Real-Virtual Driving Verification Using Urban Infrastructure Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous driving vehicle testing systems face challenges in replicating real-world road conditions and scenarios, leading to limitations in verifying performance and safety due to the difficulty in simulating complex urban environments and unexpected situations without causing accidents.
Innovation Solution
An autonomous driving verification system that converges real and virtual information to create a simulated environment, using sensors and virtual information to control vehicle functions, incorporating infrastructure elements like signal controllers and pedestrian detectors, to test autonomous driving capabilities in a controlled setting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If testing is conducted on real roads, then realistic driving scenarios can be tested, but there is a high possibility of causing accidents
Solution Approach 1:
The patent creates a virtual copy of the real road environment including infrastructure, traffic conditions, and urban scenery. This virtual environment replicates realistic driving scenarios without the physical risks of real-road testing, allowing safe verification of autonomous driving systems while maintaining ecological validity
Solution Approach 2:
The system introduces a virtual environment as an intermediary between real-road testing and conventional simulation. This intermediate testing space uses real infrastructure data and urban scenery to bridge the gap between fully simulated and fully real environments, enabling realistic scenario testing without direct exposure to real-world dangers
2Object-affected harmful factors
If conventional simulation environments are used, then safety is improved, but the ability to implement real road conditions and unexpected situations is limited
Solution Approach 1:
The system performs preliminary actions by pre-collecting and processing real infrastructure data, traffic patterns, and urban scenery information before creating the virtual environment. This preparation enables the virtual space to accurately reflect real road conditions and unexpected situations without requiring actual presence in dangerous real-world scenarios
Solution Approach 2:
The virtual environment serves multiple functions simultaneously: it provides a safe testing space, replicates realistic urban driving conditions, incorporates unexpected situations, and maintains ecological validity. This multi-functionality resolves the contradiction between safety and environmental realism by making the virtual environment versatile enough to handle both concerns
3Object-affected harmful factors
If a virtual environment is created without real infrastructure data, then safety is improved, but the ability to verify performance in realistic scenarios is reduced
Solution Approach 1:
The system creates accurate copies of real infrastructure elements including signal controllers, pedestrian detectors, CCTV systems, and urban scenery within the virtual environment. These copies maintain the functional and visual characteristics of real infrastructure, enabling precise verification of autonomous driving performance in realistic scenarios while keeping testers safe in virtual space
Data Source
AI summary
An autonomous driving verification system through real-virtual information convergence includes a vehicle driving unit that is composed of a plurality of devices that perform steering, driving, deceleration, and braking functions; a simulation unit that generates virtual information including a real city road environment, and an autonomous driving unit that verifies autonomous driving by constructing a virtual environment in which real surrounding environment information acquired from a sensor and virtual information of the simulation unit are converged, and controls the vehicle driving unit to be actually driven within the virtual environment to verify autonomous driving, in which the virtual information of the simulation unit may include signal display information received from infrastructure including at least one of a signal controller, an unexpected situation detector, a pedestrian detector, and CCTV within an intersection installed on a city street.