Stories
Slash Boxes
Comments

SoylentNews is people

Submission Preview

Link to Story

A Sense of Hearing Could Make Cars Safer and More Reliable

Accepted submission by exec at 2017-05-01 08:51:38
News

Story automatically generated by StoryBot Version 0.2.2 rel Testing.
Storybot ('Arthur T Knackerbracket') has been converted to Python3

Note: This is the complete story and will need further editing. It may also be covered
by Copyright and thus should be acknowledged and quoted rather than printed in its entirety.

FeedSource: [MITTech]

Time: 2017-05-01 04:04:28 UTC

Original URL: https://www.technologyreview.com/s/604272/a-sense-of-hearing-could-make-cars-safer-and-more-reliable/ [technologyreview.com] using ISO-8859-1 encoding.

Title: A Sense of Hearing Could Make Cars Safer and More Reliable

--- --- --- --- --- --- --- Entire Story Below --- --- --- --- --- --- ---

A Sense of Hearing Could Make Cars Safer and More Reliable

Arthur T Knackerbracket has found the following story [technologyreview.com]:

Most car owners know what it’s like to hear a new clink or grinding noise coming from the engine and wonder how costly the fix will be.

Startup OtoSense [otosense.com] is working with major automakers on software that could give cars their own sense of hearing to diagnose themselves before any problem gets too expensive. The technology could also help human-driven and automated vehicles stay safe, for example by listening for emergency sirens or sounds indicating road surface quality.

OtoSense has developed machine-learning software that can be trained to identify specific noises, including subtle changes in an engine or a vehicle’s brakes. French automaker PSA Group, owner of brands including Citroen and Peugeot, is testing a version of the software trained using thousands of sounds from its different vehicle models.

Under a project dubbed AudioHound, OtoSense has developed a prototype tablet app that a technician or even car owner could use to record audio for automated diagnosis, says Guillaume Catusseau, who works on vehicle noise in PSA’s R&D department.

Tests have shown that the system can identify unwanted noises from the engine, HVAC system, wheels, and other components. It makes the correct diagnosis 95 percent of the time. Catusseau says PSA is now considering how what he dubs a “bionic ear” could be deployed to speed up repairs and make customers happier. “Buzz, squeak, or rattle is a great concern for car owners,” he says. “The customer will perceive the vehicle as being of low quality, [and] this can affect repurchase intent.”

Sebastian Christian, CEO of OtoSense, says the software could be built into vehicles so they can automatically flag potential problems that electronic sensors can’t. Leading U.S. automakers are also testing OtoSense’s technology to see how a sense of hearing can help vehicles understand their environment. (Christian declines to identify them publicly, citing nondisclosure agreements.)

One idea the startup has tested involves adding accelerometers to a vehicle’s windshield to effectively turn it into a giant microphone. Christian says that the physical properties of windshields make this design good at detecting sirens and the direction they come from.

That could help a self-driving vehicle stay safe, and allow a human-driven car to inform its driver where to look out for an emergency vehicle. (Google previously disclosed [googleusercontent.com] that microphones that detect sirens were part of the bundle of sensors on its self-driving vehicles, which are now being developed by a separate company, Waymo.)

Audio sensors could also let a vehicle understand the nature of the road surface, for example how icy or snowy it is, says Christian. His company works with chip maker Analog Devices to embed the software needed to understand sound into low-cost processors.

Automakers have made sensors such as cameras and radar commonplace in high-end vehicles to support cruise control and safety features. Rajesh Rajamani [umn.edu], a professor at the University of Minnesota who works on novel applications for sensors, says the low cost of audio hardware suggests the technology could make it to market quickly if the current R&D proves it to be useful.

“You can spread a lot of microphones around a car without it becoming very expensive, and compared to vision, sound is much less computationally intensive to analyze,” he says.

Indeed, the potential power of low-cost sound analysis means OtoSense isn’t the only company trying to use it to help machinery stay healthy. For example, Augery, another startup, is using the same basic approach to spot problems in HVAC systems (see “This Gadget Can Tell What’s Wrong with Your Air Conditioner by Listening to It [technologyreview.com]”).

Weren't able to make it to EmTech Digital?
We've got you covered.

                                        Cars [soylentnews.org],

                                        self-driving cars [soylentnews.org],

                                        driverless cars [soylentnews.org],

                                        machine learning [soylentnews.org],

                                        automobiles [soylentnews.org]

                               

                        Tom Simonite [soylentnews.org]

  San Francisco Bureau Chief

My journey to the West Coast started in a small English market town and took in the University of Cambridge, Imperial College London, and five years writing and editing technology news coverage at New Scientist magazine.


                                Please read our commenting guidelines. [soylentnews.org]
                       

                Log in. [soylentnews.org]
       

                Activate your Insider account. [soylentnews.org]
       

Artificial intelligence and robots are transforming how we work and live.

       

With dated-looking cars and top engineers working as safety drivers, the project still looks to be in its early stages.

                        Jamie Condliffe

A documentary about the superhuman Go program created by Google DeepMind shows us what it’s like to be superseded by artificial intelligence.

                        Brenden Lake

Information security used to be able to lock down data. Now we must beware of how algorithms handle our secrets.

                        Jean Yang

                                                        In partnership with

                                                Hewlett Packard Enterprise
                                       

                                                        in partnership with

                                                SAP
                                       

                                                        In partnership with

                                                Google Cloud
                                       


                                                        {! insider.display.menuOptionsLabel !}
                                               


                                                        Six issues of our award winning magazine and daily delivery of The Download, our newsletter of what’s important in technology and innovation.
                                               

What's Included

Bimonthly home delivery and unlimited 24/7 access to MIT Technology Review’s website.


                                        *
                                        {! insider.display.footerLabel !}
                               


                                        See international prices
                               


                                        See U.S. prices
                               


                                        Revert to MIT Enterprise Forum pricing
                               


                                        Revert to standard pricing
                               

-- submitted from IRC


Original Submission