Collective Perception Validation for Misreported Object Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing wireless communication systems face challenges in accurately identifying and addressing misbehaving wireless devices, which can lead to inaccurate object reporting and potentially endanger cooperative and automated driving decisions.

Innovation Solution

The system employs sensor sharing and collective perception mechanisms to validate object detection by receiving messages from wireless devices and determining whether they have misreported objects based on detected object data, allowing for the identification and reporting of misbehaving entities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If sensor data sharing is implemented to improve cooperative driving decisions, then the reliability of object detection is improved, but the system becomes vulnerable to misbehaving wireless devices that can report inaccurate information

Engineering Contradiction:

Improvereliability of object detectionVSAvoidimpact of misbehaving devices

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system implements a feedback mechanism where wireless devices send object detection messages to neighboring devices, which then validate the reported objects against their own sensor data and provide feedback on the accuracy of the reports. This creates a closed-loop system where detection accuracy is continuously verified and improved through inter-device communication and cross-validation.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary validation process where receiving devices act as mediators to verify the authenticity of object reports from transmitting devices. By comparing reported objects with independently detected objects, the system uses the receiving device as an intermediary to filter out misbehaving devices and ensure data reliability before incorporating the information into cooperative driving decisions.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If the system validates object detection by comparing sensor data from multiple devices, then the accuracy of identifying misbehaving devices is improved, but the device complexity increases

Engineering Contradiction:

Improveaccuracy of misbehavior detectionVSAvoidcomplexity of validation mechanism

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies partial validation by focusing on verifying specific critical objects or detection scenarios rather than validating all sensor data from all devices equally. This selective approach maintains high detection accuracy for important objects while reducing the overall computational burden and system complexity by not performing exhaustive validation on every data point.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The validation process is segmented into distinct functional modules: object detection, message transmission, data comparison, misbehavior identification, and response generation. By dividing the complex validation task into these separate, manageable segments, each handled by specific system components, the patent reduces overall system complexity while maintaining comprehensive validation capability.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12205417B2Misbehavior detection using sensor sharing and collective perception

Publication Date: 2025.01.21 QUALCOMM INC

AI summary

Systems and techniques are described for validating object detection. For example, an apparatus can receive a message from a wireless device. The message includes object data corresponding to one or more objects reported by the wireless device to be within a field-of-view of the apparatus. The apparatus can further determine, based on the object data, whether the wireless device has misreported at least one of the one or more objects.