Search

In the last ten years, various automated machine learning (AutoM ) systems have been proposed to build end-to-end machine learning (ML) pipelines with minimal human interaction. Even though such automatically synthesized ML pipelines are able to achieve a competitive performance, recent studies have shown that users do not trust models constructed by AutoML due to missing transparency of AutoML systems and missing explanations for the constructed ML pipelines. In a requirements analysis study with 36 domain experts, data scientists, and AutoML researchers from different professions with vastly different expertise in ML, we collect detailed informational needs for AutoML. We propose XAutoML, an interactive visual analytics tool for explaining arbitrary AutoML optimization procedures and ML pipelines constructed by AutoML. XAutoML combines interactive visualizations with established techniques from explainable artificial intelligence (XAI) to make the complete AutoML procedure transparent and explainable. By integrating XAutoML with JupyterLab, experienced users can extend the visual analytics with ad-hoc visualizations based on information extracted from XAutoML. We validate our approach in a user study with the same diverse user group from the requirements analysis. All participants were able to extract useful information from XAutoML, leading to a significantly increased understanding of ML pipelines produced by AutoML and the AutoML optimization itself., Comment: Revised version accepted at ACM TiiS Special Issue on Human-centered Explainable AI

In the domain of computer vision, deep residual neural networks like EfficientNet have set new standards in terms of robustness and accuracy. One key problem underlying the training of deep neural networks is the immanent lack of a sufficient amount of training data. The problem worsens especially if labels cannot be generated automatically, but have to be annotated manually. This challenge occurs for instance if expert knowledge related to 3D parts should be externalized based on example models. One way to reduce the necessary amount of labeled data may be the use of autoencoders, which can be learned in an unsupervised fashion without labeled data. In this work, we present a deep residual 3D autoencoder based on the EfficientNet architecture, intended for transfer learning tasks related to 3D CAD model assessment. For this purpose, we adopted EfficientNet to 3D problems like voxel models derived from a STEP file. Striving to reduce the amount of labeled 3D data required, the networks encoder can be utilized for transfer training., Comment: Accepted/Peer-Revied Articel

Human activity recognition is seen of great importance in the medical and surveillance fields. Radar has shown great feasibility for this field based on the captured micro-Doppler ({\mu}-D) signatures. In this paper, a MIMO radar is used to formulate a novel micro-motion spectrogram for the angular velocity ({\mu}-{\omega}) in non-tangential scenarios. Combining both the {\mu}-D and the {\mu}-{\omega} signatures have shown better performance. Classification accuracy of 88.9% was achieved based on a metric learning approach. The experimental setup was designed to capture micro-motion signatures on different aspect angles and line of sight (LOS). The utilized training dataset was of smaller size compared to the state-of-the-art techniques, where eight activities were captured. A few-shot learning approach is used to adapt the pre-trained model for fall detection. The final model has shown a classification accuracy of 86.42% for ten activities., Comment: 6 pages, 7 figures, 2 tables

Radar for deep learning-based human identification has become a research area of increasing interest. It has been shown that micro-Doppler ($\mu$-D) can reflect the walking behavior through capturing the periodic limbs' micro-motions. One of the main aspects is maximizing the number of included classes while considering the real-time and training dataset size constraints. In this paper, a multiple-input-multiple-output (MIMO) radar is used to formulate micro-motion spectrograms of the elevation angular velocity ($\mu$-$\omega$). The effectiveness of concatenating this newly-formulated spectrogram with the commonly used $\mu$-D is investigated. To accommodate for non-constrained real walking motion, an adaptive cycle segmentation framework is utilized and a metric learning network is trained on half gait cycles ($\approx$ 0.5 s). Studies on the effects of various numbers of classes (5--20), different dataset sizes, and varying observation time windows 1--2 s are conducted. A non-constrained walking dataset of 22 subjects is collected with different aspect angles with respect to the radar. The proposed few-shot learning (FSL) approach achieves a classification error of 11.3 % with only 2 min of training data per subject., Comment: 5 pages, 6 figures, 2 tables

This paper introduces a novel approach for the grasping and precise placement of various known rigid objects using multiple grippers within highly cluttered scenes. Using a single depth image of the scene, our method estimates multiple 6D object poses together with an object class, a pose distance for object pose estimation, and a pose distance from a target pose for object placement for each automatically obtained grasp pose with a single forward pass of a neural network. By incorporating model knowledge into the system, our approach has higher success rates for grasping than state-of-the-art model-free approaches. Furthermore, our method chooses grasps that result in significantly more precise object placements than prior model-based work., Comment: Accepted at 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

