Tag Archives: autonomous

Data-gathering cars to hit London streets ahead of autonomous trials

 

Five A1

UK company FiveAI has been given the go-ahead to deploy data-gathering cars on London’s streets to pave the way for a potential driverless car service.

FiveAI plans to spend the next 10 months deploying five cars (with drivers on board) in Bromley and Croydon to collect data on roads, including layout, topology and traffic flow, as well as road user behaviour. The data collected will be processed in line with General Data Protection Regulations (GDPR) and used to feed into the development of FiveAI’s planned services.

FiveAI notes that all its data collection vehicles will be clearly branded and feature an “obvious array” of sensors to ensure transparency.

Towards trials

The shared service the company is working on will target commuters who drive at least part of their journey. FiveAI hopes to run a supervised trial of autonomous vehicles in London in 2019.

FiveAI co-founder Ben Peters says that autonomous vehicles will be much safer than human-driven cars and the data-gathering exercise is a crucial stage towards getting them onto the roads.

He commented: “By supporting London’s transport objectives with a shared driverless car service, FiveAI can play a crucial role in reducing congestion, emissions, incidents and the cost and time of journeys to benefit all Londoners.”

5G and autonomous vehicles

Some say that autonomous cars will only be a reality when we have 5G. Elsewhere, alongside data-gathering initiatives such as FiveAI’s, trials are ongoing to ensure that 5G connectivity will be in place to support driverless cars in the future.

For example, at Millbrook Proving Ground in Bedford, as part of the AutoAir project, led by Airspan Networks, advanced 5G test networks are being deployed to validate connected and autonomous vehicle (CAV) technologies. The researchers are focused on areas such as complicated cell-tower hand-offs and issues related to bandwidth. They are also looking at how the work they are doing on 5G connectivity could be transferred to road and rail systems.

Meanwhile, government mapping agency, Ordnance Survey (OS), is leading an initiative to help better understand the infrastructure needed to support a nationwide network of CAVs. The E-CAVE project will run for four years and will focus on the geospatial aspects of how CAVs exchange safety-related messages between themselves and the supporting environment.

OS is also working with the 5G Innovation Centre and the Met Office on a digital twinning tool to help determine the best places to put radio antennae to underpin a 5G network.

Source: Sarah Wray www.5g.co.uk

Autonomous Robot to help Winegrowers

James Thomas and Kit Franklin with Dionysus

James Thomas and Kit Franklin with Dionysus

Kit and James in the engineering workshop

Kit and James in the engineering workshop

The students test the vehicle with Head of Engineering, Professor Simon Blackmore

The students test the vehicle with Head of Engineering, Professor Simon Blackmore
 

Farmers around the world will be able to improve their irrigation efficiency thanks to an autonomous vineyard robot developed at Harper Adams University.

‘Dionysus’ has been created to use thermal imaging sensors to detect moisture levels in grape vines. This data will then be used to inform farmers as to whether irrigation is required.

Three MEng Agricultural Engineering students at the university in Shropshire have designed and built the project – James Thomas, Kit Franklin and Chris White.

23-year-old James from Devizes in Wiltshire, said: “We had to select an appropriate vehicle to work in vineyards, in this case, a child’s quad bike. We then designed our own control systems to control steering, throttle and braking.

“We have also designed a series of safety features as when Dionysus is in autonomous mode, it is important that the engine cuts out, should a safety issue arise.”

Kit, 23, from South Cerney in Cirencester, added: “These systems are linked to a laptop running SAFAR agricultural robotic software, which takes readings from GPS and also a SICK laser scanner on the front of Dionysus.

“This then guides the vehicle on a pre-set path around the vineyard.”

The team has been working on the project for the past few months, building on skills and knowledge developed during the five years spent studying at Harper Adams.

Tasks were assigned to each team member to share the workload and to get to grips with the complex systems involved.

Kit added: “This project has enabled us to develop our skills in areas such as mechanical engineering, electrical systems engineering and applications engineering.

“As we’ve had to source suitable components from outside suppliers, there has been a lot of contact with professional engineers and industry experts.

“Developing Dionysus has proven to be very good training for our future careers.”

Dionysus is the first of many robotic/autonomous systems which are to be developed by the Harper Adams Engineering Department as part of the National Centre for Precision Farming (NCPF).

The NCPF promotes and evaluates the use of technology as a vital aspect of precision agriculture, building on Harper Adams University’s reputation as an innovator within engineering.

