Autonomous Vehicle Test Logging for Fleet-Scale Parameter Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion control systems for autonomous vehicles rely on physical models that require numerous tests to identify parameters, leading to inefficiencies in data collection and analysis, especially when scaling to a fleet of vehicles, with little attention given to structured testing and data isolation.
Innovation Solution
A system that includes an on-board computing device for autonomous vehicles to execute structured tests, log response data, generate metadata, and transmit relevant logs for parameter identification, enabling efficient data analysis and model parameter estimation across a fleet.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If hundreds of tests are run per vehicle to identify model parameters, then measurement precision is improved, but productivity deteriorates due to the large number of tests required
Solution Approach 1:
The patent segments the testing process by introducing structured test identifiers and organizing tests into specific categories (e.g., actuator tests, motion response tests). Each test is assigned a unique identifier that structures the data collection process, allowing efficient retrieval and analysis of specific test results without requiring manual search through all logged data.
Solution Approach 2:
The patent implements preliminary action by pre-defining test input profiles with associated metadata schemas before actual testing begins. The system prepares the data structure in advance, including predetermined fields for test identifiers, timestamps, and parameter categories, so that during testing only the actual measurements need to be captured without requiring post-test data organization.
2Measurement precision
If all test data is logged to comprehensive log files, then measurement precision is improved, but ease of operation deteriorates due to the need to search and categorize specific data segments
Solution Approach 1:
The patent introduces an intermediary layer between the raw test data and the analysis process. Structured metadata fields act as intermediaries that automatically organize and label data segments during the logging process itself, eliminating the need for manual search and categorization while preserving complete measurement data.
Solution Approach 2:
The system implements self-service by automatically generating and attaching structured metadata to each test data segment during the logging process. The data organization occurs autonomously without human intervention, with the system itself performing the categorization and labeling that would otherwise require manual effort.
3Productivity
If tests are run across a fleet of autonomous vehicles, then productivity is improved through parallel data collection, but device complexity increases due to the need for standardized testing frameworks
Solution Approach 1:
The patent implements universality by creating a standardized test identifier framework that can be applied across all vehicles in the fleet regardless of specific test type or vehicle configuration. The same metadata structure and identification scheme universally apply to all tests, enabling consistent data collection and analysis across the entire fleet without requiring vehicle-specific customization.
4Measurement precision
If manual data search and categorization is performed, then measurement precision is improved through careful data selection, but loss of time increases due to the manual processing required
Solution Approach 1:
The system performs self-service by automatically organizing and labeling test data with structured metadata during the logging process itself. The data selection and categorization occur autonomously without human intervention, eliminating the time-consuming manual search process while maintaining accurate data identification through pre-defined metadata fields.
Data Source
AI summary
A system for testing an autonomous vehicle obtains a list of required tests the autonomous vehicle is to run, where each test is part of a commissioning process for the autonomous vehicle. The system causes the list to be displayed on a display device of the autonomous vehicle, receives a selection of a selected test from an operator of the autonomous vehicle, and receives a test input profile associated with the selected test. The system causes the autonomous vehicle to execute at the instructions of the test input profile, and logs response data to one or more log files. During execution of the test instructions, the system generates metadata associated with the selected test. The system logs the metadata to the one or more log files, and transmits at least a portion of the one or more log files to an electronic device located remotely from the autonomous vehicle.