Autonomous Mobile Apparatus SLAM Tracking Failure Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous mobile apparatuses face challenges in maintaining accurate environment mapping due to inaccuracies in odometry-based location estimation, particularly when SLAM processing fails, leading to less accurate route planning and potential navigation issues.
Innovation Solution
The autonomous mobile apparatus employs a processor with drive-based and non-drive-based location estimators, a range sensor, and a map creation module to create and update an environment map, saving the map during SLAM processing failures and restoring it when tracking is re-established, ensuring accurate mapping and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If SLAM processing is used to estimate apparatus location, then measurement precision of location is improved, but reliability deteriorates when tracking fails
Solution Approach 1:
The system performs preliminary actions by saving the environment map and timing information before SLAM tracking failure occurs. When tracking fails, the system restores the previously saved map and timing data, allowing seamless continuation without losing location estimation reliability. This preliminary saving and restoring mechanism resolves the contradiction by preparing backup data in advance.
Solution Approach 2:
The system applies beforehand cushioning by creating and storing backup environment maps and timing information before tracking failures occur. This cushioning mechanism ensures that when SLAM tracking fails, the system can revert to previously valid data, preventing complete loss of location estimation reliability while maintaining high measurement precision during normal operation.
2Manufacturing precision
If environment map is continuously updated during operation, then manufacturing precision of map data is improved, but loss of information increases when tracking fails
Solution Approach 1:
The system performs preliminary action by saving the environment map and timing information before SLAM tracking failure. This allows the system to restore accurate map data from a known good state, preventing information loss while maintaining continuous map updates during normal operation. The preliminary saving ensures map precision is preserved across tracking failures.
Solution Approach 2:
The system applies discarding and recovering by temporarily discarding the current environment map when tracking fails and recovering the previously saved map data. This mechanism prevents permanent information loss by selectively discarding potentially corrupted data and recovering verified accurate data, thus maintaining high manufacturing precision of the environment map.
3Measurement precision
If SLAM tracking is continuously performed, then measurement precision of location is improved, but loss of time increases during tracking failures
Solution Approach 1:
The system performs preliminary action by saving timing information along with the environment map before tracking failures. When tracking fails, the system restores both the map and timing data, allowing immediate resumption of navigation without time loss. This preliminary saving of timing information prevents navigation delays during and after tracking failures.
Data Source
AI summary
An autonomous mobile apparatus includes a driving unit, a memory including a map memory, and a processor. The processor is configured to estimate an apparatus location based on information from the driving unit and estimate the apparatus location based on information from other than the driving unit. The processor is configured to acquire a location of an object around the autonomous mobile apparatus, create an environment map based on the estimated apparatus location and the acquired object location, and store the environment map in the map memory. The processor is configured to use, at a time of tracking when the estimation of the apparatus location based on the information from other than the driving unit is enabled, the environment map that is in the map memory at a time of reference determined by a time of loss when the estimation of the apparatus location is not enabled.