Source: Harper Adams

Autonomous Emergency Braking – AEB

 

Research indicates that 90% of road accidents are caused by drivers who are distracted or inattentive. Car manufacturers are now developing systems which can alert the driver to an imminent crash and can help him use the maximum braking capacity of the car, and which can also apply the brakes independently of the driver if the situation becomes critical. Such intervention is known as Autonomous Emergency Braking (AEB).Real world performance data suggests that such crash avoidance systems can reduce accidents by up to 27% and can lead to a significant reduction in injuries.Euro NCAP believes that AEB systems offer a great safety potential. Their assessment will be included in the rating scheme from 2014 onwards, and tests have now been developed to allow the performance of City and Inter-Urban systems to be compared. Euro NCAP has also repeated its AEB fitment survey, originally conducted in June 2012, to establish which systems are currently in the market and the extent to which they are made available by manufacturers.

Euro NCAP has already recognised the safety benefits of some crash avoidance systems through its Advanced rewards.

Euro NCAP has grouped crash avoidance systems into three main categories: City,Inter-Urban and Pedestrian. Systems may fall into just one category, or may meet the requirements of all three.


City system
City AEB can avoid low-speed impacts in city traffic up to 20km/h.

Inter-Urban system
Inter-Urban systems operate over the speed range 50-80km/h but may also provide useful mitigation at lower speeds, typical of an urban environment.

Pedestrian system
Pedestrian systems can detect pedestrians and other vulnerable road users like cyclists.

 Source: Euro NCAP

 

   

Autonomous truck convoys: The question is when, not if

 

The grand vision of Europe’s freight transport is of sleek convoys of autonomous trucks traveling along thousands of miles of “smart” roads, with the driver’s function reduced to maintenance and security. “I would say we will eventually see part of long-haul transport on roads that are ‘green corridors,’” says Fredrik Callenryd, senior business analyst for truck manufacturer Scania. “So that we would see autonomous trucks traveling in road trains in the foreseeable future, with drivers navigating only when they leave these green corridors, to travel to the depot, for example.”

European Union legislation set to go into effect on Nov. 1 is likely to speed the realization of this vision, according to Gareth Owen, principal analyst at ABI Research. The directive, which takes effect in November 2015, calls for all newly introduced models of trucks 3.5 tons and over to be equipped with both advanced emergency braking systems (AEBS) and lane departure warning systems (LDWS). AEBS uses sensors to alert the driver to an upcoming obstacle, such as a traffic jam or when his vehicle is coming too close to a vehicle in front of him. If the driver does not react in time, the system automatically triggers a braking response that either prevents a collision or reduces the force of the impact. LDWS alerts the driver when the vehicle begins to drift out of the lane.

The road to driverless trucks Both AEBS and LDWS are integral elements of advanced driver assistance systems (ADAS) that are slowly taking over the truck driver’s decision-making duties, and which — Callenryd, Owen and other trade insiders say — are key building blocks of what ultimately will become the autonomous, or self-driven, commercial vehicle.

Already, autonomous vehicles are in use in open-pit mining and at some airports. Self-driven mining trucks are, for example, able to negotiate roads within mining sites as long as they travel along fixed routes. And driverless transit systems, which travel on rails or guide ways, are in use at some major airports, such as London’s Heathrow and Orly in Paris.

