Articles

« go back

Intelligent assistants for helping people interact with autonomous cars

While Google works on a prototype driverless car with no user operable pedals or brakes, companies that currently sell cars will be less keen to present such complete ceding of control to machines by its market as a positive view of the future.

The step-by-step process of automation of driving tasks is underway, but  manufacturers may continue to flatter the driver to perceive herself as captain of her own ship. But, increasingly, she may be 'assisted' by technology in doing that.

In the meantime, the concept of the 'intelligent assistant' could be part of the next stage towards automation, perhaps in helping integrate personal devices into the car in such a way as to prevent driver distraction.

An “intelligent assistant” is a concept predicted to become a feature of the higher-end smartphone market. Car makers (such as Jaguar) are also beginning to preview such technologies that act as a helpful interface between driver and smart technologies.

Apple iOS and Google Android devices can, for instance, remind drivers when they need to set off for an appointment ahead of time, taking into account traffic conditions. Indeed, last October, Apple acquired Cue, personal assistant app, which could mean more advances in such technologies to be built-in to iOS devices.

Both Apple and Google face a challenges in integrating their mobile devices into the attention critical environment of the car. 'Intelligent assistants' may help. Whether the term becomes more than a concept depends, perhaps more on wider acceptance rather than driver acceptance, but it is not a concept that will have escaped the notice of car brands.

Ideally, the experience of using an 'intelligent assistant' would be a seamless one, that would assist the introduction of further new technologies as they come along.

 

China’s Baidu follows Google with self-driving car including an “intelligent assistant” to aid the driver

As reported by the Financial Times, Baidu, the Chinese search engine has copied Google in experimenting with its own version of a self-driving car.

However, unlike Google’s car prototype that dispensed with steering wheels and pedals, it’s car will merely be “highly autonomous” rather than driverless, and include an “intelligent assistant” to aid the driver.

Baidu said its project consisted of one of its street-view filming cars fitted with an array of sensors and cameras, which is being tested around the company’s campus in Beijing. A prototype is expected later this year or in 2015.

Baidu started the car project earlier this year as one of several research and development initiatives designed to utilise its mapping service and gather data about Chinese road travel.

Kai Yu, Baidu’s deputy director of research, described the technology as more akin to an assistant that would use information from Baidu’s databases of locations and road conditions to plan routes.

“This is an intelligent assistant collecting data from road situations and then operating locally,” Mr Yu told The Next Web, a technology blog.

“We don’t call this a driverless car. I think a car should be helping people, not replacing people, so we call this a highly autonomous car,” he said.

“People should still enjoy the experience of driving,” Baidu said.

 

Jaguar Land Rover previews in technology in the works

Published alongside an announcement of record half yearly sales results, JLR  previewed some of its new technology concepts designed to avoid driver distraction.

Jaguar Virtual Windscreen

The 'Jaguar Virtual Windscreen' concept uses the entire windscreen as a display, in the hope that a driver's eyes need never leave the road as hazard, speed and navigation indications could all be projected onto the screen.

Jaguar Land Rover is also developing a gesture control system to help reduce distraction by limiting the need to look at or feel for buttons and switches. 

In contrast the the presumed used of voice control as a hands-free interface suited to the car, Jaguar Land Rover has previewed its gesture control research, branded E-Field Sensing. Whereas a smartphone detects the proximity of a user's finger from as far as 5mm away, Jaguar Land Rover’s system increases the range of the sensing field to around 15cm which means the system can be used to accurately track a user's hand gestures.

Jaguar Land Rover's research team is also looking at technology that could replace rear view and external mirrors with cameras and virtual displays. Using two-dimensional imaging to replace mirrors is limited by the fact that single plane images on a screen do not allow the driver to accurately judge the distance or speed of other road users, but JLR says it has developed an innovative 3D instrument cluster, which uses head- and eye-tracking technology to create a natural-looking, specs-free 3D image on the instrument panel.

Cameras positioned in the instrument binnacle or steering column area track the position of the user's head and eyes. Software then adjusts the image projection in order to create a 3D effect by feeding each eye two slightly differing angles of a particular image. This creates the perception of depth which allows the driver to judge distance.

 

Other companies developing HUDs for cars

Continental AG, the German component supplier, is reported to have lined up a production contract to supply its new HUD technology for an unnamed customer in 2017.

Its HMI division will market its technology as a safety device. HMI stands for human machine interface.

Nippon Seiki, Harman, Visteon, Bosch, Panasonic, Delphi and others are developing head-up displays, and Denso has said it will market its own version of augmented reality.

A recent report by market research group Research and Markets on the "Global Automotive Heads-up Display Market 2014-2018" predicts the global automotive heads-up display market will grow at a rate of 44% over the next four years.

