Search

This paper introduces the Bosch street dataset (BSD), a novel multi-modal large-scale dataset aimed at promoting highly automated driving (HAD) and advanced driver-assistance systems (ADAS) research. Unlike existing datasets, BSD offers a unique integration of high-resolution imaging radar, lidar, and camera sensors, providing unprecedented 360-degree coverage to bridge the current gap in high-resolution radar data availability. Spanning urban, rural, and highway environments, BSD enables detailed exploration into radar-based object detection and sensor fusion techniques. The dataset is aimed at facilitating academic and research collaborations between Bosch and current and future partners. This aims to foster joint efforts in developing cutting-edge HAD and ADAS technologies. The paper describes the dataset's key attributes, including its scalability, radar resolution, and labeling methodology. Key offerings also include initial benchmarks for sensor modalities and a development kit tailored for extensive data analysis and performance evaluation, underscoring our commitment to contributing valuable resources to the HAD and ADAS research community.

Radar sensors are low cost, long-range, and weather-resilient. Therefore, they are widely used for driver assistance functions, and are expected to be crucial for the success of autonomous driving in the future. In many perception tasks only pre-processed radar point clouds are considered. In contrast, radar spectra are a raw form of radar measurements and contain more information than radar point clouds. However, radar spectra are rather difficult to interpret. In this work, we aim to explore the semantic information contained in spectra in the context of automated driving, thereby moving towards better interpretability of radar spectra. To this end, we create a radar spectra-language model, allowing us to query radar spectra measurements for the presence of scene elements using free text. We overcome the scarcity of radar spectra data by matching the embedding space of an existing vision-language model. Finally, we explore the benefit of the learned representation for scene retrieval using radar spectra only, and obtain improvements in free space segmentation and object detection merely by injecting the spectra embedding into a baseline model.

We study the emergence of fluid flow in a closed chamber that is driven by dynamical deformations of an elastic sheet. The sheet is compressed between the sidewalls of the chamber and partitions it into two separate parts, each of which is initially filled with an inviscid fluid. When fluid exchange is allowed between the two compartments of the chamber, the sheet becomes unstable, and its motion displaces the fluid from rest. We derive an analytical model that accounts for the coupled, two-way, fluid-sheet interaction. We show that the system depends on four dimensionless parameters: the normalized excess length of the sheet compared to the lateral dimension of the chamber, $\Delta$; the normalized vertical dimension of the chamber; the normalized initial volume difference between the two parts of the chamber, $v_{\text{du}}(0)$; and the structure-to-fluid mass ratio, $\lambda$. We investigate the dynamics at the early times of the system's evolution and then at moderate times. We obtain the growth rates and the frequency of vibrations around the second and the first buckling modes, respectively. Analytical solutions are derived for these linear stability characteristics within the limit of the small-amplitude approximation. At moderate times, we investigate how the sheet escapes from the second mode. Given the chamber's dimensions, we show that the initial energy of the sheet is mostly converted into hydrodynamic energy of the fluid if $\lambda\ll 1$, and into kinetic energy of the sheet if $\lambda\gg 1$. In both cases most of the initial energy is released at time $ t_{\text{p}}\simeq \ln[c \Delta^{1/2}/v_{\text{du}}(0)]/\sigma$, where $\sigma$ is the growth rate and $c$ is a constant., Comment: 25 pages, 12 figures

We introduce BIDCD -- the Bosch Industrial Depth Completion Dataset. BIDCD is a new RGBD dataset of metallic industrial objects, collected with a depth camera mounted on a robotic manipulator. The main purpose of this dataset is to facilitate the training of domain-specific depth completion models, to be used in logistics and manufacturing tasks. We trained a State-of-the-Art depth completion model on this dataset, and report the results, setting an initial benchmark. Further, we propose to use this dataset for learning synthetic-to-depth-camera domain adaptation. Modifying synthetic RGBD data to mimic characteristics of real-world depth acquisition could potentially enhance training on synthetic data. For this end, we trained a Generative Adversarial Network (GAN) on a synthetic industrial dataset and our real-world data. Finally, to address geometric distortions in the generated images, we introduce an auxiliary loss that promotes preservation of the original shape. The BIDCD data is publicly available at https://zenodo.org/communities/bidcd.

Depth cameras are a prominent perception system for robotics, especially when operating in natural unstructured environments. Industrial applications, however, typically involve reflective objects under harsh lighting conditions, a challenging scenario for depth cameras, as it induces numerous reflections and deflections, leading to loss of robustness and deteriorated accuracy. Here, we developed a deep model to correct the depth channel in RGBD images, aiming to restore the depth information to the required accuracy. To train the model, we created a novel industrial dataset that we now present to the public. The data was collected with low-end depth cameras and the ground truth depth was generated by multi-view fusion., Comment: 17 pages, 4 figures

An extended immersed boundary method utilizing a semi-implicit direct forcing approach for the simulation of confined incompressible viscous thermal flow problems is presented. The method utilizes a Schur complement approach to enforce the kinematic constraints of no-slip and the corresponding thermal boundary conditions for immersed surfaces. The developed methodology can be straightforwardly adapted to any existing incompressible time marching solver based on a segregated pressure-velocity coupling. The method accurately meets the thermal and the no-slip boundary conditions on the surfaces of immersed bodies for the entire range of Rayleigh numbers $10^3\leqslant Ra\leqslant10^6$. Strategies for further increasing the computational efficiency of the developed approach are discussed. The method has been extensively verified by applying it for the simulation of a number of representative fully 3D confined natural convection steady and periodic flows. Complex dynamic phenomena typical of this kind of flow including vortical structures and convection cells and instability characteristics, were simulated and visualized and the results were found to compare favorably with results known from literature.

A new formulation of the immersed boundary method, which facilitates accurate simulation of incompressible isothermal and natural convection flows around immersed bodies and which may be applied for accurate linear stability analysis of the flows, is presented. The method is based on the fully pressure-velocity coupled approach, implicitly satisfying the divergence-free velocity constraint with no need for an extra projection-correction step, which is a significant advantage for the computational efficiency. The method treats pressure, boundary forces, and heat sources as Lagrange multipliers, thereby implicitly providing the kinematic constraints of no-slip and the corresponding thermal boundary conditions for immersed surfaces. Extensive verification of the developed method for both isothermal and natural convection flows is provided.

A transition to unsteadiness of a flow inside a cubic diagonally lid-driven cavity with no-slip boundaries is numerically investigated by a series of direct numerical simulations (DNS) performed on 100^3 and 200^3 stretched grids. It is found that the observed oscillatory instability is setting in via a subcritical symmetry-breaking Hopf bifurcation. The instability evolves on two vortices in a coupled manner. Critical values of Reynolds number Recr=2320 and non-dimensional angular oscillating frequency omegacr=0.249 for transition from steady to oscillatory flow are accurately estimated. Characteristic patterns of the 3D oscillatory flow are presented.