Volvo Cars calls for US national framework for regulation and testing of autonomous driving
Sandia team boosts hydrogen production activity by molybdenum disulfide four-fold; low-cost catalyst for solar-driven water splitting

$90M UR:BAN research initiative presenting results on ADAS and traffic management for cities; intelligent vehicles

In Düsseldorf, the 31 partners—automobile and electronics manufacturers, suppliers, communication technology and software companies, research institutes and cities—involved in the UR:BAN research initiative (Urban Space: user-friendly assistance systems and network management) presented the results of four years of work in a two-day event.

UR:BAN’s goal is to develop advanced driver assistance and traffic management systems for cities, with a focus on the human element in all aspects of mobility and traffic. The project pursued its objectives in three main thematic target areas: Cognitive Assistance; Networked Traffic System; and Human Factors in Traffic.

  • Cognitive Assistance (€40 million). The focus of this project is improvement of safety in urban traffic in complex situations such as intersections with pedestrian movements and bicycle traffic, narrow or obstructed streets, conflicts with opposing traffic and lane changing. Novel technologies now support panoramic sensing capabilities, which allow an evaluation of space available for possible lateral avoidance (swerving) maneuvers. Thus, collisions can be avoided not only by automatic braking, but also by swerving as required. All these challenges are supported by studies of legal issues and effectiveness evaluation.

  • Networked Traffic System (€23 million). Development of applications for energy and traffic efficient driving in urban areas is the focus of the project. The aim is to find new approaches to solution of a number of scientific and technical issues:

    • Measurement of complex urban situations for information and assistance systems supporting energy and traffic efficient, comfortable and safe mobility
    • Determination of requirements posed by vehicles with alternative power sources and optimization with respect to these special requirements
    • Infrastructure control and networking with innovative vehicle concepts and systems
    • Complex network control with aim of satisfying new demands on mobility in the post-fossil fuel era.
  • Human Factors in Traffic (€17 million). The project focuses specifically on the user of future assistance and information systems. In the case of advanced driver assistance systems for urban areas, the primary emphasis is safety rather than just comfort. By means of an individualized design of the driver-vehicle interaction for different drivers, the aim is to achieve low-stress, efficient, and safe driving in urban traffic. Research institutes and manufacturers cooperate to investigate how humans and machines interact and how to predict human behavior. Novel techniques are developed on the basis of experimental studies.

Completion date for the consortium’s research work is early 2016. The total budget for the research consortium is €80 million ($90 million). Around 50% of this amount is contributed by the German Federal Ministry for Economy and Energy in the framework of the third traffic research program of the German federal government.

UR:BAN participants include: Adam Opel AG; AUDI AG; BMW AG; BMW Forschung und Technik GmbH; Robert Bosch GmbH; German Federal Institute for Road Transportation; Continental Automotive GmbH; Continental Safety Engineering International GmbH; Continental Teves AG & Co. oHG; Daimler AG; German Aerospace Centre e.V.; Fraunhofer Institute for Labor Economy and Organization (IAO); GEVAS Software GmbH; Heusch/Boesefeldt GmbH; University of Applied Sciences Technology and Business of the State of Saarland; ifak Magdeburg e.V.; MAN Truck & Bus AG; PTV Group; Institute of Automotive Engineering at the RWTH University in Aachen; state capital Düsseldorf; city of Kassel; Tech. University of Braunschweig; Tech. University of Chemnitz; Tech. University of Munich; TomTom Development Germany GmbH; TRANSVER GmbH; University of the German Army in Munich; universities at Duisburg-Essen, Kassel and Würzburg; and Volkswagen AG. Numerous additional university and research institutes as well as small and mid-size companies are also participating in the projects as subcontractors.

Volkswagen Group Research. Volkswagen Group Research participated in all three UR:BAN project pillars: Cognitive Assistance, Human Factors in Traffic and Networked Traffic System.

  • In the Cognitive Assistance subject area, Volkswagen Group Research developed innovative assistance systems that assist the driver in urban traffic, inform the driver in a timely way, recommend suitable maneuvers and even intervene in an emergency. These systems operate in an effective and situation-specific way to offer safe longitudinal and transverse guidance that assists the driver in driving in urban traffic that in an anticipatory, safe and relaxed manner.

    For example, the “Lane changing assistant” assists with active interventions in longitudinal and transverse guidance when switching driving lanes in dense traffic on urban approach roads and arterial roads. During a maneuver, the system observes surrounding vehicles with its 360° monitoring system and helps the driver to select an open space in the destination lane and approach it by activating indicators and making steering movements.