Many long-haul trucks are already using cruise control systems similar to what is standard in passenger planes. According to Callenryd, there are two models of these systems: the basic system, in which the driver sets the speed of the vehicle, and the system maintains it, and the advanced version, in which the vehicle takes into account uphill and downhill sections and adapts to run at the optimum fuel-saving speeds. “These advanced systems have already proven to be more efficient than our best drivers in tests,” Callenryd says. Scania’s new solution is called Eco-roll, and it uses both GPS and topographic maps to calculate whether cruising in neutral down a hill or using engine braking with the fuel supply switched off is best for the vehicle’s kinetic energy. Eco-roll is set to come standard for long-haulage trucks in regions where topographic data is available. (For background on driverless passenger cars, see The autonomous car: The road to driverless driving.) Volvo’s take on AEBS and LDWS Most truck manufacturers already offer a version of AEBS and LDWS. Claes Avedal, traffic safety manager at Volvo Group Trucks Technology, says Volvo has been offering LDWS on its FH and FM models since 2007, and AEBS on the FH since 2012. Volvo’s lane departure warning system uses an optical camera sensor to detect when a vehicle begins to drift out of its lane and audible and visual warnings to alert the driver. However, the technology is not yet foolproof. “Functionality is dependent on visible lane markings,” Avedal says. Fog, rain and darkness are usually no problem. But if there are no lane markings, the system will not work. Snow and ice on the road which cover the lane markings are also problematic. For AEBS, Volvo uses both camera and radar sensors to detect traffic ahead. “Radar is used to detect traffic at longer distances, and the camera is used for object detection at shorter distances ahead of the truck,” Avedal says. “By combining camera and radar technology we can detect more traffic scenarios, like stationary vehicles, and avoid false warnings.“ The initial visual AEBS warning is projected on the windscreen in the driver’s forward field of vision so that the driver will react quickly. In addition, Avedal says, Volvo trucks are equipped with several other ADAS features, such as adaptive cruise control (ACC), which automatically adjusts the vehicle’s speed to maintain a safe distance between it and vehicles and other obstacles in front of it; lane change support (LCS), which helps the driver when changing lanes toward the passenger side; and driver alert support (DAS), which alerts the driver when he is getting drowsy or nodding off. The next step for Volvo is a technology that enables vehicles to communicate and exchange information with other vehicles (V2V) and with the infrastructure (V2I), known as Cooperative Intelligent Transportation Systems, or C-ITS. “One example of this is to provide earlier warnings to the driver of traffic conditions ahead, such as reduced visibility, slippery road, accidents or other obstacles,” Avedal says. In addition to OEMs, manufacturers of ADAS such as Delphi are working to perfect the technology while offering aftermarket products to help fleets meet the new EU regulation. Delphi, for example, offers—among other ADAS products—a radar sensor that detects moving and stationary objects at both mid- and long-range distances. (For more on V2V and V2I, see Ann Arbor and the future of V2V/V2I, part I and Ann Arbor and the future of V2V/V2I, part II.) Not a question of if, but when Avedal, Owen and Callenryd all agree that it is not a question of if, but of when autonomous truck trains become a reality, and all three say that the benefits are potentially very significant. “We believe that a step-by-step introduction of more autonomous functions will improve traffic safety, reduce congestions and fuel consumption,” Avedal says. “If you have a convoy of trucks with just one person in the lead truck and ten driverless vehicles behind it, you have significant cost savings,” Owen says. “First of all, you save on fuel. Trials have shown that these convoys can save up to 15% on fuel, in the same way bicycle racers save energy by riding in a single file, to reduce wind resistance.” There would be savings because there are far fewer drivers to pay. And traffic safety would also improve. “Human beings are lousy drivers,” Callenryd says. “How many people died on European roads last year, 40,000? If we allowed a system to kill 40,000 people a year, then we could probably implement a fully autonomous system today. But we don’t allow machines to be as inefficient as humans.” “Some 90% of accidents are caused by drivers,” Owen says. “That’s a very big target to hit.” Technical and legal obstacles Obviously, many challenges remain to be met, most of them technical. “The quality of real-time traffic information needs to be improved,” Callenryd says. But he adds that there have been “great improvements” in the technology over the past five years, and he expects that process to accelerate. Owen underlines the current high cost of radar sensors that are used to detect traffic and other obstacles. “But I expect a significant drop in the price of radar sensors,” he says. “They will eventually be mass market, not niche.” However, legal obstacles may actually be more difficult to overcome. According to Callenryd, cross-border road traffic in Europe is regulated by the Vienna Convention, agreed in 1968. “In it, it is very clear that drivers should be in control of vehicles,” he says. “There are no legal policies for computer-driven vehicles. We need a new legal framework that resolves such questions as how we judge between state-of-the-art vehicles and ‘dumb’ cars.” The problem, Callenryd says, is one of liability. “If an autonomous car causes an accident, who is responsible? The car industry is not ready to take this responsibility.” Owen agrees. “In case of an accident, the blame will probably shift more to the OEMs.

OEMs will not release [autonomous] vehicles until they’re sure the liability is containable,” he says. He sees the introduction of what he calls semi-autonomous commercial vehicles—in which the driver can take over some functions—by about 2020. “Truck trains may be possible by the year 2025,” he says. “It’s a gradual process.”

Source: Siegfried Mortkowitz Telematics Update

Super highway: A14 to become Britain’s first internet-connected road

Technology on busy road connecting Birmingham and Felixstowe could pave way for self-driving cars

  • Motorway
Sensors along a 50-mile stretch of the A14 will monitor traffic by sending signals to and from mobile phones in vehicles.
 
 
One of the UK’s most congested highways, connecting the busy container port at Felixstowe to Birmingham, is to become Britain’s first internet-connected road in a pilot project that could pave the way for everything from tolls to self-driving cars.

A network of sensors will be placed along a 50-mile stretch of the A14 in a collaboration between BT, the Department for Transport and the Cambridge start-up Neul, creating a smart road which can monitor traffic by sending signals to and from mobile phones in moving vehicles.

The technology, which sends signals over the white spaces between television channels instead of mobile phone networks, could even pave the way for government systems to automatically control car speeds.

The telecoms watchdog Ofcom, which on Wednesday approved the project as part of its new blueprint for how Britain will use spectrum, is already forecasting what high technology traffic systems will look like.

“Sensors in cars and on the roads monitor the build-up of congestions and wirelessly send this information to a central traffic control system, which automatically imposes variable speed limits that smooth the flow of traffic,” Ofcom said. “This system could also communicate directly with cars, directing them along diverted routes to avoid the congestion and even managing their speed.”

