Digital Twins
The concept of digital twins is being widely adopted throughout industry. Digital twins allow complex systems to be modelled, tested and refined in secure, interactive and immersive environments.
Scroll to explore
Adopting a digital twin methodology is essential for companies developing, manufacturing and operating autonomous vehicles (AV) and advanced driver assistance systems (ADAS). In particular, an AV digital twin ensures the safe, efficient and cost-effective deployment of each solution, while providing the vital data required for regulatory compliance.
Repeatable, deterministic safety modelling
An AVSandbox digital twin gives you the power to run simulated AV and ADAS experiments repeatedly under real-world conditions, while testing subtle refinements to each and every test parameter.
This might, for example, involve fluctuating lighting conditions, with light reflected intermittently from road surfaces, or changes to the colour of clothing worn by pedestrians.
In each case, the robust deterministic modelling possible with AVSandbox allows the effects of adjusting individual parameters to be recorded, secure in the knowledge that no other inconsistencies have been introduced, which might influence outcomes. Digital twin modelling can be carried out in conjunction with physical vehicle testing in real-world road environments. Results can then be compared, allowing simulated test results to be validated for accuracy and reliability.
Real-world precision
AVSandbox is built on the rFpro simulation platform. Unlike other products available, which are developed from gaming engines, rFpro uses an innovative simulation engine developed specifically for automotive and motorsport applications.
This is crucial for creating a truly immersive virtual replica of a real-world environment, which is geographically accurate to within a few millimetres.
The virtual replica is also functionally accurate with, for example, defects in road surfaces, actual road signs and markings, or the scale and orientation of surrounding structures being faithfully reproduced at high resolutions and fast frame rates. We then augment the stability and flexibility of rFpro with our custom developed sensor models and features that include edge-case simulatin, to create a powerful AV simulation tool that allows you to bring autonomous vehicles to market efficiently, safely and at optimum cost.
Proving your safety model
Operational safety is a fundamental requirement of every AV programme. No AV can be approved for use without a fully documented safety case, based on rigorous simulation, testing and proving of the vehicle under all operating conditions.
This requires multiple tests, based on a solid deterministic model and a simulation platform with exceptional fidelity to create a robust and dynamic simulation environment. AVSandbox is the only simulation platform capable of providing this combination of features.
Proving that an autonomous vehicle is safe, however, also requires a level of detail that only AVSandbox can deliver. Based on the proven rFpro platform, with its mm-accurate real-world mapping, and with ground truth, and a choice of camera, LIDAR and radar sensors, dynamic vehicle models and advanced weather and lighting options, AVSandbox offers the potential to create unlimited test scenarios with an extraordinary depth of data analysis.
Building your AV safety strategy
We have over 25 years of experience in developing and using simulation systems, and work with a wide range of automotive OEMs, F1 and NASCAR teams and end users in the commercial sectors.
We have the knowledge, skills and resources to help you build a robust safety strategy – a strategy that reflects the exact technical and commercial needs of your organisation, covering:
- Definition of safety criteria
- Safety measurement parameters
- Designing for safe AV deployment
- The perception of safety for AV operators and users
- Regulatory compliance, both current and planned
Discover more
The AVSandbox Knowledge Hub
Discover more about what makes AVSandbox unique. Explore our AVSandbox knowledge hub and find out about the issues, challenges and exciting developments that are behind the growth of the market for autonomous vehicles and advanced driver assistance systems.
Ultra photorealism in AVSandbox
Thanks to the hard work of rFpro, ultrarealistic light rendering is now available in the AVSandbox toolkit. This is ...
Tackling High Development Costs: How AVSandbox Can Accelerate Your Autonomous Vehicle Deployment
Reducing costs of autonomous vehicle development without compromising AV Safety The development and successful deployment of autonomous vehicles is ...
Determinist Traffic Simulation
Introduction In my previous blog deterministic scenario simulation, I detailed why we define our simulator deterministic and what is ...