    The “Bottleneck assistant”, on the other hand, helps drivers when there are obstacles that are partially or completely blocking the driving lane—such as parked vehicles—leaving just a very narrow gap for passage. An advanced development of the Lane Assist system—which has already been implemented in production cars—uses a 3D sensor system to detect obstacles adjacent to and within the car’s own driving lane. The system checks whether a safe path exists, and it assists by active steering intervention when driving past the obstacle while maintaining a safe distance.

    The “recommended speed based on the surroundings” function assists the driver in choosing a driving speed that is appropriate for a given situation. The active accelerator pedal gives the driver direct tactile feedback on whether the driver should accelerate or brake, e.g. when approaching a traffic light. The “Emergency braking assistant” reduces or even avoids imminent collisions in the urban environment by situation-specific braking and steering interventions.

    Along with relieving the driver’s work and enhancing convenience, the driver assistance functions also make a contribution toward improving traffic safety. The potential for avoiding and reducing accidents is being assessed by the Accident Research department of Group Research.

  • For the Human Factors in Traffic project, Volkswagen Group Research is working on a new type of human-machine interface. This is an intelligent communications channel that will take information, filter and prioritise it and present it to the driver as needed. It thereby contributes significantly toward achieving an anticipatory style of driving, it can make hazardous situations safer and it promotes low-emissions driving.

  • In the Networked Traffic System subproject, Volkswagen Group Research is developing the “Intersection pilot” with the goal of improving traffic efficiency in the vicinity of intersections based on Car-to-X communication. This assistance function informs the driver locally about traffic nodes located ahead. It supports the driver with optimal driving maneuvers and simultaneously enables improved traffic light switching by routing vehicle information.

  • The “Merge and start assistant” uses information from the intelligent traffic infrastructure. For one, it adjusts the vehicle’s speed immediately before entering an intersection to enable driving through on a green traffic light phase without having to stop. For another, it ensures that traffic starts up again quickly when the traffic light switches to green. This enables better utilisation of the short green phase in the interest of all traffic participants.

    The “Emergency vehicle assistant” informs all traffic participants directly of approaching emergency vehicles. It optimizes traffic light switching and ensures more rapid passage of the emergency vehicle that is safer for all vehicles.

Daimler. Daimler researchers developed a camera-based system that automatically classifies completely unknown situations using “scene labelling” and thus detects all important objects for driver assistance—from cyclists to pedestrians to wheelchair users.

Researchers in the “Environment Sensing” department showed their system thousands of photos from various German cities. In the photos, they had manually precisely labelled 25 different object classes, such as vehicles, cyclists, pedestrians, streets, pavements, buildings, posts and trees.

On the basis of these examples, the system learned automatically to classify correctly completely unknown scenes and thus to detect all important objects for driver assistance, even if the objects were highly hidden or far away. This is made possible by powerful computers that are artificially neurally networked in a manner similar to the human brain,-- i.e., deep neural networks.

Consequently, the system functions in a manner comparable to human sight. This, too, is based on a highly complex neural system that links the information from the individual sensory cells on the retina until a human is able to identify and differentiate an almost unlimited number of objects. Scene labelling transforms the camera from a mere measuring system into an interpretive system, as multifunctional as the interplay between eye and brain.

The tremendous increase in computing power in recent years has brought closer the day when vehicles will be able to see their surroundings in the same way as humans and also correctly understand complex situations in city traffic.

—Prof. Ralf Guido Herrtwich, Head of Driver Assistance and Chassis Systems, Group Research and Advance Development at Daimler AG

To advance this system quickly, Daimler continues researching together with partners to achieve the vision of the accident-free driving.

At the closing event of the UR:BAN, the Daimler researchers presented results from a total of five different test vehicles. In addition to a real-time demonstration of scene labelling, another test vehicle showed imaging radar systems and the new possibilities they offer in urban environments.

Results show that radar sensors are now capable of comprehensively resolving and visualizing not just any dynamic object, but also every static environment. The particular properties of radar waves mean that the system can also function in fog and bad weather. Moreover, the so-called micro-doppler allows the signatures of moving pedestrians and cyclists to be unambiguously classified.

In addition, Daimler showed how environment data from radar and camera sensors are merged by sensor fusion to form an environment model. The model takes account not only of the locations and speeds of the various road users, but also of attributes such as the type and size of the objects. The environment model also makes allowance for incomplete sensor data as well as missing information, as is typically the case in actual road traffic.

