Navigating self-driving vehicles on construction sites
Technology that enables automated vehicles to reliably detect traffic signs is being developed by Fraunhofer researchers.
Construction sites are particularly challenging for automated vehicles. Accidents occur more frequently due to the fact that driving lanes are generally narrow, traffic jams develop and drivers react under stress.
As well as this, automated vehicle systems are unable to cope with complex situations where old and new road markings overlap, while traffic cones can be difficult to detect by the sensors.
“Our technology enables a system to read signs of this kind with a high degree of accuracy,” said Stefan Eickeler, who is responsible for the subject of object recognition at the Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS in Sankt Augustin, Germany.
“With deep learning — a key technology for the future of the automotive industry — we teach the software to recognise the classic patterns more quickly and efficiently.”
Through the interplay between navigation equipment and onboard computers, it will be possible in the future for differently designated highway exits on construction sites to be correctly identified, for the distances to other vehicles to be kept optimally and for the speed to be adjusted in a timely manner. Automated vehicles will then react independently.
An automotive camera is used, which currently delivers 20 to 25 frames per second. During the trip, these pictures are analysed and information about signs, lane information and LED traffic signs is identified and processed. A future vision is that this camera will be able to function as a primary interface, making a large number of sensors redundant.
Fraunhofer will present its technology at CeBIT in Hannover from 20–24 March 2017. A virtual tour will be used to present several projects in the area of big data and machine learning, including the topics ‘Automated driving on construction sites’, ‘Digital assistants and real-time recommendation systems’ and ‘Knowledge graphs for data-driven business models’.
Reducing hazards during mining haul truck maintenance
Haul trucks and dumpers are among the equipment that is most frequently associated with accidents...
Immersive VR training to keep forestry workers safe
A newly developed immersive VR training tool could enable forestry workers to be trained in a...
Do cobots pose psychosocial risks to workers?
Collaborative robots, also known as cobots, have been increasingly permeating Australian...
