Unmanned Vehicle Path Risk Modeling for BVLOS Operations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current unmanned vehicle systems lack effective, automated, and real-time risk assessment and management capabilities, particularly for beyond visual line of sight (BVLOS) and autonomous operations, relying heavily on manual and offline processes.
Innovation Solution
A federated unmanned vehicle risk assessment system that integrates multiple geospatial-geotemporal data sources with risk models, providing real-time risk metrics and optimized trajectories through an API, suitable for both human-controlled and autonomous vehicles, aligning with FAA standards and local regulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual and offline risk assessment processes are used for unmanned vehicle operations, then system complexity is reduced, but risk assessment reliability and real-time monitoring capability deteriorate
Solution Approach 1:
The risk assessment system is segmented into multiple specialized modules including hazard identification module, risk analysis module, trajectory optimization module, and monitoring module. Each module handles specific aspects of risk assessment independently, improving reliability through specialized processing while managing complexity through functional decomposition
Solution Approach 2:
A central processing server acts as an intermediary between unmanned vehicles, ground control stations, and risk assessment algorithms. This intermediary coordinates data flow and computation tasks, enabling reliable real-time assessment without requiring complex direct connections between all system components
2Productivity
If real-time risk assessment and continuous monitoring are implemented, then risk monitoring capability is improved, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary risk assessment calculations during trajectory planning phases before actual vehicle operations begin. By pre-computing risk metrics and optimized trajectories, the system reduces real-time computational requirements and enables faster response during actual operations
Solution Approach 2:
The monitoring system uses periodic sampling of vehicle position and environmental data at optimized intervals rather than continuous monitoring. This periodic approach maintains effective risk monitoring capability while significantly reducing data processing time and computational resource requirements
3Measurement precision
If multiple geospatial-geotemporal data sources are integrated, then risk assessment accuracy is improved, but data integration complexity increases
Solution Approach 1:
The system employs a universal data integration framework that handles multiple geospatial-geotemporal data sources (weather data, terrain data, traffic data, regulatory constraints) through standardized processing protocols. This multi-functional framework improves risk assessment accuracy by incorporating diverse data sources while managing integration complexity through unified processing methods
4Extent of automation
If automated risk assessment systems are deployed for BVLOS and autonomous operations, then operational autonomy is improved, but system reliability requirements increase
Solution Approach 1:
The system implements beforehand cushioning by pre-planning multiple risk-mitigated trajectory options and pre-identifying hazard zones before autonomous operations begin. This preparation creates a safety buffer that allows higher operational autonomy while maintaining reliability, as the system has pre-computed fallback options and risk mitigation strategies ready for deployment
Data Source
AI summary
A method includes receiving a first navigation path risk request that includes first navigation path information associated with a first navigation path for a first unmanned vehicle through a first environment. The method also includes selecting a first risk model from a plurality of risk models based on the first navigation path information. The method also includes obtaining first data used as one or more inputs to run the first risk model from one or more data sources. The method also includes operating the first risk model with the first data to output a first risk score. The method also includes providing a first navigation path risk response in response to the first navigation path risk request that includes the first risk score that is associated with at least a portion of the first navigation path.