Heads-up display systems have mainly been adopted in sports cars and limited models of premium cars. Implementation of heads-up solutions in vehicles remains very expensive, according to Research and Markets, meaning automobile manufacturers are likely to only implement this solution in high-end models.

Key Vendors include:

  • Continental AG
  • Delphi Automotive plc
  • Denso Corp.
  • Nippon Seiki Co. Ltd

Other prominent vendors are:

  • Aisin Group
  • Robert Bosch GmbH
  • Hella KGaA Hueck & Co.
  • Iteris Inc.
  • Johnson Controls Inc.
  • Magna Electronics Inc.
  • MicroVision Inc.
  • Pioneer Corp.
  • Valeo SA.

 

 

JLR’s previews it Self-Learning Car concept

Jaguar Land Rover also previewed what it described as “a truly intelligent self-learning vehicle” that is designed to personalise the response of the car to the driver’s style and also help prevent accidents by reducing driver distraction.

A 'Smart Assistant' takes over basic driving functions to allow the driver to concentrate on driving, such as adjusting mirrors, temperature or seat functions to allow the driver to concentrate on the road ahead.

The assistant can also change preferences based on variables such as the weather and the driver’s schedule for the day and taking account of individual driving style and then apply these to Auto Adaptive Cruise Control (AACC) when it is engaged.

Jaguar Land Rover stated in a press release that most self-learning car research has focused on traffic or navigation prediction. It wants to take this a significant step further to enhance driving pleasure.

The intelligent car will recognise the driver by the smartphone or other device in their pocket and by the time the driver has opened the car door, the mirrors, steering wheel and seat settings will all be set to the individual's preferences. The cabin will be pre-set to the desired temperature - and be intelligent enough to change it if it is snowing or raining.

Through the 'Smart Assistant', the car will also review your schedule for the day and intelligently pre-set the navigation depending on traffic conditions to avoid congestion. It will also predict your next destination based on your schedule.

The self-learning car will also know if you are going to the gym, and will have learnt that you prefer a certain temperature on the way there to warm-up, and a different temperature to cool down on your way home. If you always use the massage function at a particular time or location on a journey, the car will be able to predict this as well.

The car will also recognise every passenger and offer each their own preferred infotainment options - and the 'Smart Assistant' will review your calendar and remind you before you leave the house - by sending a note to your smartphone - to collect your children's sport kit as it knows you are going to their sports day.

The concept car could also predict when a call is normally made on a journey and will offer to make the call on behalf of the driver. It can also predict if the driver is likely to be late for an appointment, the car will offer to email or call ahead with minimal or no interaction from the driver.

The self-learning car will also be able to learn an individual's driving style in a range of traffic conditions and on different types of road.  When the driver activates Auto Adaptive Cruise Control (AACC) the car will be able to apply these learned distance settings and acceleration profiles to automated cruise control.

Some of the features included in the Self-Learning Car concept:

  • Vehicle Personalisation - climate, seat, steering wheel, mirrors and infotainment settings.
  • Destination Prediction - automatic destination entry to navigation system based on historical usage.
  • Fuel Assist - suggests fuel stations which have the driver's preferred brand and location, based on historical usage. The car will let you know if you have enough fuel before long journeys the day before you travel.
  • Predictive Phone Call - predicts who you are likely to call in a certain situation.
  • Passenger Awareness - will activate passenger preferred infotainment settings and personal climate zones.
  • Intelligent Notifications - based on traffic situation, the car can alert people that you will be late or provide relevant contextual updates such as flight delays on your drive to the airport.
  • Auto Adaptive Cruise Control (AACC) - when AACC is activated, the car applies the distance setting and acceleration profile it has learned when the driver is driving the vehicle.  
Comments
No comments yet. Be the first.

Quick Links

Recent articles

Civi Maos Augmented Reality

I have been approached by Civil maps on their capabiilites for Augmented reality in the...

Transport Data Initiative

Calling all transport partitioners, managers and Directors in Local Authorities The...

Simply Connect - Seeders funding Campaign

Simoly connect is a projec tthat is aiming to provide affordable, on-demand, door-to-door...

Open testing event for Driverless and Autonomous vehicle technology

Free test track time for Connected and Autonomous vehicles

Lords Science and Technology Committee: New inquiry - Autonomous Vehicles

The House of Lords Science and Technology Committee has  launched an inquiry into...

Connected and Autonomous Vehicles Competition offers £35million

New £35 million connected and autonomous vehicles competition open now

The great road safety divide: Volvo vs. Clarkson

Volvo has famously said that, by 2020, no one should be killed or seriously injured in one of...

Digitally enabled mobility services to lead to a convergence of public and private transportation

Frost & Sullivan’s annual blockbuster Intelligent Mobility event , this year featuring...