Compared to point estimates calculated by standard neural networks, Bayesian neural networks (BNN) provide probability distributions over the output predictions and model parameters, i.e., the weights. Training the weight distribution of a BNN, however, is more involved due to the intractability of the underlying Bayesian inference problem and thus, requires efficient approximations. In this paper, we propose a novel approach for BNN learning via closed-form Bayesian inference. For this purpose, the calculation of the predictive distribution of the output and the update of the weight distribution are treated as Bayesian filtering and smoothing problems, where the weights are modeled as Gaussian random variables. This allows closed-form expressions for training the network's parameters in a sequential/online fashion without gradient descent. We demonstrate our method on several UCI datasets and compare it to the state of the art., Comment: 37th AAAI Conference on Artificial Intelligence (AAAI)

Maintenance scheduling is a complex decision-making problem in the production domain, where a number of maintenance tasks and resources has to be assigned and scheduled to production entities in order to prevent unplanned production downtime. Intelligent maintenance strategies are required that are able to adapt to the dynamics and different conditions of production systems. The paper introduces a deep reinforcement learning approach for condition-oriented maintenance scheduling in flow line systems. Different policies are learned, analyzed and evaluated against a benchmark scheduling heuristic based on reward modelling. The evaluation of the learned policies shows that reinforcement learning based maintenance strategies meet the requirements of the presented use case and are suitable for maintenance scheduling in the shop floor., Comment: Accepted at the IEEE International Conference on Industrial Informatics (INDIN) 2021

Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are hard to understand which limits their use in some context of the industrial world. A common and hard to detect challenge in machine learning (ML) tasks is data bias. In this work, we present a systematic approach to uncover data bias by means of attribution maps. For this purpose, first an artificial dataset with a known bias is created and used to train intentionally biased CNNs. The networks' decisions are then inspected using attribution maps. Finally, meaningful metrics are used to measure the attribution maps' representativeness with respect to the known bias. The proposed study shows that some attribution map techniques highlight the presence of bias in the data better than others and metrics can support the identification of bias., Comment: Accepted for publication at the 30th International Conference on Artificial Neural Networks (ICANN)

Lower extremity amputees face challenges in natural locomotion, which is partially compensated using powered assistive systems, e.g., micro-processor controlled prosthetic leg. In this paper, a radar-based perception system is proposed to assist prosthetic legs for autonomous obstacle traversing, focusing on multiple-step staircases. The presented perception system is composed of a radar module operating with a multiple-input-multiple-output (MIMO) configuration to localize consecutive stair corners. An inertial measurement unit (IMU) is integrated for coordinates correction due to the angular dis-positioning that occurs because of the knee angular motion. The captured information from both sensors is used for staircase dimensioning (depth and height). A shallow neural network (NN) is proposed to model the error due to the hardware limitations and enhance the dimension estimation accuracy (1 cm). The algorithm is implemented on a microcontroller subsystem of the radar kit to qualify the perception system for embedded integration in powered prosthetic legs., Comment: 5 pages, 6 figures, 2 tables

This paper presents a novel approach for the automatic offline grasp pose synthesis on known rigid objects for parallel jaw grippers. We use several criteria such as gripper stroke, surface friction, and a collision check to determine suitable 6D grasp poses on an object. In contrast to most available approaches, we neither aim for the best grasp pose nor for as many grasp poses as possible, but for a highly diverse set of grasps distributed all along the object. In order to accomplish this objective, we employ a clustering algorithm to the sampled set of grasps. This allows to simultaneously reduce the set of grasp pose candidates and maintain a high variance in terms of position and orientation between the individual grasps. We demonstrate that the grasps generated by our method can be successfully used in real-world robotic grasping applications., Comment: Accepted at 2021 International Conference on Intelligent Autonomous Systems (IAS-16 2021)

Single shot approaches have demonstrated tremendous success on various computer vision tasks. Finding good parameterizations for 6D object pose estimation remains an open challenge. In this work, we propose different novel parameterizations for the output of the neural network for single shot 6D object pose estimation. Our learning-based approach achieves state-of-the-art performance on two public benchmark datasets. Furthermore, we demonstrate that the pose estimates can be used for real-world robotic grasping tasks without additional ICP refinement., Comment: Accepted at 2021 IEEE International Conference on Robotics and Automation (ICRA 2021)

Automated machine learning (AutoML) aims for constructing machine learning (ML) pipelines automatically. Many studies have investigated efficient methods for algorithm selection and hyperparameter optimization. However, methods for ML pipeline synthesis and optimization considering the impact of complex pipeline structures containing multiple preprocessing and classification algorithms have not been studied thoroughly. In this paper, we propose a data-centric approach based on meta-features for pipeline construction and hyperparameter optimization inspired by human behavior. By expanding the pipeline search space incrementally in combination with meta-features of intermediate data sets, we are able to prune the pipeline structure search space efficiently. Consequently, flexible and data set specific ML pipelines can be constructed. We prove the effectiveness and competitiveness of our approach on 28 data sets used in well-established AutoML benchmarks in comparison with state-of-the-art AutoML frameworks., Comment: Conference paper accepted at Symposium on Intelligent Data Analysis (IDA) 2021

