Mapping for autonomous mobile robots
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous mobile robots face challenges in efficiently navigating and cleaning environments due to reliance on immediate sensor responses, leading to potential error conditions and inefficient task performance, particularly when encountering features like doors and obstacles with changing states.
Innovation Solution
The implementation of intelligent mapping and labeling systems that utilize data from previous missions to plan paths, integrate with smart devices, and adjust behaviors based on feature states, allowing robots to avoid errors and optimize navigation and cleaning tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If autonomous mobile robots rely on immediate sensor responses for navigation, then the robot can react quickly to obstacles, but the robot encounters error conditions and has reduced reliability when facing features with changing states like doors
Solution Approach 1:
The system performs preliminary actions by constructing an intelligent map of the environment beforehand, identifying features such as doors and their states during initial exploration. This pre-mapping allows the robot to plan navigation paths in advance, avoiding error conditions that would occur with immediate sensor responses alone. The robot uses this pre-acquired environmental knowledge to make more reliable navigation decisions.
Solution Approach 2:
The intelligent map serves as an intermediary between the robot's sensor system and its navigation behavior. Rather than directly reacting to sensor inputs, the robot consults the pre-constructed map to determine appropriate actions. This intermediary layer processes environmental information and provides contextual guidance, improving navigation reliability while maintaining responsive behavior.
2Reliability
If autonomous mobile robots use data from previous missions for path planning, then the robot improves task performance and avoids error conditions, but the robot requires more complex mapping and data processing systems
Solution Approach 1:
The mapping system is segmented into distinct functional components: feature detection modules that identify specific elements like doors, threshold detection modules that determine traversability, and path planning modules that use this information for navigation. This segmentation allows the complex mapping task to be divided into manageable, specialized functions, reducing overall system complexity while maintaining high task performance.
Solution Approach 2:
The system performs preliminary environmental analysis during initial missions, constructing an intelligent map that stores feature locations and states. This pre-processing of environmental data eliminates the need for complex real-time decision-making during subsequent missions, as the robot can rely on pre-analyzed information for efficient path planning and error avoidance.
3Measurement precision
If autonomous mobile robots construct detailed intelligent maps with labels and states, then the robot improves navigation accuracy and task optimization, but the robot requires more data collection and processing resources
Solution Approach 1:
The mapping system applies local quality by focusing detailed detection and labeling on specific features of interest such as doors, thresholds, and obstacles, rather than uniformly processing all environmental data. The robot identifies and meticulously maps only those features that impact navigation and task performance, reducing overall data collection requirements while maintaining high precision for critical elements.
Solution Approach 2:
The system changes parameters by adapting its data collection intensity based on feature importance. For critical navigation features like doors and thresholds, the robot collects detailed information including precise location, state, and traversability parameters. For less critical areas, data collection is reduced, optimizing the balance between measurement precision and data volume.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
A method includes constructing a map of an environment based on mapping data produced by an autonomous cleaning robot in the environment during a first cleaning mission. Constructing the map includes providing a label associated with a portion of the mapping data. The method includes causing a remote computing device to present a visual representation of the environment based on the map, and a visual indicator of the label. The method includes causing the autonomous cleaning robot to initiate a behavior associated with the label during a second cleaning mission.