Helge Ritter's research while affiliated with Bielefeld University and other places

Publications (451)

Preprint
Full-text available
Fig. 1: Placing Sequence: an object is handed to the robot in an unknown pose (I). Then it is aligned with the placing surface solely based on tactile feedback (II). Finally it is placed on the table (III) and the robot retreats with its arm (IV). Abstract-Tactile sensors are promising tools for endowing robots with embodied intelligence and increa...
Preprint
Learn-to-Race Autonomous Racing Virtual Challenge hosted on www.aicrowd.com platform consisted of two tracks: Single and Multi Camera. Our UniTeam team was among the final winners in the Single Camera track. The agent is required to pass the previously unknown F1-style track in the minimum time with the least amount of off-road driving violations....
Chapter
In this work, we demonstrate how a publicly available, pre-trained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel. Our neural network architecture, which is using transfer learning, is quick to train and the results demonstrate performance comparable to other state-of-the-art approaches tha...
Conference Paper
Full-text available
We present a holistic grasping controller, combining free-space position control and in-contact force-control for reliable grasping given uncertain object pose estimates. Employing tactile fingertip sensors, undesired object displacement during grasping is minimized by pausing the finger closing motion for individual joints on first contact until f...
Preprint
Full-text available
With this work we are explaining the "You Only Look Once" (YOLO) single-stage object detection approach as a parallel classification of 10647 fixed region proposals. We support this view by showing that each of YOLOs output pixel is attentive to a specific sub-region of previous layers, comparable to a local region proposal. This understanding redu...
Chapter
In order to realize in-hand manipulation of unknown objects, we propose a dexterous manipulation framework based on visual and tactile feedback. Employing reactive controllers, this framework firstly allows to realize small-scale object manipulations while maintaining a stable grasp in the presence of unpredictable contact rolling or sliding. Secon...
Preprint
In this work, we demonstrate how to adapt a publicly available pre-trained Jukebox model for the problem of audio source separation from a single mixed audio channel. Our neural network architecture for transfer learning is fast to train and results demonstrate comparable performance to other state-of-the-art approaches. We provide an open-source c...
Chapter
Full-text available
This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic’s score of a high score image and increase the critic’s scor...
Article
Full-text available
Locomotion in animals provides a model for adaptive behavior as it is able to deal with various kinds of perturbations. Work in insects suggests that this evolved flexibility results from a modular architecture, which can be characterized by a recurrent neural network allowing for various emerging attractor states. Whereas a lower control-level coo...
Chapter
Variational Auto Encoder (VAE) provide an efficient latent space representation of complex data distributions which is learned in an unsupervised fashion. Using such a representation as input to Reinforcement Learning (RL) approaches may reduce learning time, enable domain transfer or improve interpretability of the model. However, current state-of...
Preprint
Full-text available
This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's sco...
Preprint
Full-text available
Variational Auto Encoder (VAE) provide an efficient latent space representation of complex data distributions which is learned in an unsupervised fashion. Using such a representation as input to Reinforcement Learning (RL) approaches may reduce learning time, enable domain transfer or improve interpretability of the model. However, current state-of...
Preprint
Full-text available
A typical part of learning to play the piano is the progression through a series of practice units that focus on individual dimensions of the skill, such as hand coordination, correct posture, or correct timing. Ideally, a focus on a particular practice method should be made in a way to maximize the learner's progress in learning to play the piano....
Preprint
Full-text available
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Despite this, a majority of challenges suffer from the same fundamental problems: participant solutions to the posed challenge are usually domain-specific, biased to maximall...
Article
Full-text available
Deep Reinforcement Learning techniques demonstrate advances in the domain of robotics. One of the limiting factors is a large number of interaction samples usually required for training in simulated and real-world environments. In this work, we demonstrate for a set of simulated dexterous in-hand object manipulation tasks that tactile information c...
Article
In daily life, humans use their limbs to perform various movements to interact with an external environment. Thanks to limb's variable and adaptive stiffness, humans can adapt their movements to unstable dynamics of the external environments. The underlying adaptive mechanism has been investigated, employing a simple planar device perturbed by exte...
