Mapping for autonomous mobile robots
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous mobile robots face challenges in efficiently navigating and cleaning environments due to the lack of effective mapping and navigation systems, leading to errors and inefficiencies in task performance.
Innovation Solution
The development of an intelligent robot-facing map that allows autonomous mobile robots to collect and utilize data on environmental features, such as doors and dirty areas, to plan paths and behaviors, enabling improved navigation and task performance by integrating with other smart devices and sharing mapping data within fleets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous mobile robots rely only on immediate sensor responses for navigation, then the robot can react to current environmental conditions, but the robot encounters error conditions and has poor task performance due to lack of historical data utilization
Solution Approach 1:
The robot performs preliminary mapping and feature detection during initial navigation missions, storing environmental data before actual task execution. This preliminary action allows the robot to recognize patterns and predict potential error conditions in advance, improving navigation reliability without losing time during operational missions.
Solution Approach 2:
The system implements feedback loops where navigation errors and sensor detections from previous missions are fed back into the mapping database. This continuous feedback mechanism allows the robot to learn from past experiences and improve its navigation decisions in subsequent missions, resolving the contradiction between reliability and learning time.
2Reliability
If autonomous mobile robots collect and process extensive mapping data from previous missions, then the robot can intelligently plan paths and avoid error conditions, but the device complexity increases
Solution Approach 1:
The patent extracts only the most critical environmental features and error-prone areas from extensive mapping data, storing them in a simplified format. Instead of processing all raw sensor data, the system identifies and stores key landmarks, obstacles, and error conditions, reducing computational complexity while maintaining high task performance reliability.
Solution Approach 2:
The mapping system applies different levels of detail to different regions of the environment. High-detail mapping is applied to areas where errors frequently occur or where precise navigation is critical, while lower-detail mapping is used in safe, open areas. This local quality approach reduces overall system complexity while maintaining reliability where needed.
3Productivity
If a fleet of autonomous mobile robots each independently collects mapping data, then each robot can operate autonomously, but the map construction efficiency is reduced and learning about features takes longer
Solution Approach 1:
The patent implements a centralized mapping database that merges data from multiple robots in the fleet. Each robot contributes its sensor data and detections to a shared map, which is continuously updated and refined. This merging approach dramatically improves map construction efficiency, allowing the fleet to build a comprehensive environmental model much faster than any single robot could independently.
Solution Approach 2:
The shared mapping database serves multiple functions simultaneously: it provides navigation guidance for all robots, stores error condition information for fleet-wide learning, enables task coordination between robots, and maintains an updated environmental model. This multi-functionality resolves the contradiction by maximizing productivity while keeping coordination complexity manageable through a universal data structure.
Data Source
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.