Operational testing of autonomous vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for testing autonomous vehicle algorithms are inefficient and unsafe, as they require extensive real-world testing, which is dangerous and costly, and existing simulators lack the capability to realistically model interactions with other vehicles in a time-efficient manner.
Innovation Solution
The development of a simulation framework that enables 'super real-time' simulation of autonomous vehicle systems, allowing for the collection of data to improve algorithm training, sensor accuracy, and road data quality by configuring primary and secondary vehicular models with algorithms and trajectories, and integrating updated algorithms into autonomous vehicle systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-world driving environments are used for testing autonomous algorithms, then the testing realism and validity are improved, but the safety risks and costs increase significantly
Solution Approach 1:
The patent creates virtual copies of real-world driving environments, vehicles, and scenarios through high-fidelity simulation. The simulation system replicates physical laws, vehicle dynamics, and environmental conditions without using actual physical resources, thereby eliminating safety risks while preserving testing validity through accurate virtual modeling.
2Object-affected harmful factors
If traditional simulators are used to test autonomous vehicles, then safety risks are reduced, but the testing efficiency and realism deteriorate
Solution Approach 1:
The system pre-generates diverse driving scenarios, environmental conditions, and vehicle behaviors before actual testing begins. Virtual vehicles and environmental elements are prepared in advance with predefined trajectories and interaction patterns, enabling rapid sequential testing without time-consuming real-world setup while maintaining safety through virtual containment.
3Reliability
If more real-world testing is conducted to improve algorithm robustness, then the algorithm reliability is improved, but the time and cost increase significantly
Solution Approach 1:
The simulation system executes periodic, systematic testing cycles through diverse scenarios including normal driving, edge cases, and failure conditions. Multiple virtual vehicles simultaneously undergo repeated testing iterations across various environmental conditions, accelerating robustness validation through high-frequency periodic evaluation rather than slow sequential real-world testing.
4Reliability
If the simulation models include complex interactions with other vehicles and environments, then the testing realism is improved, but the computational complexity and time consumption increase
Solution Approach 1:
The simulation system divides the complex driving environment into independent modular components: primary vehicle model, secondary vehicle models, environmental elements, and interaction physics. Each component is modeled separately with standardized interfaces, allowing realistic complex interactions to be composed from simpler validated modules, reducing overall computational complexity through systematic decomposition.
Data Source
AI summary
Disclosed are devices, systems and methods for the operational testing on autonomous vehicles. One exemplary method includes configuring a primary vehicular model with an algorithm, calculating one or more trajectories for each of one or more secondary vehicular models that exclude the algorithm, configuring the one or more secondary vehicular models with a corresponding trajectory of the one or more trajectories, generating an updated algorithm based on running a simulation of the primary vehicular model interacting with the one or more secondary vehicular models that conform to the corresponding trajectory in the simulation, and integrating the updated algorithm into an algorithmic unit of the autonomous vehicle.