Localization and mapping using physical features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current localization and mapping techniques for autonomous robots, such as SLAM, face challenges in maintaining accurate pose estimation and map generation due to odometry drift and error, requiring additional sensors and complex data processing, which increases costs and computational requirements.
Innovation Solution
The method involves using conventional sensors like encoders, bumper sensors, gyroscopes, and accelerometers to estimate the robot's pose and confidence level, allowing it to re-localize by interacting with the environment and generating data for SLAM, thereby simplifying the system and reducing the need for specialized sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If SLAM techniques use additional sensors and complex data processing to maintain accurate pose estimation, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates virtual copies of physical path segments by recording sensor data (odometry, bumper sensor, gyroscope, accelerometer) during wall-following mode and storing them as template path segments. These virtual representations allow the robot to compare current sensor readings against stored templates to determine pose confidence and trigger re-localization, eliminating the need for additional specialized sensors while maintaining accurate pose estimation through data-driven template matching
Solution Approach 2:
The system uses the robot's existing sensors (odometry, bumper sensors, gyroscope, accelerometer) to generate and store path segment templates during normal operation. These templates then serve the dual purpose of both navigation guidance and pose verification, allowing the same sensor suite to perform multiple functions without requiring additional measurement devices
2Measurement precision
If SLAM techniques process complex data to maintain accurate maps, then measurement precision is improved, but computational requirements and energy consumption increase
Solution Approach 1:
The patent divides the environment into discrete path segments along walls and obstacles, recording sensor data for each segment separately. This segmentation allows the system to process and compare smaller, manageable data units rather than handling entire maps at once, reducing computational overhead while maintaining overall mapping accuracy through cumulative segment verification
Solution Approach 2:
Instead of continuously processing all sensor data for full SLAM operations, the system performs partial verification by comparing current sensor readings against stored path segment templates only when needed (when pose confidence drops below threshold). This selective processing reduces computational energy consumption while maintaining map accuracy by focusing computational resources on critical verification moments
3Reliability
If the robot continuously monitors pose confidence and re-localizes, then reliability is improved, but loss of time increases due to frequent mode switching
Solution Approach 1:
The system continuously monitors pose confidence by comparing current sensor data against stored path segment templates and uses this feedback to trigger re-localization only when confidence drops below a predetermined threshold. This feedback mechanism ensures reliable pose estimation while minimizing unnecessary re-localization operations that would waste time, as the robot only switches modes when actually needed based on real-time confidence assessment
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A method includes maneuvering a robot in (i) a following mode in which the robot is controlled to travel along a path segment adjacent an obstacle, while recording data indicative of the path segment, and (ii) in a coverage mode in which the robot is controlled to traverse an area. The method includes generating data indicative of a layout of the area, updating data indicative of a calculated robot pose based at least on odometry, and calculating a pose confidence level. The method includes, in response to the confidence level being below a confidence limit, maneuvering the robot to a suspected location of the path segment, based on the calculated robot pose and the data indicative of the layout and, in response to detecting the path segment within a distance from the suspected location, updating the data indicative of the calculated pose and/or the layout.