The third test vehicle included a system for the detection, classification and intention identification of pedestrians and cyclists. Similarly to a human driver, this system analyses head posture, body position and curbside position to predict whether a pedestrian intends to stay on the pavement or cross the road. In dangerous situations, this allows an accident-preventing system response to be triggered up to one second earlier than with currently available systems.

A further highlight that was demonstrated was how radar- and camera-based systems can make lane-changing in city traffic safer and more comfortable. Following a command from the driver, this system provides assisted lane-changing in a speed range between 30 and 60 km/h. The system senses the environment as well as the traffic in the lanes. The situational analysis predicts how the scenario will develop and then enables the computed trajectory. This is followed by assisted longitudinal and transverse control for changing lane.

The driver can tell intuitively from the instrument cluster whether or not the requested lane change can be executed by the system. After the change of lane has been successfully completed, longitudinal control with lane-keeping function is resumed. The driver at all times has the option of overruling the system by intervening with the steering, accelerator or brakes.

The fifth test vehicle showed the potential for predicting driver behavior in relation to planned lane changes or changes of direction. With regard to an imminent change of lane, for example, glances over the shoulder are linked with driving parameters that have already been sensed. A likely change of direction can be predicted from the interplay between steering movement, reduction of speed and map information. In the demonstration, the direction indicator was then automatically activated to inform other road users as early as possible.

Opel. Opel built an Insignia demonstration vehicle that not only warns the driver of dangers, but can also avoid collisions with vehicles and pedestrians by taking automatic evasive action through steering combined with braking. The car is equipped with advanced camera and radar, and modified braking and steering systems, which can intervene in the control of the vehicle.

Another Opel demonstration vehicle shows the potential for further development of driver assistance systems through studying driver behavior. Using vehicle data, a front camera and a head-tracking camera, a specially developed algorithm analyzes driver behavior patterns to predict at an early stage, for example, whether the driver will perform a lane change maneuver or not. Such enhancements will optimize the performance of driver assistance systems such as side blind-zone alert by avoiding unnecessary warnings and driver irritation, helping to increase the acceptance of active safety features in the future.

In addition to avoiding collisions, Opel is also working on improving inner-city traffic conditions for the benefit of motorists, city dwellers and the climate. Opel has built a demonstration vehicle based on the Insignia Sports Tourer that shows how information sent via Wi-Fi from the traffic management infrastructure and other vehicles can generate recommendations for driving at intersections. The recommendations can help the driver approach the intersection smoothly, safely and without wasting fuel, and preferably without stopping. They are displayed via an advanced Man-Machine-Interface (MMI) using the Driver Info Center in the instrument panel, with secondary information shown in the central console.

Bosch. The Bosch research team developed an assistance system that intervenes to prevent a collision with a pedestrian. At vehicle speeds up to 50 km/h, the system helps drivers brake and take evasive action. If braking alone is no longer enough to prevent a collision with a pedestrian who suddenly walks out in front of the car, the assistant instantaneously computes an evasive maneuver. As soon as drivers start using the steering wheel to take evasive action, the system kicks in to support the steering maneuver.

The evasive steering support system integrates the production stereo video camera with a computer in the trunk. Using smart algorithms, the computer calculates how the environment is changing and where objects are headed. In other words, the Bosch technology not only detects the current position of pedestrians and cyclists, but also predicts where they will be in a second’s time. This presents new opportunities for pedestrian protection.

According to our studies, provided the driver reacts at least half a second before a potential collision, the assistance system can help avoid it in 58 percent of cases.

—Dr. Lutz Bürkle

Bosch further has developed a system for driver observation that uses tiny cameras in the interior to monitor drivers’ line of sight. The goal is to warn distracted drivers before a risky situation develops. In this context, Bosch believes that it helps to place indicators in the instrument clusters or an LED display on the dashboard directly in the driver’s field of vision.

Another Bosch system recognizes crossing pedestrians and brings the car to a stop before an accident can happen. An assistance system for tight spaces goes even further. It maneuvers the car through tight spaces such as streets where cars are double parked. Using images from the stereo video camera, the computer calculates the path the car should travel. It then controls the electrical power steering and ensures that the car maneuvers through a tight space unscathed. The Bosch system also recognizes when a space is too tight to pass through, warning the driver or stopping the car in time before the exterior rear-view mirrors or fenders are damaged.


The comments to this entry are closed.