Onboard computers could essentially override the driver, imposing maximum speeds on the vehicle by controlling the brakes and the engine. While the concept may sound futuristic, Google is already developing a computer-driven car, which uses cameras, radar, and range finders to detect obstacles and other vehicles. The Google smart car has been extensively tested on public highways and smart roads lined with sensors.

The A14 project will not involve smart cars, but is a first step in building the infrastructure such vehicles will need. It could also lay the ground for charging motorists to use busy roads.

The Highways Agency is proposing a £1.5bn improvement to the A14 which would be paid for by a toll, with lorries paying up to £3 to use the improved route. The BT’s sensor project could help design the toll and the road improvements. The project will initially gather information on car drivers before moving on to collect information on heavy goods vehicles. The information will be sent back to a database to which the Department for Transport will have access.

“Understanding traffic patterns, in different weather conditions at different times of day, will allow changes to traffic regulation,” said Stan Boland, chief executive of Neul. “In the future it might provide data that could be used for road pricing, vehicle tracking, and breakdown.”

Within one or two years, Boland believes the UK will have national, regional and city-wide networks of sensors, connected to simple tracking devices monitoring everything from whether council bins need emptying and which parking spaces are free to the location of missing pets.

While traffic data is already gathered by companies such as the satnav maker TomTom, using mobile phone networks, the A14 project offers a low-cost alternative. Instead of relying on mobile masts, which costs tens of thousands to install, Neul will use small base stations that cost a few pounds and can be fixed to street lamps or, in the case of the A14, the outside of nearby BT exchanges.

The project is one of a series approved by Ofcom to explore white space, which is currently used by cameras and microphones for films, theatres and live events but in many areas lies empty. In Glasgow, where consumer take-up of broadband is among the lowest in the country, Microsoft will be using the spectrum to install free wifi in the city centre. Working with the University of Strathclyde, the software group will install sensors around the city to measure pollution and humidity.

White space is also useful for getting broadband signals into rural areas, because it travels longer distances and through obstacles such as leaves and trees. On the Isle of Wight, an Ofcom-approved trial will get remote homes online.

Google is also taking part as one of a number of companies developing intelligent databases that could eventually allow smartphones and tablets to use white space to connect to the internet instead as an alternative to mobile signals.

The databases will tell devices which bands are empty in their local area, and at what power level the signal can safely operate without interfering with nearby users. Demand for data over wireless devices is forecast to be 80 times higher than it is today by 2030, and Ofcom is bent on increasing the amount of spectrum available to connect machines ranging from computers to parking meter sensors to the internet.

Source: The Guardian

Mercedes S 500 Drives 100 KM Autonomously through interurban and urban route

When it sent its S 500 INTELLIGENT DRIVE research vehicle along a historic route in August 2013, Mercedes-Benz became the first motor manufacturer to demonstrate the feasibility of autonomous driving on both interurban and urban routes. The route in question, covering the 100 kilometres or so from Mannheim to Pforzheim, retraced that taken by motoring pioneer Bertha Benz exactly 125 years ago when she boldly set off on the very first long-distance drive. In the heavy traffic of the 21st century the self-driving S-Class had to deal autonomously with a number of highly complex situations – traffic lights, roundabouts, pedestrians, cyclists and trams. It should be noted that this trailblazing success was not achieved using extremely expensive special technology, but with the aid of near-production-standard technology, very similar to that already found in the new E and S-Class. The project thus marks a milestone along the way that leads from the self-propelled (automobile) to the self-driving (autonomous) vehicle.

In August 1888, Bertha Benz set off on her famous first long-distance automobile journey from Mannheim to Pforzheim. In doing so, the wife of Carl Benz demonstrated the suitability of the Benz patent motor car for everyday use and thus paved the way for the worldwide success of the automobile. Precisely 125 years later, in August 2013, Mercedes-Benz recorded a no less spectacular pioneering achievement following the same route. Developed on the basis of the new Mercedes-Benz S-Class, the S 500 INTELLIGENT DRIVE research vehicle autonomously covered the approximately 100 kilometres between Mannheim and Pforzheim. Yet, unlike Bertha Benz all those years ago, it did not have the road “all to itself”, but had to negotiate dense traffic and complex traffic situations.

“This S-Class spells out where we’re headed with “Intelligent Drive” and what tremendous potential there is in currently available technology,” says Dr. Dieter Zetsche, Chief Executive Officer of Daimler AG and Head of Mercedes-Benz Cars. “Of course, it would have been a lot easier to take the autobahn for the autonomous drive from Mannheim to Pforzheim. But there was a special motivation for us to carry out this autonomous drive along this very route 125 years after Bertha Benz. After all, we wouldn’t be Mercedes-Benz unless we set ourselves challenging goals and then went on to achieve them.”

