Sensor Data Sharing With Privacy Filtering for Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face challenges in efficiently sharing sensor data while protecting personal information and generating high-definition maps, and they lack effective methods for selective data sharing based on event occurrences or object classes, which affects data sharing efficiency and vehicle control, particularly in handling risks like blind spots.
Innovation Solution
A method for sharing sensor data between devices that involves processing point data to include privacy protection when personal information is involved, determining data sharing based on object classes, and generating different sharing data sets based on event occurrences, allowing for efficient data transmission and vehicle path calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If sensor data is shared to improve autonomous driving performance and generate high-definition maps, then the quality and quantity of available data increases, but personal information of pedestrians and objects may be exposed
Solution Approach 1:
The patent extracts and removes personal information from sensor data before sharing. The processing unit identifies and removes identifying features such as facial features, license plate numbers, and other personal identifiers from the original sensor data, creating anonymized data that maintains utility for autonomous driving while protecting privacy
Solution Approach 2:
The patent applies different processing quality levels to different regions of the sensor data. Important areas for autonomous driving (road conditions, obstacles, traffic signs) are preserved with high quality, while areas containing personal information are processed with lower quality or anonymized, creating locally differentiated data quality
2Measurement precision
If all sensor data is shared to improve map generation accuracy, then the completeness of high-definition maps increases, but data transmission efficiency decreases
Solution Approach 1:
The patent segments sensor data into different categories based on importance and type (e.g., road infrastructure data, obstacle data, environmental data). This segmentation allows selective sharing of only necessary data portions, reducing overall transmission volume while maintaining map generation accuracy for critical elements
Solution Approach 2:
The patent changes data representation parameters by converting detailed sensor data into simplified formats suitable for map generation. This includes transforming point cloud data into polygon representations, converting high-resolution images into lower-resolution maps, and encoding spatial relationships in compressed formats
3Reliability
If sensor data is processed to protect privacy, then personal information security improves, but data processing complexity increases
Solution Approach 1:
The patent performs preliminary privacy protection processing on sensor data before it leaves the collecting device. The processing unit anonymizes data in real-time during the data acquisition phase, so that personal information is removed before transmission, reducing the need for complex post-processing at receiving devices
4Productivity
If selective data sharing based on object class is implemented, then data sharing efficiency improves, but the complexity of data classification increases
Solution Approach 1:
The patent segments objects detected by sensors into different classes (e.g., vehicles, pedestrians, infrastructure, animals) and applies different sharing strategies to each class. This classification-based segmentation enables efficient selective sharing by treating different object types differently based on their relevance to autonomous driving
Data Source
AI summary
Sharing sensor data of a first device with a second device includes obtaining a set of point data from at least one of a sensors located in the first device, generating a first property data of the first subset of point data based on the first subset of point data, generating a sharing data including at least a portion of the first subset of point data and the first property data, and transmitting the sharing data to the second device. If a class of a first object included in the class information a class in which personal information must be protected, a content of the sharing data includes a privacy protection data in which the first subset of point data is processed such that personal information of the first object does not identified by the second device.