Chapter
Full-text available
Interactive teaching from a human can be applied to extend the knowledge of a service robot according to novel task demands. This is particularly attractive if it is either inefficient or not feasible to pre-train all relevant object knowledge beforehand. Like in a normal human teacher and student situation it is then vital to estimate the learning...
Preprint
Full-text available
We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular structure is motivated by hypothesizing a sequence of intuitive steps that humans apply when trying to solve such a task. The model first predicts the path the target object wo...
Article
Full-text available
Brain-Computer Interfaces (BCI) offer unique windows into the cognitive processes underlying human-machine interaction. Identifying and analyzing the appropriate brain activity to have access to such windows is often difficult due to technical or psycho-physiological constraints. Indeed, studying interactions through this approach frequently requir...
Chapter
When a robot perceives its environment, it is not only important to know what kind of objects are present in it, but also how they relate to each other. For example in a cleanup task in a cluttered environment, a sensible strategy is to pick the objects with the least contacts to other objects first, to minimize the chance of unwanted movements not...
Chapter
Algorithms in machine learning commonly require training data to be independent and identically distributed. This assumption is not always valid, e. g. in online learning, when data becomes available in homogeneously labeled blocks, which can severely impede especially instance-based learning algorithms. In this work, we analyze and visualize this...
Article
Full-text available
For incremental machine-learning applications it is often important to robustly estimate the system accuracy during training, especially if humans perform the supervised teaching. Cross-validation and interleaved test/train error are here the standard supervised approaches. We propose a novel semi-supervised accuracy estimation approach that clearl...
Chapter
Full-text available
Haptic interaction involved in almost any physical interaction with the environment performed by humans is a highly sophisticated and to a large extent a computationally unmodelled process. Unlike humans, who seamlessly handle a complex mixture of haptic features and profit from their integration over space and time, even the most advanced robots a...
Article
Full-text available
Tactile sensing is a key sensor modality for robots interacting with their surroundings. These sensors provide a rich and diverse set of data signals that contain detailed information collected from contacts between the robot and its environment. The data are however not limited to individual contacts and can be used to extract a wide range of info...
Article
This work presents a novel object-level control framework for the dexterous in-hand manipulation of objects with torque-controlled robotic hands. The proposed impedance-based controller realizes the compliant 6-DOF control of a grasped object. Enabled by the in-hand localization, the slippage of contacts is avoided by actively maintaining the desir...
Article
Full-text available
Haptic exploration is a key skill for both robots and humans to discriminate and handle unknown objects or to recognize familiar objects. Its active nature is evident in humans who from early on reliably acquire sophisticated sensory-motor capabilities for active exploratory touch and directed manual exploration that associates surfaces and object...
Chapter
We propose a reinforcement learning approach that combines an asynchronous actor-critic model with a recurrent model of visual attention. Instead of using the full visual information of the scene, the resulting model accumulates the foveal information of controlled glimpses and is thus able to reduce the complexity of the network. Using the designe...
Chapter
Full-text available
Deep Reinforcement Learning has recently seen progress for continuous control tasks, driven by yearly challenges such as the NeurIPS Competition Track. This work combines complementary characteristics of two current state of the art methods, Twin-Delayed Deep Deterministic Policy Gradient and Distributed Distributional Deep Deterministic Policy Gra...
Chapter
Full-text available
We present a distributed supervised learning architecture, which can generate trajectory data conditioned by control commands and learned from demonstrations. The architecture consists of an ensemble of neural networks (NNs) which learns the dynamic model and a separate addressing NN that decides from which NN to draw a prediction. We introduce an...
Chapter
Full-text available
This paper introduces a novel approach for querying samples to be labeled in active learning for image recognition. The user is able to efficiently label images with a visualization for training a classifier. This visualization is achieved by using dimension reduction techniques to create a 2D feature embedding from high-dimensional features. This...
