Driving-Task Sensor Classification for Real-Time Vehicle Monitoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional vehicle monitoring systems face challenges in processing large amounts of data from multiple sensors in real-time, especially in complex traffic situations, leading to unreliable detection of relevant objects, and require significant computational resources.

Innovation Solution

A monitoring system that classifies sensors into subsets based on the driving task, prioritizing sensor data processing to allocate computational resources efficiently, allowing for situational-dependent processing and reduced processing of less critical regions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple sensors are processed in parallel to improve situational awareness, then the coverage and detection capability are improved, but the computational resources and processing time are significantly increased

Engineering Contradiction:
Improvedetection reliabilityVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the sensor group into multiple subsets based on their relevance to the current driving task. The classification module divides sensors into first subset (highly relevant), second subset (moderately relevant), and third subset (less relevant). This segmentation allows the processing module to handle only the necessary subsets, reducing computational complexity while maintaining detection reliability for critical sensors.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by assigning different processing priorities to different sensor subsets based on their specific relevance to the driving task. Sensors in the first subset receive full processing priority, while sensors in lower-priority subsets receive reduced processing. This differential treatment optimizes computational resource allocation according to the specific needs of each sensor group.

Inventive Principle:
Principle #3Local quality

2Reliability

If all sensors are processed with equal priority to ensure comprehensive monitoring, then the coverage is improved, but the processing time and computational load increase

Engineering Contradiction:
Improvemonitoring reliabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent implements dynamic priority assignment where the classification of sensors into subsets is not fixed but changes based on the current driving task and situational context. The classification module continuously evaluates sensor relevance and adjusts subset assignments dynamically, allowing the system to adapt processing priorities in real-time according to changing driving conditions, thereby reducing processing time while maintaining monitoring reliability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the processing parameter (priority level) of different sensor subsets based on the driving task requirements. By modifying the processing priority parameter dynamically, the system can focus computational resources on critical sensors during specific driving scenarios, reducing overall processing time while ensuring that essential monitoring functions maintain adequate reliability.

Inventive Principle:
Principle #35Parameter changes

3Area of stationary object

If more sensors are installed to improve situational awareness, then the coverage area is increased, but the data processing complexity and computational requirements increase

Engineering Contradiction:
Improvecoverage areaVSAvoiddata processing complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The patent extracts and processes only the essential sensor data required for the current driving task. By using the classification module to identify and separate highly relevant sensors (first subset) from less relevant ones, the system extracts only the critical data streams that need full processing attention. This extraction approach allows comprehensive sensor coverage to be maintained physically, while computationally only the necessary portion is fully processed, reducing data processing complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

4Measurement precision

If sensor data from all regions is processed with high priority, then the detection accuracy is improved, but the computational resources required increase

Engineering Contradiction:
Improvedetection accuracyVSAvoidcomputational resources
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by providing high-priority processing only to sensor subsets that are partially sufficient for the current driving task, rather than processing all sensors with equal high priority. The classification module identifies the minimum necessary subset of sensors (first subset) that provides adequate detection accuracy for the specific driving context. This partial processing approach maintains sufficient detection accuracy while significantly reducing computational resource consumption compared to processing all sensors at full priority.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4287146A1Monitoring system and method for monitoring
Publication Date: 2023.12.06 KNORR BREMSE SYSTEME FUER NUTZFAHIZEUGE GMBH
  • EP4287146A1 patent drawingFigure 1
  • EP4287146A1 patent drawingFigure 2
  • EP4287146A1 patent drawingFigure 3

AI summary

A monitoring system (100) for an environment of a vehicle (10) is disclosed. The vehicle (10) comprises a group of sensors (20) adapted to cover various regions of the environment. The monitoring system (100) includes a receiving module (110), a classification module (120), and a processing module (130). The receiving module (110) is adapted to obtain information (115) about a driving task of the vehicle (10). The classification module (120) is adapted to classify, based on the obtained information (115), the group of sensors (20) in at least a first subset (21) and a second subset (22). The processing module (130) is adapted to process sensor data of the first subset (21) with higher priority than sensor data from sensors from the second subset (22).