Accelerating Autonomous Vehicle Development with Photorealistic, Virtual AI Training and Testing Simulation

Project Information

aiSim

Grant agreement ID: 856138

DOI

10.3030/856138

Project closed

EC signature date 15 March 2019

Start date 1 February 2019

End date 30 April 2019

Funded under

• INDUSTRIAL LEADERSHIP - Innovation In SMEs

Total cost

€ 71 429,00

EU contribution

€ 50 000,00

Coordinated by

AIMOTIVE INFORMATIKAI KFT
Hungary

Periodic Reporting for period 1 - aiSim (Accelerating Autonomous Vehicle Development with Photorealistic, Virtual AI Training and Testing Simulation)

Reporting period: 2019-02-01 to 2019-04-30

Summary of the context and overall objectives of the project

Level 5 autonomous driving (AD), i.e. completely self-driving cars, are now the foreseeable future of mobility. There are numerous ongoing developments globally: every significant automaker is pursuing the technology either in-house or in partnerships with specialist companies. Emerging “mobility providers”, such as Uber and Lyft aim to disrupt the entire transportation industry with driverless Mobility-as-a-Service business models. Tech giants are also seeking opportunities to enter the sector, with Alphabet’s Waymo in the forefront of developments. This resulted in significant advances in all areas of autonomous driving technologies, bringing them closer to market deployment.
However, the great challenge is to make sure that these technologies work safely and properly. Testing and validation of autonomous driving technology is slow and costly. Considering that the full-scale testing of an autonomous vehicle may require billions of kilometers of testing until its reliability is demonstrated, this seems an impossible challenge with real road testing. Furthermore, real road testing is not only time consuming and expensive, but is actually quite inefficient as well: it is not possible to create situations that characteristically lead to accidents without hazarding other road users; or to reproduce the same situations later to test the improvements made to the software.

Designed to accelerate autonomous vehicle development, aiSim is a simulator for self-driving technologies. Its ability to recreate real-world situations and create unique scenarios ensures the safe development of autonomous vehicle technology. Virtual testing guarantees that the final product can adapt to different environments. Scenarios based on situations which are common overall but rarely experienced by single drivers allow engineers to evaluate new solutions before real-world road tests. Compared to real-world testing, simulation is reproducible, easily parameterized, is less resource intensive, and it is much easier to create interesting and meaningful scenarios.

aiSim was originally developed as an in-house support tool for the development of our driver assistance and self-driving solutions, and our overall objective in the present project was successfully achieved by validating the market opportunity of commercialising our technology as a standalone product suite.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

We prepared B2B interviews with target customers of aiSim, to better specify user needs. This information was compounded by secondary research based on sectorial analyses and reports, in order to acquire a comprehensive picture of current and future user requirements.
The future evolution of standards, regulations and policies concerning autonomous vehicles will greatly impact the market demand and the specific requirements for simulation solutions. Therefore, we investigated the current regulatory environment and potential directions of regulatory change; in order to be able to derive requirements for technological and business development. Finally, we prepared the plan for the next stage of development and for the commercialisation of the technology based on the results of the B2B interviews.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

In the next decades, autonomous vehicles will transform not only the automotive industry itself, but will create a whole new “Passenger Economy” with new products and services based on the use of fully autonomous, pilotless vehicles. Intel predicts that the size of this market will reach $800 billion by 2035; and $7 trillion by 2050. New developments will all have to be rigorously tested before authorised for in-traffic use. Therefore we foresee demand for cost-efficient simulated testing in the entire automotive ecosystem: OEMs and their suppliers, in particular sensor providers; companies providing new mobility services; as well as regulators and certification bodies.

Despite being a very young company, AImotive is working together with some of the largest automakers (OEMs), their suppliers (Tier 1 / Tier 2 companies) and technology providers (in particular sensor providers). Being familiar with the latest developments and requirements in all these domains enables AImotive to be a frontrunner in AV simulation, giving a competitive advantage over pure play simulator companies. This competitive advantage will not only be sustained, but significantly increased by developing our aiSim technology into a product with a highly modular architecture connected by industry-standard interfaces, making it easy to integrate with existing / third party content, infrastructures, and development pipelines. This is also in line with our conviction that the massive challenges of autonomous driving can only be tackled by a healthy dose of industry-level cooperation, rather than pure competition.

Company logo