Occupancy Mapping That Excludes Moving Objects in Indoor Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional approaches to building a map of a physical space often fail to accurately distinguish between stationary and non-stationary objects, leading to misclassifications that result in incorrect occupancy maps and hinder autonomous navigation.
Innovation Solution
An autonomous mobile device (AMD) uses sensor data from depth sensors and image sensors to classify objects as stationary or non-stationary, excluding non-stationary objects from the occupancy map to prevent clutter and ensure accurate path planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping approaches are used to build an occupancy map, then the map includes all detected objects, but non-stationary objects are misclassified as stationary objects leading to map clutter and navigation errors
Solution Approach 1:
The system applies dynamics by continuously tracking objects across multiple time frames and using motion history to distinguish stationary from non-stationary objects. Objects are re-evaluated over time, and their classification changes based on observed motion patterns, allowing the system to adapt to dynamic environments while maintaining accurate occupancy maps
Solution Approach 2:
The system performs preliminary classification of objects as potential non-stationary objects before finalizing the occupancy map. By pre-identifying and tracking moving objects separately, the system prevents them from contaminating the stationary object map in advance, ensuring map accuracy before navigation decisions are made
2Measurement precision
If multiple sensors are used to detect objects, then object detection capability is improved, but the complexity of distinguishing stationary from non-stationary objects increases
Solution Approach 1:
The system segments the object classification process into distinct stages: initial detection by multiple sensors, tracking across time frames, motion analysis, and final classification. This segmentation breaks down the complex task of distinguishing stationary from non-stationary objects into manageable steps, reducing overall system complexity while maintaining high detection accuracy
Solution Approach 2:
The tracking system serves multiple functions simultaneously: it detects objects, determines their motion state, classifies them as stationary or non-stationary, and provides this information to the occupancy map builder. This multi-functionality reduces the need for separate specialized systems, thereby reducing complexity while maintaining comprehensive object detection and classification capabilities
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A physical space contains stationary objects that do not move overtime (e.g., a couch) and may have non-stationary objects that do move over time (e.g., people and pets). An autonomous mobile device (AMD) determines and uses an occupancy map of stationary objects to find a route from one point to another in a physical space. Non-stationary objects are detected and prevented from being incorrectly added to the occupancy map. Point cloud data is processed to determine first candidate objects. Image data is processed to determine second candidate objects. These candidate objects are associated with each other and their characteristics assessed to determine if the candidate objects are stationary or non-stationary. The occupancy map is updated with stationary obstacles. During navigation, the occupancy map may be used for route planning while the non-stationary objects are used for local avoidance.