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 drift and error in odometry data, requiring additional sensors and complex data processing, which increases costs and computational requirements.
Innovation Solution
The method involves an autonomous robot using existing sensors like encoders, bumper sensors, gyroscopes, and cameras to estimate its pose and generate maps by recording interactions with the environment, updating its pose confidence, and re-localizing when confidence falls below a threshold, thereby simplifying the system and reducing the need for specialized SLAM sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If SLAM techniques are used for localization and mapping, then accurate robot pose estimation and map generation are achieved, but device complexity and computational requirements increase
Solution Approach 1:
The robot uses its own operational data (odometry, sensor readings from normal operation) to perform localization and mapping without requiring specialized SLAM sensors. The system serves itself by utilizing existing operational data for pose estimation and map generation, eliminating the need for additional dedicated hardware
Solution Approach 2:
Existing sensors (encoders, bumper sensors, gyroscopes, cameras) perform multiple functions: both their primary functions and localization/mapping functions. The odometry data originally for navigation control is also used for pose estimation, and bumper sensor data originally for obstacle avoidance is used for map generation, making the system multi-functional without additional hardware
2Measurement precision
If SLAM techniques are used for localization and mapping, then accurate robot pose estimation and map generation are achieved, but computational expense increases
Solution Approach 1:
The robot utilizes its own operational data generated during normal operation to perform localization and mapping. By using existing odometry and sensor data from regular navigation and obstacle avoidance tasks, the system avoids the computational burden of dedicated SLAM processing while achieving accurate pose estimation and map generation
Solution Approach 2:
The patent combines localization and mapping functions with the robot's primary navigation and obstacle avoidance operations. The same sensors and processing pipelines used for navigation control and safety are merged to perform SLAM functions, eliminating duplicate computational processes and reducing overall computational expense
3Measurement precision
If specialized SLAM sensors are used, then localization and mapping accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The robot system performs localization and mapping using its own operational data from existing sensors without requiring specialized SLAM hardware. The encoders, bumper sensors, gyroscopes, and cameras that are already part of the navigation system generate the necessary data for accurate pose estimation and map generation
Solution Approach 2:
Instead of using specialized SLAM sensors, the system creates virtual representations (copies) of the environment and robot pose using data from existing sensors. The occupancy grid map and pose estimates are computational copies that serve the same purpose as data from dedicated SLAM hardware would provide
Data Source
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.