Chapter
A powerful concept that emerged within the field of educational psychology is scaffolding. Characterizing favourable expert-learner interaction, it can be defined as a temporal support that provides a novice an adaptable guidance to either learn tasks that would usually be beyond own capabilities or to speed up and refine the learning of manageable...
Preprint
Full-text available
Recent developments in machine-learning algorithms have led to impressive performance increases in many traditional application scenarios of artificial intelligence research. In the area of deep reinforcement learning, deep learning functional architectures are combined with incremental learning schemes for sequential tasks that include interaction...
Preprint
Haptic exploration is a key skill for both robots and humans to discriminate and handle unknown or recognize familiar objects. Its active nature is impressively evident in humans which from early on reliably acquire sophisticated sensory-motor capabilites for active exploratory touch and directed manual exploration that associates surfaces and obje...
Preprint
Full-text available
Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable objects and universal value function approximator learning for controllable objects. Such decomposition should...
Chapter
Full-text available
If label information in a classification task is expensive, it can be beneficial to use active learning to get the most informative samples to label by a human. However, there can be samples which are meaningless to the human or recorded wrongly. If these samples are near the classifier’s decision boundary, they are queried repeatedly for labeling....
Conference Paper
Single-trial classification of EEG data from Disorder of Consciousness patients (DoC) has proved particularly challenging. We present an approach that establishes a measure to relate the performance of single-trial classification of DoC patient EEG data with relational frequency bands and thus with their mental state. We evaluate our approach on 31...
Chapter
In this work, we investigate how local shape elements of a grasped object affect performance of haptic rotation. Blindfolded participants were asked to grasp a rotary knob using thumb and index finger and to rotate it 90\(^\circ \) counterclockwise around its own axis. The knobs exhibited a suitably distributed “grasp conform” combination of local...
Conference Paper
Full-text available
Estimating systems accuracy is crucial for applications of in-cremental learning. In this paper, we introduce the Distogram Estimation (DGE) approach to estimate the accuracy of instance-based classifiers. By calculating relative distances to samples it is possible to train an offline regression model, capable of predicting the classifiers accuracy...
Article
Full-text available
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on alg...
Article
Robotic manipulation of such highly deformable objects as clothes is a challenging problem. Robot-assisted dressing adds even more complexity as the garment motions must be aligned with a human body under conditions of strong and variable occlusion. As a step toward solutions for the general task, we consider the example of a dual-arm robot with at...
Conference Paper
Finding good principles to choose the actions of artificial agents like robots in the most beneficial way to optimize their control of the environment is very much in the focus of current research in the field of intelligent systems. Especially in reinforcement learning, where the agent learns through the direct interaction with the environment, a...
Chapter
In this work we propose a supplementary haptic framework for dexterous training during rehabilitation. Based on a variety of goal-oriented tasks in a form of puzzles and a set of specifically designed objects, we aim to improve the dexterity and the sense of touch of the impaired hand and fingers w.r.t. different shapes and shape features, such as...
Conference Paper
Recent advances in the development of optical head-mounted displays (HMDs), such as the Microsoft HoloLens, Google Glass, or Epson Moverio, which overlay visual information directly in the user's field of vision, have opened up new possibilities for augmented reality (AR) applications. We propose a system that uses such an optical HMD to assist the...
Article
Cooking is a complex activity of daily living that requires intuition, coordination, multitasking and time-critical planning abilities. We introduce KogniChef, a cognitive cooking assistive system that provides users with interactive, multi-modal and intuitive assistance while preparing a meal. Our system augments common kitchen appliances with a w...
Article
Full-text available
Because of the complex anatomy of the human hand, in the absence of external constraints a large number of postures and force combinations can be used to attain a stable grasp. Motor synergies provide a viable strategy to solve this problem of motor redundancy. In this study, we exploited the technical advantages of an innovative sensorized object...
Article
We present a method for automatically generating reduced marker layouts for marker-based optical motion capture of human hands. The employed motion reconstruction method is based on subspace-constrained inverse kinematics, which allows for the recovery of realistic hand movements even from sparse input data. We additionally present a user-specific...