Autonomous driving with production-based sensors

The Mercedes-Benz S 500 INTELLIGENT DRIVE research vehicle was equipped with production-based sensors for the project. Based on a further development of the sensor technologies already in use in the new S-Class, the developers taught the technology platform to know where it is, what it sees and how to react autonomously. With the aid of its highly automated “Route Pilot”, the vehicle is able to negotiate its own way through dense urban and rural traffic.

“For us, autonomous vehicles are an important step on the way to accident-free driving,” says Zetsche. “They will bring greater comfort and safety for all road users. That’s because autonomous vehicles also react when the driver is inattentive or fails to spot something. On top of that, they relieve the driver of tedious or difficult tasks while at the wheel.”

“With our successful test drives following in the tracks of Bertha Benz, we have demonstrated that highly automated driving is possible without the luxury of specially closed-off sections of road and relatively straightforward traffic situations,” says Professor Thomas Weber, member of the Board of Management of Daimler AG with responsibility for Group Research and Head of Mercedes-Benz Cars Development. “In line with the goal of the project, we have gained important insights into the direction in which we need to further develop our current systems in order to enable autonomous driving not just on motorways, but also in other traffic scenarios. Even we ourselves were quite surprised at just how far we got using our present-day sensor technology. But now we also know how much time and effort is needed to teach the vehicle how to react correctly in a host of traffic situations – because every part of the route was different,” adds Weber. This experience will now be incorporated into the engineering of future vehicle generations to be equipped with such innovative, further-developed functions. The Head of Daimler’s Research and Development stresses: “With the new S-Class, we are the first to drive autonomously during traffic jams. We also want to be the first to bring other autonomous functions in series production vehicles. You can expect that we will reach this goal within this decade.”

Several levels of autonomous driving

The main advantages of autonomous driving are plain to see: it allows motorists to reach their destination quickly, safely and in a more relaxed frame of mind. Above all on routine journeys, in traffic jams, on crowded motorways with speed restrictions and at accident blackspots, an autonomous vehicle is capable of assisting the driver and relieving them of tedious routine tasks. However, the intention is not to deprive the driver of the experience and pleasure of doing the driving for themselves. “Our autonomous systems offer to assist and unburden the driver. Those who want to drive themselves are free to do so, and that won’t change in future either,” stresses Daimler development chief Weber. “It’s clear, however, that autonomous driving will not come overnight, but will be realised in stages. With this drive, we’ve now taken another important step into the future.”

A distinction is made between three levels of autonomous driving. These have been defined by a VDA working group in collaboration with the German Federal Highway Research Institute (BASt): partially, highly and fully automated.

  • With partially automated driving, the driver must constantly monitor the automatic functions and must not pursue any non-driving-related activity.
  • In the case of highly automated driving, the driver need not permanently monitor the system. In this case, non-driving-related activities are conceivable on a limited scale. The system recognises its limitations by itself and passes the driving function back to the driver with sufficient time to spare.
  • With fully automated driving, the system is capable of autonomously coping with every situation; the driver need not monitor the system and can pursue non-driving-related activities. Equally, driverless driving is possible at this level.

Partially automated driving is already available to drivers of new Mercedes-Benz E and S-Class models: the new DISTRONIC PLUS with Steering Assist and Stop&Go Pilot is capable of steering the vehicle mainly autonomously through traffic jams. This system thus forms the core of “Mercedes-Benz Intelligent Drive”, the intelligent networking of all safety and comfort systems on the way to accident-free and, ultimately, autonomous driving.

The now successfully conducted autonomous test drives along the Bertha Benz route allowed the Daimler researchers to gather important information on the challenges that remain to be addressed on the way to highly and fully automated driving and what, for example, still needs to be done to enable a car to navigate safely in highly complex situations involving traffic lights, roundabouts, pedestrians and trams.

Initial road tests using technology platforms based on the E and S-Class

Unnoticed by the public, yet authorised by appropriate official exemptions and certificates from the TÜV (German Technical Inspection Authority), testing of the “Route Pilot” on the Bertha Benz route began in early 2012 with a total of three technology platforms based on the E and S-Class, which are equipped with all available active and passive safety systems.

These test vehicles employed only those sensor technologies that are already today used in similar form in Mercedes-Benz standard-production vehicles. This is because those technologies are already affordable and suitable for everyday use, which facilitates a possible transfer to subsequent standard-production models. However, improvements were made to the number and arrangement of the sensors in order to achieve comprehensive coverage of the vehicle’s surroundings in every direction, and to obtain additional information on the area around the vehicle.

Based on these sensor data and determination of the vehicle’s own position with reference to information from a digital map, an autonomously driving vehicle analyses the available free area for driving and plans its own route. The required algorithms were developed by the Mercedes-Benz research team in collaboration with the Institute for Measuring and Control Technology at the Karlsruhe Institute of Technology (KIT).

