German startup Phantasma Lab is developing a new data set to help self-driving cars predict and understand human behavior more accurately.
Autonomous driving systems have made great progress when it comes to avoiding accidents by using sensors and cameras.
They are however a long way off from being able to accurately anticipate what an unpredictable human being might do.
Such technical limitations has slowed the widespread adoption of autonomous driving in urban and city environments.
One way of sorting this is by imbibing autonomous vehicle systems with human behavior data sets that anticipate unpredictable human behavior, notes Hong Kong Polytechnic University assistant professor Li-Ta Hsu.
And this is exactly what Phantasma Lab intends to do with the help of virtual simulations based on mathematical rules.
Founded in 2018 by software engineer Maria Meier and simulation expert Ramakrishna Nanjundaiah, the German startup is already courting Chinese self-driving car makers to adopt its technology.
Meier believes that better sensors and cameras alone cannot solve the unpredictability problem.
“Sensors will help the car recognize what was there, but not what to do after that,” she contends.
Phantasma isn’t the only company propagating a human behavior data set for self-driving cars.
U.S. start-up Perceptive Automata is also using behavioral science techniques to characterize the way human drivers understand the states of the minds of other humans.
Toyota too has made several inroads in this area with the introduction of its Guardian automated safety system that takes over from drivers if a life-threatening situation occurs on the road.
Experts nevertheless caution that passengers hopping into a driverless car and sleeping soundly until it arrives safely at a given destination is still a long way off.
A further challenge for autonomous carmakers is that each city will have different levels of complexity when it comes to road rules and human behavior.
For instance, streets in Hong Kong will be very different from that of Germany or Japan, and so too the behavior of pedestrians and motorists.
Both Meier and Nanjundaiah agree it that will be a slow road ahead to achieve that capability.
“The time when you can deploy a self-driving car in any part of the world that can drive by itself – that is going to be at least a decade away, ” opines Nanjundaiah.
Image and original content: Bosch/South China Morning Post