Reliable tracking of road users plays a critical part on the way to safe automated driving. In this paper, a machine learning based tracking approach on radar data is presented utilizing the radar target point clouds from multiple time steps as input to detect road users and to predict their tracking information. The detection and tracking of objects is achieved by applying a combination of known feature extractors from lidar and camera detection tasks. The generated feature maps are used as input to two branches - one branch for detection and one for tracking. In experiments on an extensive real-world radar data set, the proposed model achieves promising results in tracking performance compared to a basic clustering and a classification assisted tracking approach.

Binary Neural Networks (BNNs) can drastically reduce memory size and accesses by applying bit-wise operations instead of standard arithmetic operations. Therefore it could significantly improve the efficiency and lower the energy consumption at runtime, which enables the application of state-of-the-art deep learning models on low power devices. BMXNet is an open-source BNN library based on MXNet, which supports both XNOR-Networks and Quantized Neural Networks. The developed BNN layers can be seamlessly applied with other standard library components and work in both GPU and CPU mode. BMXNet is maintained and developed by the multimedia research group at Hasso Plattner Institute and released under Apache license. Extensive experiments validate the efficiency and effectiveness of our implementation. The BMXNet library, several sample projects, and a collection of pre-trained binary deep models are available for download at https://github.com/hpi-xnor.

Requirements change and so (should) do requirements artifacts, such as use cases. However, we have little knowledge about which changes requirements engineers actually perform on use cases. We do not know what is changing, at which locations use cases change and need a deeper understanding of which changes are problematic in terms of difficult or risky.

We present a simple self-contained appliance that allows relocating inanimate physical objects across distance. Each unit consists of an off-the-shelf 3D printer that we have extended with a 3-axis milling machine, a camera, and a micro-controller for encryption/decryption and transmission. Users place an object into the sender unit, enter the address of a receiver unit, and press the relocate button. The sender unit now digitizes the original object layer-by-layer: it shaves off material using the built-in milling machine, takes a photo using the built-in camera, encrypts the layer using the public key of the receiver, and transmits it. The receiving unit decrypts the layer in real-time and starts printing right away. Users thus see the object appear layer-by-layer on the receiver side as it disappears layer-by-layer at the sender side. Scotty is different from previous systems that copy physical objects, as its destruction and encryption mechanism guarantees that only one copy of the object exists at a time. Even though our current prototype is limited to single-material plastic objects, it allows us to address two application scenarios: (1) Scotty can help preserve the uniqueness and thus the emotional value of physical objects shared between friends. (2) Scotty can address some of the licensing issues involved in fast electronic delivery of physical goods. We explore the former in an exploratory user study with three pairs of participants.

This contribution presents a precise localization method for advanced driver assistance systems. A Maximally Stable Extremal Region (MSER) detector is used to extract bright areas, i.e. lane markings, from grayscale camera images. Furthermore, this algorithm is also used to extract features from a laser scanner grid map. These regions are automatically stored as landmarks in a geospatial data base during a map creation phase. A particle filter is then employed to perform the pose estimation. For the weight update of the filter the similarity between the set of online MSER detections and the set of mapped landmarks within the field of view is evaluated. Hereby, a two stage sensor fusion is carried out. First, in order to have a large field of view available, not only a forward facing camera but also a rearward facing camera is used and the detections from both sensors are fused. Secondly, the weight update also integrates the features detected from the laser grid map, which is created using measurements of three laser scanners. The performance of the proposed algorithm is evaluated on a 7 km long stretch of a rural road. The evaluation reveals that a relatively good position estimation and a very accurate orientation estimation (0.01 deg ± 0.22 deg) can be achieved using the presented localization method. In addition, an evaluation of the localization performance based only on each of the respective kinds of MSER features is provided in this contribution and compared to the combined approach.

With the help of advanced driver assistance systems (ADAS), today's vehicles are already able to perform impressive perception tasks. Besides information about other traffic participants, the current environmental visibility condition is one key aspect to enable further development, especially in difficult scenarios and adverse weather conditions. This work presents a system to estimate the visibility range for both the driver and vision-based ADAS. On the basis of an existing probabilistic radar-camera vehicle tracking framework, individual visibility range measurements are deduced by monitoring camera measurements to vehicles already confirmed by the radar sensor. This individual track-level information is then combined with spatial and temporal memory to build a holistic system to infer the current visibility condition in a probabilistic way. Experiments on both synthetic and real-world data validate the proposed concepts. In addition, a conducted user study compares system outputs to human visibility perception on realword scenes.