The specific technical modifications compared with the standard-production version of a Mercedes-Benz S-Class are as follows:

  • The base width (distance between the eyes) of the stereo camera was increased to allow more-distant objects to be detected not only by the radar, but also by the camera.
  • Two additional long-range radars were installed at the sides of the front bumpers to provide early detection of vehicles coming from the left or right at junctions. A further long-range radar monitors the traffic to the rear.
  • Four short-range radars at the corners of the vehicle provide improved detection of the nearer surroundings and other road users.
  • Traffic lights are monitored by a colour camera behind the windscreen with a 90-degree opening angle.
  • Another camera looks towards the back through the rear window to locate the vehicle with reference to known environment features. These environment features were previously entered on a digital map. By comparing what has just been seen by the camera with what is stored on the map, the vehicle is able to locate its position with significantly greater accuracy than would be possible with GPS alone.

For the trip along the Bertha Benz route, Mercedes-Benz collaborated with KIT and HERE, a division of Nokia specialised in the production of digital maps and location-specific services, to produce a 3D digital map of the route between Mannheim and Pforzheim that was specifically adapted to the requirements of an autonomous vehicle. In addition to the road layout, this map – which must meet special requirements with regard to accuracy – includes information on the number and direction of traffic lanes and traffic signs as well as the positions of traffic lights. Digital maps of this kind are a key prerequisite for autonomous driving. Mercedes-Benz and HERE will therefore continue their collaboration in future with regard to the development of “intelligent” 3D digital maps for autonomous vehicles.

Route Pilot reacts to diverse traffic situations

The Route Pilot in the research vehicle is required to cope with a host of different challenges both on country roads and in urban traffic: roundabouts, obstructions in built-up areas with oncoming traffic, cyclists on the road, turn-off manoeuvres, variously parked vehicles, red traffic lights, “right before left” priority junctions, crossing pedestrians and trams.

The autonomously driving S-Class was monitored during the tests by specially trained safety drivers who, whenever the system made an incorrect decision, were able to intervene immediately and take over control of the vehicle. As real traffic is unpredictable – which means that no driving situation is exactly the same as an earlier one – a record was made each time it became necessary for the safety driver to take over control of the vehicle. This information was then evaluated by the development team, thus making it possible to extend the vehicle’s repertoire of manoeuvres. This advances the development of the technology platform, enabling it to cope with more and more traffic situations.

The test drives along the 100-kilometre-long route deliver important information for further development of the technology and the product. “For example, it became apparent that the recognition of traffic light phases under different lighting conditions and the correct pairing of individual traffic lights with traffic lanes represents a major challenge,” explains Prof. Ralf Herrtwich, head of driver assistance and suspension systems at Daimler Group Research and Advance Development, a role in which he initiated the autonomous driving project. “However, it is not our intention that the vehicle should master every situation on its own. If, for example, the road is blocked by a refuse collection vehicle, we certainly don’t want the vehicle to automatically overtake it, especially as the vision of the vehicle’s sensors is restricted in such a case. In such a situation, the vehicle passes control back to the driver.”

For the company, the success of the autonomous road tests lies above all in having identified those areas on which the development team needs to concentrate in future. “We now know where we can make further improvements and refinements to the vehicle’s repertoire of programmed manoeuvres, i.e. the situation-dependent control commands for steering, engine and brakes, such as how to autonomously negotiate a roundabout.” A further challenge is to correctly locate the vehicle on the road, in order to determine, for example, precisely where a vehicle should stop at a junction while at the same time having a view of cross-traffic.

A particular challenge for autonomous vehicles is the way in which they communicate and interact with other road users. Coming to an agreement with an oncoming vehicle on who should proceed first around an obstruction is something that requires a very great deal of situational analysis. “Where a human driver might boldly move forward into a gap, our autonomous vehicle tends to adopt a more cautious approach,” says Herrtwich. “This sometimes results in comical situations, such as when, having stopped at a zebra crossing, the vehicle gets waved through by the pedestrian – yet our car stoically continues to wait, because we failed to anticipate such politeness when we programmed the system.”

To enable the developers to reconstruct the decisions made by the autonomous research vehicle in individual driving situations, the car makes recordings of all its sensor data. Images from the stereo camera alone generate 300 gigabytes of data every hour. Also in later standard operation, some of these data will continue to be stored. That’s because if, for example, an autonomous vehicle is involved in an accident, this information will make it possible to establish what happened.

Challenges on the path to autonomous driving

Before the goal of highly and fully autonomous driving is achieved, the obstacles to be overcome will not be just of a technical nature. Many of the things that are already technically feasible are still not universally permitted.

