Robust and reliable online 3D multi-object tracking is an essential component of autonomous driving. Recent research follows the tracking-by-detection paradigm and focuses mainly on lidar sensors, due to their superior range, resolution and depth accuracy compared to other automotive sensors. This simplifies the challenging data association in crowded urban road scenes, resulting in a predominant status of laser based methods. In contrast, we propose an online 3D multi-object tracker based solely on mono camera images and radar data to promote non-lidar based tracking research. By representing all detections of one frame as a Gaussian mixture model (GMM), we are able to avoid a fixed data association, which may include wrong assumptions. Instead, we assign the GMM to each tracked object and solve the data association implicitly and jointly by estimating the full 3D object tracks in our factor graph based optimization back end. By including all available information from the object detector, our algorithm achieves accurate, robust and reliable tracking results. We conduct real world experiments on the nuScenes tracking data set improving the state-of-the-art for non-lidar based methods from 17.7% to 34.1 % AMOTA.

Accurate and reliable tracking of multiple moving objects in 3D space is an essential component of urban scene understanding. This is a challenging task because it requires the assignment of detections in the current frame to the predicted objects from the previous one. Existing filter-based approaches tend to struggle if this initial assignment is not correct, which can happen easily.We propose a novel optimization-based approach that does not rely on explicit and fixed assignments. Instead, we represent the result of an off-the-shelf 3D object detector as Gaussian mixture model, which is incorporated in a factor graph framework. This gives us the flexibility to assign all detections to all objects simultaneously. As a result, the assignment problem is solved implicitly and jointly with the 3D spatial multi-object state estimation using non-linear least squares optimization.Despite its simplicity, the proposed algorithm achieves robust and reliable tracking results and can be applied for offline as well as online tracking. We demonstrate its performance on the real world KITTI tracking dataset and achieve better results than many state-of-the-art algorithms. Especially the consistency of the estimated tracks is superior offline as well as online.

Non-Gaussian and multimodal distributions are an important part of many recent robust sensor fusion algorithms. In difference to robust cost functions, they are probabilistically founded and have good convergence properties. Since their robustness depends on a close approximation of the real error distribution, their parametrization is crucial. We propose a novel approach that allows to adapt a multi-modal Gaussian mixture model to the error distribution of a sensor fusion problem. By combining expectation-maximization and non-linear least squares optimization, we are able to provide a computationally efficient solution with well-behaved convergence properties. We demonstrate the performance of these algorithms on several real-world GNSS and indoor localization datasets. The proposed adaptive mixture algorithm outperforms state-of-the-art approaches with static parametrization. Source code and datasets are available under https://mytuc.org/libRSF.

GNSS localization is an important part of today's autonomous systems, although it suffers from non-Gaussian errors caused by non-line-of-sight effects. Recent methods are able to mitigate these effects by including the corresponding distributions in the sensor fusion algorithm. However, these approaches require prior knowledge about the sensor's distribution, which is often not available. We introduce a novel sensor fusion algorithm based on variational Bayesian inference, that is able to approximate the true distribution with a Gaussian mixture model and to learn its parametrization online. The proposed Incremental Variational Mixture algorithm automatically adapts the number of mixture components to the complexity of the measurement's error distribution. We compare the proposed algorithm against current state-of-the-art approaches using a collection of open access real world datasets and demonstrate its superior localization accuracy.

A fundamental problem of non-linear state estimation in robotics is the violation of assumptions about the sensors' error distribution. State of the art approaches reduce the impact of these violations with robust cost functions or predefined non-Gaussian error models. Both require extensive parameter tuning and fail if the sensors' error characteristic changes over time, due to environmental changes, ageing or sensor malfunctions. We demonstrate how the error distribution itself can be part of the state estimation process. Based on an efficient approximation of a Gaussian mixture, we optimize the sensor model simultaneously during the standard state estimation. Due to an implicit expectation-maximization approach, we achieve a fast convergence without prior knowledge of the true distribution parameters. We implement this self-tuning algorithm in a least-squares optimization framework and demonstrate its real time capability on a real world dataset for satellite localization of a driving vehicle. The resulting estimation quality is superior to previous robust algorithms.

While many applications of sensor fusion suffer from the occurrence of outliers, a broad range of outlier robust graph optimization techniques has been developed for simultaneous localization and mapping. In this paper we investigate the performance of some of the most advanced algorithms for a simulated wireless localization setting affected by non-Gaussian errors. With this first analysis we can show some of the advantages and disadvantages that are connected with the different concepts behind Max-Mixture, Generalized iSAM, Switchable Constraints and Dynamic Covariance Scaling.