Making Autonomous Vehicles Safe
by bringing the human element into traffic simulation.
30 Billion Kilometers
of testing are required to ensure an autonomous vehicle is safer than a human driver.
This is why testing and development must take place in simulation.
Human Limitations and Errors
are currently the main cause of road accidents.
Interactions with human traffic agents pose a major challenge for the safe operation of autonomous vehicles.
is to enable automotive companies to test in simulation whether their cars safely interact with humans. We achieve this by simulating human cognition and behavior in traffic.
realistic models for simulating the behavior of traffic participants. Based on state-of-the-art neuroscientific and sensorimotor research, our driveBOT ensures high validity of traffic simulations.
Instead of using pre-generated, open-loop trajectories, our driveBOTs realistically interact with the vehicle under test in a closed-loop simulation.
Just like humans, the driveBOTs have typical human limitations such as a limited field of view, reaction times or lack of attention.
Factors such as age and emotions can be adapted for each simulated individual driver to represent the continuum of human behavior in road traffic.
Systematic variations of scenarios automatically generate plausible and life-like traffic flows including (near-) accidents.
combines expertise from neuroscientific and sensorimotor research with technical competence and experience in the automotive industry.