For instance, international UN/ECE Regulation R 79 (steering systems) allows only corrective steering functions, but not automatic steering at speeds above 10 km/h. Under the Vienna Road Traffic Convention, which is relevant for EU law, the driver must be in constant control of their vehicle and be capable of intervening at all times. As autonomous vehicles were still out of the question at the time this convention was adopted, clarification is needed with regard to what this means for highly or fully automated vehicles. In some US states such as Nevada, there has already been such clarification, at least as far as the trial operation of autonomous vehicles is concerned. Another prerequisite for the transition from partially to highly automated systems is their acceptance in society. Just as when the automobile was originally invented, it will first of all be necessary to build up confidence in the technical capabilities of the systems. This is borne out by a recent study carried out by the Customer Research Centre at Mercedes-Benz involving around 100 test persons aged between 18 and 60. The initial scepticism of the study participants was almost entirely dispelled following an autonomous drive in the driving simulator. Even among those participants who were negatively disposed to begin with, there was a significant increase in acceptance after the drive in the simulator.

One way of ensuring that map data and route information is always kept up to date is to use “Car-to-X Communication”. This could enable future vehicles to help each other to generate real-time maps, because, theoretically, every car is capable of recording the route it has driven and entering it in a database. Information on a red traffic light could be relayed from a waiting car to other road users. Alternatively, the traffic light itself could send a signal to nearby vehicles. Mercedes-Benz has been working for several years on communication between vehicles and between vehicles and their environment. This year, it is set to become the first manufacturer to bring “Car-to-X functions” onto the market.

PROMETHEUS – pioneering achievement on the way to autonomous driving

Mercedes-Benz’s success on the Bertha Benz route is the latest result of years of research in the field of autonomous driving. An earlier milestone was the Daimler-Benz-initiated research project EUREKA-PROMETHEUS (“Programme for European Traffic with Highest Efficiency and Unprecedented Safety”), which ran from 1986 and whose test vehicles made headlines when, in 1994, in normal traffic, they covered around 1000 kilometres, mainly autonomously, on a multi-lane motorway in the Paris region and then, in 1995, drove from Munich to Copenhagen. Consequently, almost 20 years ago, Mercedes-Benz demonstrated that automated driving on motorways, including lane-changing, overtaking and keeping a safe distance, is technically feasible.

One of the outcomes of the Prometheus project was DISTRONIC adaptive cruise control, which went into production in the S-Class in 1998. Based on DISTRONIC, Mercedes-Benz has developed a succession of assistance systems capable of detecting hazardous situations, warning the driver and, ever more frequently, also automatically intervening. The project also resulted in Speed Limit Assist, which went into series production in 2005. Continuous further advances in environment detection using stereo cameras, also first tested as part of PROMETHEUS, created the foundation for the “6D Vision” stereo camera, which has now been launched in the new E- and S-Class. Patented by Daimler, this technology makes it possible to anticipate the real-time movements of other nearby road users.

At a technical level, Prometheus and the Mercedes-Benz S 500 INTELLIGENT DRIVE are worlds apart. “Progress has been due above all to modern-day hardware and software, which have been the focus of targeted optimisation over the years,” explains Mercedes-Benz development chief Weber. “Technical components in those days were much too big and much too expensive for standard use in automobiles. Also, they were not powerful or reliable enough. The situation today is a quite different one. Our modern systems can be installed in compact control units that, while exceptionally powerful, are still affordable. Because that’s the only way in which the maximum possible number of customers can benefit from autonomous vehicle functions – and that’s our ultimate goal.”

Mercedes-Benz assistance systems with partially automated driving functions in standard-production vehicles

  • DISTRONIC/DISTRONIC PLUS adaptive cruise control (1998/2005) Launched in 1998 and further developed in 2005 with improved radar sensors, adaptive cruise control automatically maintains a safe distance from the vehicle in front. It is capable of autonomous braking and acceleration.
  • PRE-SAFE Brake (2006) Automatically brakes the vehicle if there is a risk of a rear-end collision (autonomous partial/emergency braking).
  • Active Blind Spot Assist (2010) Detects whether there is a vehicle in the driver’s blind spot and, by means of one-sided application of the brakes, can reduce the risk of collision from a change of lane.
  • Active Lane Keeping Assist (2010) Networked with ESP. If the driver unintentionally crosses a continuous or discontinuous lane marking, Active Lane Keeping Assist can brake the wheels on the opposite side, thereby returning the vehicle to the original lane.
  • Active Parking Assist (2010) Uses electromechanical direct steering to navigate the vehicle into a parking space.
  • DISTRONIC Plus with Steering Assist and Stop&Go Pilot (2013) Helps the driver not only to maintain a desired distance from the vehicle in front, but also to stay in the centre of the lane. This makes it possible to autonomously follow vehicles in traffic tailbacks.
  • BAS PLUS Brake Assist with Cross-Traffic Assist (2013) Capable of detecting cross-traffic and pedestrians and boosting the braking power applied by the driver.

