Automotive

In the automotive domain, the following use cases are defined:

  • Highway pilot

Highly-automated driving on single- or multi-lane highway networks is currently one of the most attractive functions for passenger cars and commerical vehicles. It allows the driver to turn attention away from the driving task for a longer period. The highly-automated functions handles all of the driving-related tasks like overtaking slower vehicles, driving in tunnels or through toll booths. In addition the system initiates the process of returning responsibility back to the driver. In emergency situations the functions execute defined actions. The use case will provide all relevant scenarios and boundary conditions for verification and validation of all related highly-automated functions. Main aspects are early functional and non-functional verification as well as new approaches for early validation of safety and security aspects under all possible driving conditions.automotive

The DrivingCube is an automotive test bed (power train test bed or alternatively a chassis dynamometer) extended by physical sensor stimulators. It is used to reproduce plausible, physically correct environmental conditions for the vehicle and therefore for the automated driving function. The test bed includes dynos, vehicle fixation and hardware interfaces for the sensor stimulators. In order to facilitate the development and facilitate the demonstration, there is also a small-scale 1:10 version of the test bed.  The intention of this demonstrator is to integrate the different tools and methods, related to the Highway Pilot testing functions that have been developed during the project. The car is equipped with an automated highway pilot function as well as the required sensors. The considered sensors will be camera, radar, and ultrasonic (just used for the small 1:10 scale version of the driving cube). The environment is simulated in Vires VTD.

  • Intersection crossing

The crossing of a road intersection is difficult and might lead to hazardous situations. In urban areas, almost 50% of traffic accidents with physical injuries happen within intersections and branches. Left turns at intersections are particularly challenging because of the large number of factors which must be considered. An important factor is the surrounding traffic especially the vehicles on the oncoming lanes which should be crossed during a left turn.

Systems which support autonomous left turn may help to reduce the number of accidents in this area. Use Case 2 intersection crossing using autonomous vehicles will test the usability of validation and verification methodology, bricks and tools developed within Enable-S3. The test will take place by applying them to several existing autonomously left turning research prototypes of automated cyber physical systems (ACPS).

The validation of this ACPS will take place in several experiments which have a special focus on testing the decision making component of the ACPS. This core component has to decide if the ACPS vehicle will turn left before, after or in-between oncoming vehicles and can lead to hazardous situations in case of an wrong decision.

Therefore  the first step of UC2 was the definition and implementation of significant left turn scenarios and on the assessment of Key Performance Indicators (KPIs) which can provide quantified results on the capabilities of the vehicle decision making component.

A first UC2 experiment is planned for September 2017. It will focus on optimization of the scenarios and KPIs and will take place on Proving Ground and within a Vehicle in the Loop (ViL) Simulator. In both environments the same ACPS within the same vehicle will drive through the same scenarios over the same intersection. Thereby a scenario based comparison of the validation results between reality and simulation will be possible. This comparison will take place in another experiment in 2018 as soon as further suitable models (for: vehicle, sensors, C2X and environment) are available by Enable-S3 bricks.

The first model available for the UC2 experiment in 2017 is the 3D Environment Model. This Model provides an accurate Digital Map (for the ACPS) as well as 3D Environment of the proving ground intersection (for the simulation).

dlrr

UC2 Test Intersection on Proving Ground (Source: Aerial image from City of Brunswick 2014);
Right: Intersection as 3D Environment Model “first Version” (Source: DLR)

  • Context-Aware In-Car Reasoning System

As part of ENABLE-S3, IBM is leading the development, test and validation of a context-aware in-car reasoning system. This is a connected service for connected vehicles, which is a cognitive personal companion for the driver. The in-car companion debates and reasons with driver in order to mitigate personalized risks for the journey. Within this UC, we are developing a system to test and validate services for connected vehicles, without requiring a large number of real vehicles.

We consider the connected car scenario and aim to push the limits of off-line testing as far as possible within this scenario. In our use case, a context-aware in-car reasoning system supports passengers in their travel decisions. For instance, in the context of a motorway ride, assume that a large traffic accident occurs on the planned route. The reasoning system would detect that the accident will affect the arrival time at the destination, alert the driver and provide, upon request, alternative routes specifying the consequences in terms of cost, average arrival time and uncertainty in arrival time. It would also provide assistance to the driver in choosing among the proposed alternatives by asking information about preferences (for instance preferring to take a toll road to ensure a high probability of arriving at a given time). To this end the in-car reasoning system must have a contextual understanding of the vehicle’s surroundings and be able to interact in a meaningful manner with the driver. This interaction can involve advice and discussion of route options up to context aware alerts issued to the driver.

  • Traffic Jam Pilot with V2x Communication

The “Traffic Jam Pilot” (TJA) is intended to allow vehicles to safely drive their passengers through congestion scenarios, in other words, the vehicle will guide itself during predictable, low-speed conditions, using in-vehicle sub-systems such as Adaptive Cruise Control (ACC - which enables the vehicle to “follow” the vehicle ahead and brake whenever needed), “Lane Assistant” (to keep the vehicle within the boundaries of the lane) and V2V communication to enhance the vehicles situational awareness about environmental conditions related to the surrounding vehicles. The idea behind the “Traffic Jam Assist” system (TJA) is to propose the activation of the autonomous driving mode to the driver based on the current traffic situation.  The TJA has three working states based on the traffic density measured by the average speed of the vehicle and its neighbours. In case of an average speed above 60 km/h for cars and 30 km/h for trucks, the nothing will be done apart from monitoring. Below this average speed, the TJA activation will be suggested to the driver, on the dashboard that, if confirmed, will activate the semi-autonomous mode above 20 km/h for cars and 10 km/h for trucks using only the basic ADAS functions (ACC and Lane Keeping). The fully-autonomous mode will be automatically activated below this average speed which will make the vehicle enter into platooning mode with lead and follow vehicles.tjp

 

  • Valet parking

Valet parking means automated parking in a parking area. Potential scenario: when you approach a shopping mall, you receive an offer by the valet parking system to safely park your car. If you accept, you can start your shopping while the vehicle parks itself. A remote Parking Area Management (PAM) locates the free parking slots, and defines the optimal path for the vehicle. This path is tracked by vehicle, which also sense its’ environment. The path is dynamically adapted if obstacles are detected. All this runs under a supervisory control, which observes the scene and can interrupt the path following, for example by requiring an emergency brake.