Systems and methods for configurable operation of a robot based on area classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robots lack predictability and user control in their mission operations, as users have limited understanding of the areas they will cover and no input on the mission specifics, leading to inefficient and potentially incomplete tasks.
Innovation Solution
A computing system that generates a segmentation map of a surface based on occupancy data, classifies areas as clutter and non-clutter, and computes a coverage pattern for navigation, allowing the robot to sequentially traverse these areas in a predetermined sequence, with user input options for modifying the map and specifying cleaning levels or boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If autonomous robots navigate surfaces to perform tasks, then task coverage is achieved, but predictability and user understanding of robot behavior deteriorates
Solution Approach 1:
The system provides continuous feedback to users through a graphical user interface that displays the segmentation map, current robot position, and planned coverage pattern. Users can observe the robot's intended actions and modify the coverage pattern before execution, creating a closed-loop information flow that resolves the predictability issue while maintaining autonomous operation.
Solution Approach 2:
The system creates a virtual copy of the physical environment through the segmentation map, which represents the surface area as discrete regions and corridors. This digital model allows users to visualize and control robot behavior without directly observing the physical robot, bridging the information gap between autonomous operation and user understanding.
2Extent of automation
If robots autonomously determine navigation paths, then operational independence is improved, but user control and input capability deteriorates
Solution Approach 1:
The system implements dynamic control where the coverage pattern can be automatically generated by the robot's autonomous system, but remains modifiable by users through the graphical interface. Users can adjust parameters such as cleaning levels for specific regions, modify corridor definitions, or change the overall coverage sequence, allowing the system to adapt between fully autonomous and user-directed operation modes.
Solution Approach 2:
The surface area is segmented into discrete regions and corridors in the segmentation map, allowing users to selectively control different portions of the environment. Users can assign different cleaning levels to specific regions, define which corridors to clean, and control the sequence of region visits, providing granular user control without requiring complete manual path planning.
3Reliability
If robots clean entire surface areas, then coverage completeness is improved, but time and energy consumption deteriorates
Solution Approach 1:
The system applies different cleaning qualities to different regions based on user-defined preferences. High-traffic or heavily soiled regions can be assigned higher cleaning levels with multiple passes, while low-traffic areas receive minimal cleaning. This localized differentiation ensures complete coverage of all regions while optimizing the time and energy spent in each area according to its specific requirements.
Solution Approach 2:
The system allows users to specify partial cleaning of surface areas by defining which regions and corridors require attention. Users can exclude certain areas from cleaning or reduce cleaning intensity in specific zones, enabling the robot to achieve sufficient coverage completeness for critical areas while spending minimal time and energy on less important regions.
4Measurement precision
If segmentation maps are generated and processed, then navigation precision is improved, but computational complexity and system complexity deteriorates
Solution Approach 1:
The segmentation map divides the continuous surface area into discrete regions and corridors, transforming a complex continuous navigation problem into a simpler discrete path planning problem. The robot navigates by transitioning between defined regions through specified corridors, which simplifies the computational requirements for path planning while maintaining precise navigation through well-defined boundaries and waypoints.
Data Source
Figure 1~2A
Figure 2B~2C
Figure 3~4
AI summary
A method of operating a mobile robot includes generating a segmentation map defining respective regions of a surface based on occupancy data that is collected by a mobile robot responsive to navigation of the surface, identifying sub-regions of at least one of the respective regions as non-clutter and clutter areas, and computing a coverage pattern based on identification of the sub-regions. The coverage pattern indicates a sequence for navigation of the non-clutter and clutter areas, and is provided to the mobile robot. Responsive to the coverage pattern, the mobile robot sequentially navigates the non-clutter and clutter areas of the at least one of the respective regions of the surface in the sequence indicated by the coverage pattern. Related methods, computing devices, and computer program products are also discussed.