Source: Mercedes

60% of cars will be internet-enabled by 2025, says IEEE

The IEEE has released a report saying Internet-enabled vehicles will play an instrumental role in improving the future of commuting. It is estimated that by 2025, 60 percent of the cars on the road will be internet connected, which will promote advanced safety features, upgraded vehicle software protection and the continued adoption of autonomous vehicles.

“With cars being equipped with blue tooth and the ability to interact with mobile devices, we’re already beginning to see car manufacturers implementing connected car technologies,” stated Jeffrey Miller, IEEE member and Associate Professor in the Computer Systems Engineering department at University of Alaska, Anchorage. “The widespread adoption of connected cars will allow consumers to treat their vehicles as just another one of their devices. Hosting mobile operating systems and purchasing data packages from wireless providers will be commonplace in the future.”

21st Century Safety
Internet-connected vehicles will also play a vital role in improving safety and convenience features. As technology supports the communication between people, we will also begin seeing a shift in how vehicles interact with each other, known as vehicle-to-vehicle communication. “Through vehicle-to-vehicle communication, cars will be able to travel in closer proximity at faster speeds, as well as automatically reroute to avoid hazardous weather conditions or congested roadways,” said Christoph Stiller, IEEE member and professor at Karlsruhe Institute of Technology, Germany. “Because of these features, human error will nearly be removed from driving, therefore making it a safer and more enjoyable experience.”

Hacked on the Highway?
As vehicles become more accepting of wireless communication, connected cars will become increasingly vulnerable to software hacks. “Hackers could potentially have the ability to affect audio features, disable the vehicle’s ignition, override braking systems and infect the software with Trojans and viruses,” said Kevin Curran, IEEE Senior Member and professor of Computing and Engineering at the University of Ulster, U.K. “In order to combat this, manufacturers need to begin setting firewalls in place to restrict access from integrated systems. There is a strong presence of interconnectivity between vehicle networks, so a breach in one network may cause havoc in another.”

Autonomous Vehicles and the Internet: A More Productive Commute
The increased dependence on connected devices and the rise of the internet-enabled vehicle signifies that consumers will increase their trust and reliance on automated systems. This trend will promote increased adoption of autonomous vehicles, further justifying IEEE’s prediction made last year that 75 percent of the cars on the road would be autonomous by 2040.

“Trust in automated technology systems is the key to widespread adoption of autonomous vehicles,” said Alberto Broggi, IEEE Senior Member and professor of computer engineering at the University of Parma in Italy. “It’s amazing to think that just six years ago, smartphones did not exist and now people cannot live without them. This dependence that consumers have acquired will be the catalyst for autonomous vehicles, leading people to trust in automated technology. Within the next five years, lanes will be dedicated for the specific use of autonomous vehicles.”

In the future, Broggi believes that driving will be more of a novelty where, “people will actually pay to drive cars manually similar to go carts.”

Source: IEEE/Telematics News

 

Nissan announces plans for autonomous driving

Nissan Motor has announced that the company will be ready with multiple, commercially-viable Autonomous Drive vehicles by 2020. Nissan announced that the company’s engineers have been carrying out intensive research on the technology for years, alongside teams from the world’s top universities, including MIT, Stanford, Oxford, Carnegie Mellon and the University of Tokyo.

Work is already underway in Japan to build a dedicated autonomous driving proving ground, to be completed by the end of fiscal year 2014. Featuring real townscapes – masonry not mock-ups – it will be used to push vehicle testing beyond the limits possible on public roads to ensure the technology is safe.
Nissan’s autonomous driving will be achieved at realistic prices for consumers. The goal is availability across the model range within two vehicle generations.

“Nissan Motor Company’s willingness to question conventional thinking and to drive progress – is what sets us apart,” said CEO Carlos Ghosn. “In 2007 I pledged that – by 2010 – Nissan would mass market a zero-emission vehicle. Today, the Nissan LEAF is the best-selling electric vehicle in history. Now I am committing to be ready to introduce a new ground-breaking technology, Autonomous Drive, by 2020, and we are on track to realize it.”

Nissan is demonstrating the breadth of the capability of its autonomous drive technology for the first time at Nissan 360, a huge test drive and stakeholder interaction event being held in Southern California. Laser scanners, Around View Monitor cameras, as well as advanced artificial intelligence and actuators, have been installed in Nissan LEAFs to enable them to negotiate complex real-world driving scenarios.

Nissan’s autonomous driving technology is an extension of its Safety Shield, which monitors a 360-degree view around a vehicle for risks, offers warnings to the driver and takes action if necessary. It is based on the philosophy that everything required should be on board the vehicle, rather than relying on detailed external data. The technology being demonstrated at Nissan 360 means the car could drive autonomously on a highway – sticking to or changing lanes and avoiding collisions – without a map. It can also be integrated with a standard in-car navigation system so the vehicle knows which turns to take to reach its destination.

Source: Nissan/Telematics News