Developing realistic crash scenarios and simulations of future traffic situations involving many autonomous vehicles is at the heart of a recently established project at IMC Krems – University of Applied Sciences (Austria). In the first step of the project, driving scenarios extracted from publicly available databases will be fed into specialized driving simulations. Following this, an optimization process based on state-of-the-art search algorithms will create novel driving scenarios with increased criticality and severity. The project is part of a large EU-funded international research effort aiming at developing safety mechanisms for autonomous cars that reduce accident-related consequences by using advanced manufacturing technologies.
Autonomous cars could significantly reduce the number of traffic accidents. In future that is, as of now they are still involved in crashes, some with fatal consequences. This calls for improving the safety of such vehicles. However, achieving an optimization remains difficult as simulating crash scenarios of mixed traffic situations (i.e. involving cars with different levels of autonomy) is hampered by a scarcity of relevant data. A project at IMC Krems, Austria, is going to change this by harnessing the power of purpose-developed machine learning algorithms that will extract and analyze data from existing car crash databases.
“Autonomous driven cars are still not capable of avoiding accidents in all possible situations”, says Prof. Alessio Gambi, project leader at the Department of Science and Technology at IMC Krems. “And as they react autonomously and hence in other ways than human controlled cars, crashes will look differently to the ones seen so far. But currently we don’t exactly know what they will look like. This lack of knowledge is a hindrance to improve the safety of future mixed traffic situations.”
Dr. Gambi and his team will now contribute to generate a knowledge base for addressing this problem in an international research project funded with 4 Mio. EUR by an EU grant (ID 101069674). Using data from existing sources such as large databases recording car crashes, the team will select a set of reference driving scenarios as a base for the next project step. “It is noteworthy”, explains Dr. Gambi, “that worldwide only one openly accessible database exists that actually records the level of autonomy of cars involved in a crash, California’s DMV autonomous vehicle collision report database. That is a very limited base for simulating future car crash scenarios. Our project will help to widen that base.”
Simulation for Safety
Using the extracted reference scenarios from existing sources (e.g. CARE, GIDAS, STRADA, ZEDATU) the team will feed a state-of-the-art driving simulation (BeamNG.tech). Additionally, the team will develop an online, open simulation platform that follows multi-player paradigms as know from popular video games where remote players interact with each other and with an artificial intelligence. Using this platform, the team will study virtual live interactions between human drivers and (simulated) autonomous vehicles and be able to generate an additional set of traffic scenarios that is not based on previous accidents but real interaction.
With those two sources, specialized search algorithms will now calculate virtual crash scenarios that anticipate possible actions by autonomous vehicles. “We actually develop these algorithms in-house and hence we can easily increase the virtual criticality and severity of the simulated crashes”, explains Prof. Gambi. “This will expose car structures chiefly involved in severe crashes and predict their behavior in such situations.”
At this stage, Dr. Gambi’s project ties in with a larger EU-project called Flexcrash. IMC Krems’ part is the basic work package of Flexcrash. The results from the advanced simulation will provide data for improving the design of future autonomous cars. The final goal is to use hybrid manufacturing technology for applying surface patterns using additive manufacturing onto preformed parts. This will greatly help reducing accident-related fatalities, injuries, pollution and manufacturing costs in future.