Cognition-Enabled Driving Pattern Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-driving vehicles lack the ability to consider historical patterns of nearby vehicles and do not utilize cognition to provide comprehensive information to drivers, resulting in incomplete situational awareness and inaccurate information delivery.
Innovation Solution
A cognition-enabled driving pattern detection system that analyzes real-time and historical data from various sources to predict driving outcomes and provide natural language notifications to drivers, using a computer system with modules for data reception, storage, analytics, detection, and notification, integrated with vehicle systems and sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If self-driving vehicles use sensors to build environmental images, then positional information is obtained, but comprehensive cognitive understanding of driving situations is lacking
Solution Approach 1:
The system performs preliminary actions by collecting and storing historical driving data from multiple sources (sensors, telematics, external databases) before actual driving pattern detection is needed. This pre-collection of data enables the cognitive system to have access to historical patterns when making real-time driving decisions, resolving the information loss problem.
Solution Approach 2:
The invention adds a temporal dimension to the environmental images by integrating historical driving data with real-time sensor data. This transforms the system from processing only spatial information to processing spatio-temporal information, enabling comprehensive cognitive understanding that includes both current situation and historical patterns.
2Reliability
If historical driving data is collected and analyzed, then predictive driving outcomes are detected, but system complexity increases
Solution Approach 1:
The cognitive system is segmented into distinct functional modules: data collection module, data storage module, data analysis module, pattern detection module, and notification module. Each module handles specific aspects of the complex task, making the overall system more manageable and maintainable while achieving high prediction accuracy through coordinated operation of specialized components.
Solution Approach 2:
The system introduces intermediary components including processors that mediate between raw sensor data and driving pattern detection, and communication interfaces that mediate between the cognitive system and external data sources. These intermediaries simplify the architecture by providing standardized interfaces and abstraction layers.
3Speed
If real-time sensor data is processed, then current driving situations are monitored, but historical pattern recognition is insufficient
Solution Approach 1:
Historical driving data is collected and stored in advance in databases before real-time analysis is needed. This preliminary data preparation allows the system to quickly query and compare historical patterns during real-time operation without sacrificing processing speed, as the heavy lifting of data collection is already complete.
Solution Approach 2:
The system maintains continuous operation by simultaneously processing real-time sensor data while querying historical databases for pattern matching. This continuous action ensures that both real-time monitoring and historical pattern recognition occur without interruption, providing comprehensive situational awareness.
Data Source
AI summary
A method, and associated computer system and computer program product, for cognition enabled driving pattern detection that includes receiving driving related data, storing the driving related data in one or more data repositories, receiving real-time driving data from at least one sensor related to an active driving situation, analyzing the driving related data and the real-time driving data, detecting a predictive driving outcome prior to the occurrence of the predictive driving outcome based on the analyzing, and notifying a driver based on the predictive driving outcome.