset of the depth measurements; selecting, from the primary subset, a corner candidate subset of the depth measurements; generating, from the corner candidate subset, a corner edge corresponding to the navigational structure; selecting an aisle subset of the depth measurements from the primary subset, according to the corner edge; selecting, from the aisle subset, a local minimum depth measurement for each of a plurality of sampling planes extending from the depth sensor; generating a shelf plane from the local minimum depth measurements; and updating a localization of the mobile automation apparatus based on the corner edge and the shelf plane.