On-Vehicle Simulation Architecture for Repeatable AV Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The testing and validation of autonomous and semi-autonomous driving systems are costly, time-consuming, and disruptive to the development cycle, as they require extensive real-world testing that is difficult to replicate precisely and safely, and software simulations may not accurately represent real-world conditions.
Innovation Solution
The method involves injecting simulated data, such as sensor data, perception data, prediction data, and planning data, into the vehicle's control system to create a controlled and repeatable testing environment, allowing for precise characterization of vehicle behavior under various scenarios without the need for physical setup and real-world testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-world testing is conducted to validate autonomous driving systems, then testing accuracy and reliability are improved, but testing cost and time consumption increase significantly
Solution Approach 1:
The patent applies preliminary action by pre-configuring test scenarios, environmental conditions, and test sequences in a simulation environment before actual vehicle testing. Test protocols, boundary conditions, and expected outcomes are established in advance through software simulation, allowing systematic validation without repeated physical setup. This reduces on-site testing time while maintaining validation rigor.
Solution Approach 2:
The patent uses copying by creating virtual replicas of real-world driving scenarios, road conditions, weather environments, and traffic patterns in a simulation system. These digital twins enable repeated testing of identical scenarios without physical reconstruction, allowing comprehensive validation of autonomous driving systems at lower cost and with faster iteration cycles.
2Reliability
If real-world testing is conducted to validate autonomous driving systems, then testing reliability is improved, but testing cost increases significantly
Solution Approach 1:
The patent employs copying by creating virtual test environments that replicate real-world driving conditions, road geometries, weather patterns, and traffic scenarios. This digital replication allows comprehensive system validation without the substantial costs of physical test track setup, vehicle deployment, and personnel coordination required for equivalent real-world testing programs.
Solution Approach 2:
The patent applies this principle by using software-based test scenarios that can be rapidly created, modified, and discarded without physical infrastructure investment. Virtual test cases can be generated algorithmically and executed repeatedly at minimal marginal cost, replacing expensive and time-consuming physical test setups that would require significant resource allocation for each test iteration.
3Productivity
If software simulation is used for testing autonomous driving systems, then testing cost and time are reduced, but testing accuracy may decrease due to differences between simulated and real-world features
Solution Approach 1:
The patent implements feedback by continuously comparing simulation results with real-world test data to validate and refine the simulation model. Discrepancies between simulated and actual vehicle responses are used to adjust simulation parameters, environmental models, and system dynamics, ensuring the virtual environment accurately reflects real-world behavior while maintaining high testing throughput.
Data Source
AI summary
In one embodiment, a computing system of a vehicle generates perception data based on sensor data captured by one or more sensors of the vehicle. The perception data includes one or more representations of physical objects in an environment associated with the vehicle. The computing system further determines simulated perception data that includes one or more representations of virtual objects within the environment and generates modified perception data based on the perception data and the simulated perception data. The modified perception data includes at least one of the one or more representations of physical objects and the one or more representations of virtual objects. The computing system further determines a path of travel for the vehicle based on the modified perception data, which includes the one or more representations of the virtual objects.