Autonomous Lawnmower Self-Localization via Image Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous locomotion devices, such as lawnmowers, face challenges in precise self-localization and movement strategy development, especially in dynamic environments with prominent visual objects, requiring significant computing power and lacking independence from specific visual features.
Innovation Solution
The device employs an image acquisition unit, computing unit, and memory unit to compare current environmental images with stored sequences, generating optical flow and motion vectors to develop a movement strategy, allowing for precise self-localization and autonomous navigation independent of prominent visual objects, using a method that requires minimal computing power and accounts for historical data during a learning process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous locomotion devices use prominent visual objects for self-localization, then localization can be achieved, but the device becomes dependent on specific visual features and requires significant computing power
Solution Approach 1:
The system performs preliminary actions by storing multiple environmental images and sequences in advance during a learning phase. These pre-stored images serve as reference data for later self-localization, eliminating the need for complex real-time processing of prominent visual objects.
Solution Approach 2:
The system creates copies of environmental images and stores them in memory units. Instead of processing complex visual features in real-time, the device compares current sensor data with stored image copies to achieve self-localization, significantly reducing computing power requirements.
2Ease of operation
If autonomous locomotion devices rely on prominent visual objects for navigation, then movement strategy can be developed, but the device lacks independence from specific visual features
Solution Approach 1:
The system uses environmental images that serve multiple functions: they are stored as reference data, used for self-localization, and serve as basis for movement strategy development. This multi-functional approach eliminates dependence on specific prominent visual objects while maintaining ease of operation.
Solution Approach 2:
The system changes the parameter basis for navigation from relying on prominent visual objects to using stored environmental image sequences. This parameter change enables the device to develop movement strategies independently of specific visual features while maintaining operational ease.
3Loss of time
If autonomous locomotion devices process environmental images in real-time, then current position can be determined, but computing power consumption increases
Solution Approach 1:
Environmental images are stored in advance during a learning phase, creating a reference library before actual navigation begins. This preliminary action eliminates the need for complex real-time processing, reducing both time loss and computing power consumption during operation.
Solution Approach 2:
The system stores copies of environmental images in memory units for later comparison. This copying approach allows rapid position determination through simple comparison operations rather than complex real-time processing, significantly reducing computing power consumption.
Data Source
Figure 1
AI summary
The invention relates to an autonomous transportation device, in particular to an autonomous lawnmower, having at least one image capture unit (12) for recording at least one environmental image and/or at least one environmental image sequence, having at least one computation unit (14) at least for evaluating the recorded environmental image and/or the environmental image sequence and having at least one memory unit (16) for storing at least one environmental image and/or at least one environmental image sequence. According to the invention the computation unit (14), in at least one operating state for creating a movement strategy, executes a movement estimation by comparing at least one environmental image recorded by the image capture unit (12) and/or an environmental image sequence recorded by the image capture unit (12) with an environmental image stored in the memory unit (16) and/or with an environmental image sequence stored in the memory unit (16).