Stephan Reuter

The Labeled Multi-Bernoulli Filter

This paper proposes a generalization of the multi- Bernoulli filter called the labeled multi-Bernoulli filter that outputs target tracks. Moreover, the labeled multi-Bernoulli filter does not exhibit a cardinality bias due to a more accurate update approximation compared to the multi-Bernoulli filter by exploiting the conjugate prior form for labeled Random Finite Sets. The proposed filter can be interpreted as an efficient approximation of the δ-Generalized Labeled Multi-Bernoulli filter. It inherits the advantages of the multi-Bernoulli filter in regards to particle implementation and state estimation. It also inherits advantages of the δ-Generalized Labeled Multi-Bernoulli filter in that it outputs (labeled) target tracks and achieves better performance.

Multiple Extended Target Tracking With Labeled Random Finite Sets

Targets that generate multiple measurements at a given instant in time are commonly known as extended targets. These present a challenge for many tracking algorithms, as they violate one of the key assumptions of the standard measurement model. In this paper, a new algorithm is proposed for tracking multiple extended targets in clutter, which is capable of estimating the number of targets, as well the trajectories of their states, comprising the kinematics, measurement rates, and extents. The proposed technique is based on modeling the multi-target state as a generalized labeled multi-Bernoulli (GLMB) random finite set (RFS), within which the extended targets are modeled using gamma Gaussian inverse Wishart (GGIW) distributions. A cheaper variant of the algorithm is also proposed, based on the labelled multi-Bernoulli (LMB) filter. The proposed GLMB/LMB-based algorithms are compared with an extended target version of the cardinalized probability hypothesis density (CPHD) filter, and simulation results show that the (G)LMB has improved estimation and tracking performance.

The Labeled Multi-Bernoulli SLAM Filter

In this contribution, a new algorithm addressing the simultaneous localization and mapping (SLAM) problem is proposed: a Rao-Blackwellized implementation of the Labeled Multi-Bernoulli SLAM (LMB-SLAM) filter. Further, we establish that the LMB-SLAM does not require the approximations used in Probability Hypothesis Density SLAM (PHD-SLAM). The LMB-SLAM is shown to outperform PHD-SLAM in simulations by providing a more accurate map as well as an improved estimate of the vehicles trajectory which is an expected result due to the superior performance of the LMB filter in tracking applications.

Autonomous driving at Ulm University: A modular, robust, and sensor-independent fusion approach

The project “Autonomous Driving” at Ulm University aims at advancing highly-automated driving with close-to-market sensors while ensuring easy exchangeability of the particular components. In this contribution, the experimental vehicle that was realized during the project is presented along with its software modules. To achieve the mentioned goals, a sophisticated fusion approach for robust environment perception is essential. Apart from the necessary motion planning algorithms, this paper thus focuses on the sensor-independent fusion scheme. It allows for an efficient sensor replacement and realizes redundancy by using probabilistic and generic interfaces. Redundancy is ensured by utilizing multiple sensors of different types in crucial modules like grid mapping, localization and tracking. Furthermore, the combination of the module outputs to a consistent environment model is achieved by employing their probabilistic representation. The performance of the vehicle is discussed using the experience from numerous autonomous driving tests on public roads.

Companion-Technology: Towards User- and Situation-Adaptive Functionality of Technical Systems

The properties of multimodality, individuality, adaptability, availability, cooperativeness and trustworthiness are at the focus of the investigation of Companion Systems. In this article, we describe the involved key components of such a system and the way they interact with each other. Along with the article comes a video, in which we demonstrate a fully functional prototypical implementation and explain the involved scientific contributions in a simplified manner. The realized technology considers the entire situation of the user and the environment in current and past states. The gained knowledge reflects the context of use and serves as basis for decision-making in the presented adaptive system.

Road user tracking at intersections using a multiple-model PHD filter

A major aim of the joint project Ko-PER is the mitigation of fatal accidents at urban intersections. Therefore several test intersections have been equipped with multiple laser range finders to recognize and track road users. Besides a high traffic density the variety of road users is challenging. In this contribution a multiple-model (MM) probability hypothesis density filter with a track representation extended by class probabilities is proposed. The approach enables tracking of road users with appropriate motion models using a single MM filter. Due to the estimation of the class probabilities an adaption of the transition probabilities between the models is possible. The performance of the road user tracking is evaluated using real world data.

Fusion of laser and radar sensor data with a sequential Monte Carlo Bayesian occupancy filter

Occupancy grid mapping is a well-known environment perception approach. A grid map divides the environment into cells and estimates the occupancy probability of each cell based on sensor measurements. An important extension is the Bayesian occupancy filter (BOF), which additionally estimates the dynamic state of grid cells and allows modeling changing environments. In recent years, the BOF attracted more and more attention, especially sequential Monte Carlo implementations (SMC-BOF), requiring less computational costs. An advantage compared to classical object tracking approaches is the object-free representation of arbitrarily shaped obstacles and free-space areas. Unfortunately, publications about BOF based on laser measurements report that grid cells representing big, contiguous, stationary obstacles are often mistaken as moving with the velocity of the ego vehicle (ghost movements). This paper presents a method to fuse laser and radar measurement data with the SMC-BOF. It shows that the doppler information of radar measurements significantly improves the dynamic estimation of the grid map, reduces ghost movements, and in general leads to a faster convergence of the dynamic estimation.

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

The number of fatal accidents involving pedestrians and bikers at urban intersections is still increasing. Therefore, an intersection-based perception system provides a dynamic model of the intersection scene to the vehicles. Based on that, the intersection perception facilitates to discriminate occlusions which is expected to significantly reduce the number of accidents at intersections. Therefore this contribution presents a general purpose multi-sensor tracking algorithm, the classifying multiple-model probability hypothesis density (CMMPHD) filter, which facilitates the tracking and classification of relevant objects using a single filter. Due to the different motion characteristics, a multiple-model approach is required to obtain accurate state estimates and persistent tracks for all types of objects. Additionally, an extension of the PHD filter to handle contradictory measurements of different sensor types based on the Dempster-Shafer theory of evidence is proposed. The performance of tracking and classification is evaluated using real world sensor data of a public intersection.

Real-Time Multi-Object Tracking using Random Finite Sets

The multi-object Bayes (MOB) filter uses random finite sets (RFSs) to represent a scene. A drawback of this filter is the computational complexity of the multi-object likelihood function. In this contribution, an approximation of the multi-object likelihood function is presented allowing for real-time implementation on a graphics processing unit using sequential Monte Carlo (SMC) methods. Additionally, a track extraction algorithm using clustering as well as an approach to determine the existence probability of each single object are proposed.

Fusion paradigms in cognitive technical systems for human-computer interaction

Recent trends in human-computer interaction (HCI) show a development towards cognitive technical systems (CTS) to provide natural and efficient operating principles. To do so, a CTS has to rely on data from multiple sensors which must be processed and combined by fusion algorithms. Furthermore, additional sources of knowledge have to be integrated, to put the observations made into the correct context. Research in this field often focuses on optimizing the performance of the individual algorithms, rather than reflecting the requirements of CTS. This paper presents the information fusion principles in CTS architectures we developed for Companion Technologies. Combination of information generally goes along with the level of abstractness, time granularity and robustness, such that large CTS architectures must perform fusion gradually on different levels - starting from sensor-based recognitions to highly abstract logical inferences. In our CTS application we sectioned information fusion approaches into three categories: perception-level fusion, knowledge-based fusion and application-level fusion. For each category, we introduce examples of characteristic algorithms. In addition, we provide a detailed protocol on the implementation performed in order to study the interplay of the developed algorithms.