Obstacle Detection Database Management Using Multi-Source Weightages
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aircraft navigating complex environments face safety risks due to new obstacles not included in periodic obstacle and terrain databases, leading to inefficient navigation and resource consumption in communication bandwidth and storage.
Innovation Solution
A system that detects new obstacles using onboard sensors, determines their nature by comparing with known objects, updates databases with multi-source weightages, and performs actions based on these weightages to enhance safety and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If obstacle databases are updated periodically by database suppliers, then the databases remain manageable in size and update frequency, but new obstacles encountered between release periods are not detected, creating flight safety risks
Solution Approach 1:
The system performs preliminary detection of obstacles using onboard sensors before they become a safety risk. By continuously scanning the environment and comparing detected objects against the periodic database updates, the system proactively identifies new obstacles that would otherwise be missed between database releases, preventing safety incidents rather than reacting to them later
Solution Approach 2:
The system implements a feedback mechanism where detected unknown objects are reported to an off-board service, which then provides weightage information back to update the obstacle database. This closed-loop feedback ensures that new obstacles detected by individual vehicles are shared with the broader system, improving collective awareness and preventing other vehicles from encountering the same undetected obstacles
2Reliability
If database updates are transmitted frequently to capture new obstacles, then new obstacle detection improves, but communication bandwidth and onboard storage resources are consumed
Solution Approach 1:
Instead of performing complete database updates for every detected object, the system applies partial action by only transmitting and processing information for unknown objects that require verification. The off-board service assigns weightages to filter out false detections, and only confirmed obstacles trigger database updates. This selective approach consumes minimal communication bandwidth and storage resources while maintaining high detection accuracy
Solution Approach 2:
The off-board service acts as an intermediary between individual vehicle detections and the central obstacle database. Rather than each vehicle directly updating the database (which would consume excessive resources), the intermediary aggregates detections, assigns weightages to filter false positives, and manages updates efficiently. This intermediary layer optimizes resource usage by coordinating updates across the entire vehicle fleet rather than allowing independent, redundant updates
3Reliability
If all detected unknown objects are added to the obstacle database, then detection coverage is maximized, but false detections and navigation inefficiency increase
Solution Approach 1:
The system changes the parameter of object verification by introducing weightage values that represent the confidence level of obstacle detection. Instead of treating all detections equally (binary yes/no), the weightage parameter allows the system to prioritize confirmed obstacles over uncertain detections. This parameter transformation enables efficient navigation by allowing vehicles to confidently avoid high-weightage obstacles while treating low-weightage detections as lower priority, maintaining navigation speed and efficiency
Data Source
AI summary
Disclosed are methods, systems, and computer-readable medium for obstacle detection and database management using multi-source weightages. For instance, the method may include: responsive to a detection of an object, determining whether the object is a known object or an unknown object based on object features and known objects indicated by vehicle state information and an obstacle database; responsive to a determination that the object is an unknown object, updating the obstacle database with unknown object information and transmitting the unknown object information to an off-board service; receiving a response from the off-board service, the response including a weightage assigned to the unknown object; updating the obstacle database with the weightage assigned to the unknown object; and performing at least one action based on the weightage of the unknown object.