The idea presented in this paper is an online learning approach for behavior prediction of other road participants at an intersection. Learning traffic situations online has the advantage that it is possible to react to changes in driving behavior due to changes in the environment. If visual obstruction occurs because of changes in the environment, e.g. a growing corn field, the behavior of drivers changes. In contrast to pre-trained models an online learning concept is able to react to these changes in driving behavior. In this contribution Case-Based Reasoning, a concept which adapts human reasoning and thinking to a system, is used. The functionality of the concept is shown by predicting the maneuver of an approaching vehicle at an intersection. The presented concept is able to predict if a vehicle turns in front of the ego-vehicle or stops and give the ego-vehicle right of way.

Current advanced driver assistance systems (ADAS) measure and evaluate every environment scenario in each trip from scratch. They are not able to draw on information of previous trips because currently a memory function in production vehicles does not exist. Learning systems for vehicles were proposed to aggregate information gathered by driving routes multiple times. This information can be used to create a learning map and enable highly automated driving. Learned information can represent a certain state of the environment captured by sensors like speed limits or geo-positions of roadworks. Changes in the vehicle relevant environment will affect vehicle perception and may affect the distribution of measured variables over time. The instant where the underlying distribution of a variable changes is denoted as change point. This can invalidate parts of the acquired knowledge and was not sufficiently dealt with in previous publications in the automotive field. The ability to detect the mentioned change points is essential for the necessary ongoing update of the learning map by devaluing or removing any invalidated knowledge from memory. For this purpose we propose a statistical hypothesis test and investigate its application for a prototypic ADAS: a Curve Warning Assistance System. The formulated test is able to detect change points faster and more robust than previously proposed algorithms. The ability to aggregate information in a learning map and to handle information actualization and devaluation represents a major building block for future highly automated driver assistance systems.

This paper presents a novel approach towards highly precise self-localization of a vehicle on a digital map. The proposed approach utilizes a map containing region descriptors extracted from ordinary occupancy grid maps. The Maximally Stable Extremal Regions (MSER) algorithm provides robust feature extraction from grid maps in a completely unsupervised process. This allows for the automatic creation of huge maps. Since only single region descriptor points of grid maps are saved in the map database, the data volume of the produced map is kept low. The approach uses a particle filter to estimate the vehicle position on the digital map. The particle filter associates MSER features extracted from an online generated grid map with features of the digital map. An evaluation with real world sensor data, collected on a German rural road, shows that the approach locates the vehicle very precisely.

This paper presents a self-learning spatial memory approach for advanced driver assistance systems. The storage concept for this memory is based on an object relational data base with support for spatial queries. This memory component is applied to the problem of stationary false alarms of an adaptive cruise control system. Test results which demonstrate the practicality of this approach are also provided. Furthermore, an evaluation for different weather conditions is presented.

Future driving assistance systems will need an increase ability to handle complex driving situations and to react appropriately according to situation criticality and requirements for risk minimization. Humans, driving on motorways, are able to judge, for example, cut-in situations of vehicles because of their experiences. The idea presented in this paper is to adapt these human abilities to technical systems and learn different situations over time. Case-Based Reasoning is applied to predict the behavior of road participants because it incorporates a learning aspect, based on knowledge acquired from the driving history. This concept facilitates recognition by matching actual driving situations against stored ones. In the first instance, the concept is evaluated on action prediction of vehicles on adjacent lanes on motorways and focuses on the aspect of vehicles cutting into the lane of the host vehicle.

As their functionality becomes more and more complex, future driver assistance systems rely on several different sensors in order to combine the advantages of different measurement principles. However, in multi-sensor fusion, measurements may arrive at the fusion unit out-of-sequence, the original order of the measurements may be lost. Whereas out-of-sequence measurement processing in state estimation has been studied extensively, their incorporation in existence estimation has not been solved in the past. This paper presents a new algorithm for state and existence estimation in time-critical applications, where out-of-sequence measurements are handled adequately. The derived algorithm is validated with real-world data from crash tests.

This paper addresses the problem of joint state and existence estimation in the presence of temporally asynchronous measurements. In multi-sensor fusion, the problem can occur that measurements from different sensors can arrive at the processing unit out of sequence, i.e., the original temporal order of the measurements is lost. For the first time, the influence of these out-of-sequence measurements on state estimation as well as on existence estimation is examined. The existence probabilities are estimated via the Joint Integrated Probabilistic Data Association Filter (JIPDA) [17]. Two different methods to deal with out-of-sequence measurements in JIPDA are described and compared. It is shown that the handling of out-of-sequence measurements has a considerable influence not only on state, but also on existence estimation.

This paper presents a new approach to exact timestamping of asynchronous measurements in a multi-sensor setup. In order to improve the performance of a single sensor, driver assistance systems use several different sensors which have different latencies that usually cannot be measured directly. These unknown latencies pose a problem in data association and temporal synchronization. Consequently, a method to estimate or incorporate the latencies is needed in all sensor fusion algorithms in order to derive the real time of a measurement. In this paper a method is described to compensate the sensor latencies even if they cannot be observed directly.