Engineering news
Designed to enable autonomous journeys with no reduction in speed, the ‘dynamic risk management system’ is in development at two Fraunhofer Institutes in Germany and the University of York.
With today’s state-of-the-art technology, building self-driving cars that are safer than human drivers would result in a loss of speed and comfort and further decrease the acceptance of autonomous mobility, a Fraunhofer announcement said, citing studies by the US Insurance Institute for Highway Safety. Pilot studies by German carmakers have also confirmed that passengers perceive autonomous vehicles as “mostly slow and hesitant”, the announcement added.
Ensuring safety without limiting speed and comfort is therefore key to acceptance – and adoption – of autonomous vehicles, said the researchers from the Lopaas project (Layers of Protection Architecture for Autonomous Systems).
Aimed at providing vehicles with a better understanding of driving hazards, the team’s new system uses AI capabilities to analyse and account for factors such as the driving behaviour of other road users. The project partners are developing safety concepts for two major application areas – ‘robotaxis’ with one or more passengers, and private cars capable of switching between human drivers and autonomous operation.
Instead of assuming the worst-case scenario in highway situations, the project’s digital safety engineer is designed to enable a smarter and more flexible approach to driving.
“Current approaches assume worst-case scenarios to ensure optimal safety. Among other things, they are based on calculations of physical laws governing how objects move,” said project manager Dr Rasmus Adler.
“However, this leads to reduced speed of the vehicle. It is also difficult to correctly assess multiple risks that can occur simultaneously, such as a pedestrian suddenly appearing on the left of the vehicle and a cyclist on the right side of the vehicle.
“The aim is to implement an understanding of risk in vehicles that does not calculate the worst case and thus does not overestimate all risks.”
Adapted to the traffic situation, the digital safety engineer reacts individually and influences driving behaviour and driving experience. This enables ‘anticipatory driving’, the researchers said, maintaining the required distance to other vehicles and preventing hard braking.
The new methodology is already being applied in a project with Hitachi, focused on safe and efficient collaboration between autonomous mobile robots and human workers in industrial warehouses.
“In simple environments like warehouses, our approach to dynamic risk management works very well. Hitachi plans to equip its driverless forklifts with this,” said Dr Adler.
“We will be optimising our methodology for complex traffic situations with robotaxis and autopilots until the project ends in June 2024. For this purpose, we are also using AI and data-driven models, which are essential for environment recognition and object classification.”
Want the best engineering stories delivered straight to your inbox? The Professional Engineering newsletter gives you vital updates on the most cutting-edge engineering and exciting new job opportunities. To sign up, click here.
Content published by Professional Engineering does not necessarily represent the views of the Institution of Mechanical Engineers.