Vehicle Situation Awareness Using Attention-Based Event Prioritization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated driving systems lack effective situation awareness and efficient data processing, leading to inadequate prioritization and handling of environmental entities, which can result in suboptimal navigation decisions and increased computational complexity.
Innovation Solution
A prioritized attention-based event structure is implemented, using human perception-inspired cognitive analysis to classify and prioritize perception input data into high, low, and no attention zones, and generate a hierarchical event structure that prioritizes entities based on risk levels, enabling efficient data processing and urgent attention zone handling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all perception input data is processed equally without prioritization, then comprehensive situation awareness is achieved, but computational complexity increases and processing efficiency decreases
Solution Approach 1:
The patent segments perception input data into three distinct attention zones (high attention zone, low attention zone, no attention zone) based on entity characteristics and risk levels. This segmentation allows the system to process only relevant data at high priority, reducing computational complexity while maintaining comprehensive situation awareness through hierarchical processing of all zones.
Solution Approach 2:
The patent applies different processing qualities and depths to different spatial zones. High attention zone entities receive detailed, real-time processing with full analysis, while low attention and no attention zone entities receive simplified or periodic processing. This local quality differentiation reduces overall computational complexity while preserving reliability for critical entities.
2Reliability
If all external entities are monitored with equal detail, then complete situation awareness is achieved, but data processing time and computational resources increase
Solution Approach 1:
The patent divides the monitoring scope into three time-criticality segments: high attention zone entities processed immediately with full detail, low attention zone entities processed with reduced detail or lower frequency, and no attention zone entities processed minimally or not at all. This segmentation reduces data processing time while maintaining complete situation awareness through hierarchical coverage.
Solution Approach 2:
The patent applies partial processing action to non-critical entities. Instead of processing all entities with equal detail, the system applies full processing only to high attention zone entities that require immediate response, while applying reduced or selective processing to low and no attention zone entities, thereby reducing overall processing time while maintaining situational awareness.
3Productivity
If a simple classification system is used for external entities, then processing efficiency improves, but navigation decision quality deteriorates
Solution Approach 1:
The patent adds multiple dimensional criteria to the classification system beyond simple spatial zones. Entities are classified using a multi-dimensional framework including spatial position (attention zones), risk level (hazardous, moderate, low risk), entity type (vehicle, pedestrian, animal, obstacle), and behavioral characteristics. This multi-dimensional classification maintains processing efficiency through structured categorization while improving navigation decision quality through comprehensive entity characterization.
Solution Approach 2:
The patent changes the parameters used for entity classification from simple spatial coordinates to a comprehensive set of parameters including risk level, entity type, velocity, acceleration, and predicted trajectory. These parameter changes enable more accurate entity prioritization and navigation decisions while maintaining processing efficiency through systematic parameter evaluation and threshold-based classification.
Data Source
AI summary
A method of using perception-inspired event generation for situation awareness for a vehicle, including receiving perception input data from a sensor of the vehicle and processing the perception input data to classify and generate parameters related to an external entity in a vicinity of the vehicle. The method includes generating a hierarchical event structure that classifies and prioritizes the perception input data by classifying the external entity into an attention zone and prioritizing the external entity within the attention zone according to a risk level value for the external entity. A higher risk level value indicates a higher priority within the attention zone. The method further includes developing a behavior plan for the vehicle based on the hierarchical event structure.