Transformed Sensor Data for Realistic AEB Test Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous emergency braking (AEB) and collision mitigation warning (CMW) systems face challenges in accurately testing their performance due to the limitations of using either fake objects or synthetically generated sensor data, which can lead to unsafe deployments in real-world environments.
Innovation Solution
The system transforms real-world sensor data captured from actual vehicle operations into simulated test data based on a physics model and desired vehicle states, allowing for the generation of accurate and reliable test data without the need for extensive real-world data collection or virtual simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-world sensor data is collected through field testing to accurately test AEB systems, then measurement precision and reliability improve, but loss of time and cost increase significantly
Solution Approach 1:
The system performs preliminary actions by collecting and storing sensor data during normal vehicle operations before the actual testing phase. This pre-collected data is then transformed and used for comprehensive AEB system testing, eliminating the need for time-consuming field testing specifically for data collection purposes.
Solution Approach 2:
The system creates transformed copies of real-world sensor data that preserve the essential characteristics and patterns of actual driving scenarios. These transformed data copies are used for testing AEB systems, providing realistic test conditions without requiring physical field testing.
2Reliability
If real-world sensor data is collected through field testing to accurately test AEB systems, then reliability improves, but cost increases significantly
Solution Approach 1:
The system creates transformed copies of real-world sensor data that preserve the essential characteristics and patterns of actual driving scenarios. These transformed data copies are used for testing AEB systems, providing realistic test conditions without requiring expensive field testing infrastructure.
Solution Approach 2:
The system leverages data that is naturally generated during normal vehicle operations and self-service purposes. The sensor data collected during regular driving is repurposed for AEB testing, eliminating the need for separate expensive field testing campaigns.
3Productivity
If synthetically generated sensor data is used to test AEB systems, then productivity increases, but measurement precision deteriorates
Solution Approach 1:
Instead of generating synthetic data, the system copies and transforms real sensor data patterns. The transformation process creates realistic test scenarios by modifying existing real-world data, preserving the authenticity and precision characteristics of actual sensor measurements while enabling diverse testing conditions.
Data Source
AI summary
In various examples, sensor data recorded in the real-world may be leveraged to generate transformed, additional, sensor data to test one or more functions of a vehicle—such as a function of an AEB, CMW, LDW, ALC, or ACC system. Sensor data recorded by the sensors may be augmented, transformed, or otherwise updated to represent sensor data corresponding to state information defined by a simulation test profile for testing the vehicle function(s). Once a set of test data has been generated, the test data may be processed by a system of the vehicle to determine the efficacy of the system with respect to any number of test criteria. As a result, a test set including additional or alternative instances of sensor data may be generated from real-world recorded sensor data to test a vehicle in a variety of test scenarios—including those that may be too dangerous to test in the real-world.