In this paper, we introduce a novel learning-based approach for grasping known rigid objects in highly cluttered scenes and precisely placing them based on depth images. Our Placement Quality Network (PQ-Net) estimates the object pose and the quality for each automatically generated grasp pose for multiple objects simultaneously at 92 fps in a single forward pass of a neural network. All grasping and placement trials are executed in a physics simulation and the gained experience is transferred to the real world using domain randomization. We demonstrate that our policy successfully transfers to the real world. PQ-Net outperforms other model-free approaches in terms of grasping success rate and automatically scales to new objects of arbitrary symmetry without any human intervention., Comment: Accepted at 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020)

Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or fifinance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions., Comment: Accepted for publication at the Journal of Artificial Intelligence Research (JAIR)

We show that in the variational multiscale framework, the weak enforcement of essential boundary conditions via Nitsche's method corresponds directly to a particular choice of projection operator. The consistency, symmetry and penalty terms of Nitsche's method all originate from the fine-scale closure dictated by the corresponding scale decomposition. As a result of this formalism, we are able to determine the exact fine-scale contributions in Nitsche-type formulations. In the context of the advection-diffusion equation, we develop a residual-based model that incorporates the non-vanishing fine scales at the Dirichlet boundaries. This results in an additional boundary term with a new model parameter. We then propose a parameter estimation strategy for all parameters involved that is also consistent for higher-order basis functions. We illustrate with numerical experiments that our new augmented model mitigates the overly diffusive behavior that the classical residual-based fine-scale model exhibits in boundary layers at boundaries with weakly enforced essential conditions.

Artificial neural networks (NNs) have become the de facto standard in machine learning. They allow learning highly nonlinear transformations in a plethora of applications. However, NNs usually only provide point estimates without systematically quantifying corresponding uncertainties. In this paper a novel approach towards fully Bayesian NNs is proposed, where training and predictions of a perceptron are performed within the Bayesian inference framework in closed-form. The weights and the predictions of the perceptron are considered Gaussian random variables. Analytical expressions for predicting the perceptron's output and for learning the weights are provided for commonly used activation functions like sigmoid or ReLU. This approach requires no computationally expensive gradient calculations and further allows sequential learning., Comment: Accepted for publication at the 59th IEEE Conference on Decision and Control (CDC) 2020. v2: correction of typos

Recent years have seen many advances in methods for causal structure learning from data. The empirical assessment of such methods, however, is much less developed. Motivated by this gap, we pose the following question: how can one assess, in a given problem setting, the practical efficacy of one or more causal structure learning methods? We formalize the problem in a decision-theoretic framework, via a notion of expected loss or risk for the causal setting. We introduce a theoretical notion of causal risk as well as sample quantities that can be computed from data, and study the relationship between the two, both theoretically and through an extensive simulation study. Our results provide an assumptions-light framework for assessing causal structure learning methods that can be applied in a range of practical use-cases.

In this paper, we introduce a novel single shot approach for 6D object pose estimation of rigid objects based on depth images. For this purpose, a fully convolutional neural network is employed, where the 3D input data is spatially discretized and pose estimation is considered as a regression task that is solved locally on the resulting volume elements. With 65 fps on a GPU, our Object Pose Network (OP-Net) is extremely fast, is optimized end-to-end, and estimates the 6D pose of multiple objects in the image simultaneously. Our approach does not require manually 6D pose-annotated real-world datasets and transfers to the real world, although being entirely trained on synthetic data. The proposed method is evaluated on public benchmark datasets, where we can demonstrate that state-of-the-art methods are significantly outperformed., Comment: Accepted at 2020 IEEE International Conference on Robotics and Automation (ICRA 2020)

In this paper, we introduce a new public dataset for 6D object pose estimation and instance segmentation for industrial bin-picking. The dataset comprises both synthetic and real-world scenes. For both, point clouds, depth images, and annotations comprising the 6D pose (position and orientation), a visibility score, and a segmentation mask for each object are provided. Along with the raw data, a method for precisely annotating real-world scenes is proposed. To the best of our knowledge, this is the first public dataset for 6D object pose estimation and instance segmentation for bin-picking containing sufficiently annotated data for learning-based approaches. Furthermore, it is one of the largest public datasets for object pose estimation in general. The dataset is publicly available at http://www.bin-picking.ai/en/dataset.html., Comment: Accepted at 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)