Floor Plan Updating from Occupancy Maps for Robot Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Consumer-grade household robots face challenges in navigating complex environments safely due to limitations in sensor quality, which affects their ability to make sharp turns, move at faster speeds, and accurately map spaces, especially when relying solely on occupancy maps without additional data-rich sources.
Innovation Solution
A floor plan system that generates, updates, and repairs spatial maps using occupancy map data, enabling automatic segmentation of room geometries, user-provided tagging, and metadata integration, allowing multiple autonomous mobile devices to share a consistent and accurate representation of the environment, even in the absence of additional data sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If consumer-grade sensors are used in household robots, then the robot can be manufactured at lower cost and made accessible to consumers, but the robot's ability to navigate complex environments safely, make sharp turns, move at faster speeds, and accurately map spaces is limited
Solution Approach 1:
The patent segments the mapping problem into two distinct representations: occupancy maps for hazard detection and avoidance, and floor plans for navigation and user interaction. This segmentation allows the robot to use simpler sensors for safety-critical functions while generating semantically rich floor plans through algorithmic processing, resolving the contradiction between sensor limitations and navigation requirements
Solution Approach 2:
The patent introduces floor plans as an intermediary data structure that bridges the gap between limited sensor data and comprehensive environmental understanding. Floor plans serve as a mediator that encodes semantic information about walls, floors, and room geometries, enabling the robot to navigate complex environments safely without requiring expensive high-quality sensors
2Device complexity
If occupancy maps are used without additional data-rich sources, then the system can operate with simpler sensors and lower data requirements, but the ability to create semantically meaningful and accurate spatial representations is reduced
Solution Approach 1:
The patent implements a self-service mechanism where the robot's existing sensors and occupancy maps are processed through algorithmic floor plan generation to create semantically rich spatial representations. The system serves itself by extracting wall locations, room geometries, and floor plan features from occupancy data without requiring additional external data sources, thereby maintaining operational simplicity while improving spatial understanding
Solution Approach 2:
The patent transforms occupancy map data into floor plan representations by changing the parameters and organization of spatial information. Instead of storing raw occupancy grid data, the system extracts and represents walls as line segments, identifies room geometries, and encodes semantic relationships, thereby enriching the spatial representation without adding external data sources
3Reliability
If floor plans are updated frequently to maintain accuracy in dynamic environments, then the navigation accuracy is improved, but the computational overhead and time required for map maintenance increases
Solution Approach 1:
The patent performs preliminary action by generating complete floor plans during the initial environment mapping phase, establishing a baseline spatial representation before the robot begins operation. This preliminary floor plan serves as a reference that can be efficiently updated later by comparing new occupancy data against the existing floor plan structure, reducing the computational overhead of frequent updates
Solution Approach 2:
The patent implements feedback mechanisms where the robot continuously compares new occupancy map data against the stored floor plan, identifying discrepancies and updating only the necessary portions of the floor plan. This feedback-driven update approach maintains navigation accuracy by detecting changes in the environment while minimizing computational overhead by updating only affected areas rather than regenerating entire floor plans
Data Source
AI summary
Systems and techniques for updating floor plans for use by autonomous mobile devices. The techniques include accessing a first floor plan with associated spatial metadata. An updated occupancy map is received with additional geographic updates over the first floor plan. A transformation of the first floor plan is determined to match the new occupancy map. The spatial data and the first floor plan are transformed and the transformed spatial metadata is associated with the new occupancy map to form a second floor plan.