Image-Feature Markers for SLAM-Based Mobile Exploration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous mobile devices (AMDs) face challenges in accurately mapping and navigating physical spaces due to sensor limitations, such as field of view, blind spots, and uncertainty from factors like sensor noise and dynamic obstacles, leading to inaccuracies in obstacle localization and navigation.
Innovation Solution
The use of markers based on image features allows for efficient exploration and mapping by designating observation targets and goal poses to optimize sensor data collection, reducing duplicative efforts and improving navigation accuracy through the alignment of submaps and occupancy maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor-based mapping is used, then obstacle detection is performed, but inaccuracies occur due to sensor limitations and noise
Solution Approach 1:
The patent introduces markers as intermediary objects placed in the physical environment. These markers serve as mediators between the AMD and the physical space, providing stable, easily detectable reference points that compensate for sensor limitations. The markers act as intermediaries that bridge the gap between imperfect sensor data and accurate spatial understanding, enabling more reliable obstacle localization and navigation.
2Measurement precision
If comprehensive sensor scanning is performed to improve mapping accuracy, then more data is collected, but time consumption and resource usage increase
Solution Approach 1:
The patent employs markers that are placed in advance in the physical environment before the AMD begins its exploration. These pre-positioned markers provide immediate reference points that guide the AMD's movement and data collection efforts. By having markers ready beforehand, the system eliminates the need for extensive preliminary scanning to establish reference frames, significantly reducing exploration time while maintaining high mapping accuracy.
Solution Approach 2:
The patent creates a simplified representation of the physical space by using markers as surrogate reference objects. Instead of requiring the AMD to scan and process all environmental features to build spatial understanding, the system uses a subset of carefully placed markers as representative copies of the environment's structure. This copying approach allows accurate mapping with minimal data collection, reducing both time and computational resource consumption.
3Adaptability or versatility
If multiple sensors are used to overcome blind spots, then coverage is improved, but device complexity increases
Solution Approach 1:
The markers serve as intermediaries that provide unambiguous reference information visible from multiple angles and positions. This allows a single sensor on the AMD to effectively achieve multi-sensor coverage by leveraging the geometric relationships between the AMD, multiple markers, and the physical environment. The markers mediate the sensing process, enabling comprehensive spatial understanding without requiring complex multi-sensor systems.
Data Source
AI summary
An autonomous mobile device (AMD) uses sensors to explore a physical space and determine the locations of obstacles. Simultaneous localization and mapping (SLAM) techniques are used by the AMD to designate as keyframes some images and their associated descriptors of features in the space. Each keyframe indicates a location and orientation of the AMD relative to those features. Anchors are specified relative to keyframes. A marker is specified relative to one or more anchors. Because markers are associated with features in the physical space, they maintain their association with the physical space through various processes such as SLAM loop closures. Markers may specify locations in the physical space, such as navigation waypoints, navigation destinations such as a goal pose for exploring an unexplored area, as an observation target to facilitate exploration, and so forth. Markers may also be used to specify block listed locations to be avoided during exploration.