There may be no need for a loud exhaust so drivers can hear riders with future technology allowing cars to listen for vital noises as quiet as a nail puncturing a tyre.
Researchers at the Fraunhofer Institute for Digital Media Technology (IDMT) in Oldenburg, Germany, have developed a prototype system capable of recognising important external noises.
The system could very well find its way into many modern cars to alert drivers to all sorts of other road users including motorcycles.
Even more importantly, it may be able to listen for the coming wave of near-silent electric motorcycles.
Listen to the traffic
The European Association of Motorcycle Manufacturers report says much of the current automated technology is untested in the real world and questions its ability to detect motorcycles.
This new auditory technology is designed to fill in the gaps left by lidar sensors that fail to detect small objects such as motorcyclists, cyclists and pedestrians as well as stray livestock and wildlife.
Fraunhofer IDMT Acoustic Event Recognition group chief Danilo Hollosi says no autonomous vehicle has yet been equipped with a system capable of perceiving external noises.
“Such systems would be able to immediately recognise the siren of an approaching emergency vehicle, for example, so that the autonomous vehicle would then know to move over to one side of the highway and form an access lane for the rescue services,” Danilo says.
“There are numerous other scenarios in which an acoustic early-warning system can play a vital role – when an autonomous vehicle is turning into a pedestrian area or residential road where children are playing, for example, or for recognising defects or dangerous situations such as a nail in a tyre.”
“In addition, such systems could also be used to monitor the condition of the vehicle or even double as an emergency telephone equipped with voice-recognition technology.”
The Fraunhofer IDMT acoustic sensor system consists of microphones mounted on the outside of the car to listen to traffic, plus a control unit and software stored inside.
Their project uses artificial intelligence to recognise the acoustic signature of each relevant sound event.
This is done by machine-learning methods that use acoustic libraries compiled by Fraunhofer IDMT.
“Beamforming algorithms” enable the system to dynamically locate and identify moving sound sources.
The technology is expected to reach the market by the middle of the coming decade.