Discovering and plotting the boundary of an enclosure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mapping methods for autonomous robotic devices, such as SLAM, are costly, require substantial processing power, and often fail to provide complete closed-loop maps due to gaps in data collection, especially in low-light environments or areas with transparent surfaces, and lack methods for identifying and closing these gaps.
Innovation Solution
A method that uses a robotic device equipped with sensors to iteratively map a workspace by moving to undiscovered areas, updating the map with higher confidence scores for overlapping data, and combining distance measurements from successive positions to create a complete boundary of an enclosure without the need for additional equipment or high processing power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If SLAM methods use laser distance sensors with high data collection rates, then mapping precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces expensive, complex laser distance sensors with a simple, inexpensive camera that captures images. The camera is a common, low-cost component that can be easily integrated into the robotic device, eliminating the need for costly specialized sensing equipment while still achieving effective mapping through image processing.
Solution Approach 2:
The patent substitutes the mechanical laser distance sensing system with an optical imaging system (camera). Instead of using active laser ranging mechanisms, the system passively captures visual information and processes images to extract spatial data, thereby reducing mechanical complexity and cost.
2Measurement precision
If VSLAM solutions use image processing techniques with multiple processing stages, then measurement precision is improved, but computing power requirements increase
Solution Approach 1:
The patent extracts only the essential spatial information needed for mapping from images, rather than performing comprehensive multi-stage image processing. By focusing specifically on detecting lines, corners, and geometric features relevant to boundary identification, the system achieves adequate measurement precision with reduced computational overhead.
Solution Approach 2:
The patent applies a simplified version of image processing that performs only the necessary operations for boundary detection and mapping. Rather than implementing full VSLAM pipelines with probabilistic processing and particle filtering, the system uses targeted image analysis that processes only the critical features needed for the mapping task, reducing computing power requirements while maintaining sufficient precision.
3Reliability
If SLAM methods use probabilistic processing and particle filtering, then reliability is improved, but memory requirements increase
Solution Approach 1:
The patent extracts and stores only the essential mapping data representing the enclosure boundary, rather than maintaining multiple sets of redundant probabilistic data. By representing the environment as a simplified geometric model (boundary lines and features), the system achieves reliable mapping information with minimal memory consumption.
4Measurement precision
If distance sensors are used to create depth maps, then measurement precision is improved, but completeness of the map decreases due to gaps
Solution Approach 1:
The patent merges multiple image captures taken from different positions and angles to construct a complete boundary map. By combining visual information from various viewpoints and using image processing to detect features across multiple frames, the system fills in gaps and creates a more complete representation of the enclosure boundary compared to single-position depth sensing.
Data Source
AI summary
Provided is a process that includes: obtaining a first version of a map of a workspace; selecting a first undiscovered area of the workspace; in response to selecting the first undiscovered area, causing the robot to move to a position and orientation to sense data in at least part of the first undiscovered area; and obtaining an updated version of the map mapping a larger area of the workspace than the first version.