Oliver Brock's research while affiliated with Technische Universität Berlin and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (211)
We present a simple approach to in-hand cube reconfiguration. By simplifying planning, control, and perception as much as possible, while maintaining robust and general performance, we gain insights into the inherent complexity of in-hand cube reconfiguration. We also demonstrate the effectiveness of combining GOFAI-based planning with the exploita...
This paper presents a feedback-control framework for in-hand manipulation (IHM) with dexterous soft hands that enables the acquisition of manipulation skills in the real-world within minutes. We choose the deformation state of the soft hand as the control variable. To control for a desired deformation state, we use coarsely approximated Jacobians o...
Scarcity of structural and evolutionary information on protein complexes poses a challenge to deep learning-based structure modelling. We integrated experimental distance restraints obtained by crosslinking mass spectrometry (MS) into AlphaFold-Multimer, by extending AlphaLink to protein complexes. Integrating crosslinking MS data substantially imp...
We propose a sensorization method for soft pneumatic actuators that uses an embedded microphone and speaker to measure different actuator properties. The physical state of the actuator determines the specific modulation of sound as it travels through the structure. Using simple machine learning, we create a computational sensor that infers the corr...
We implement Adelson and Bergen's spatiotemporal energy model with extension to three-dimensional (x–y–t) in an interactive tool. It helps gain an easy understanding of early (first-order) visual motion perception. We demonstrate its usefulness in explaining an assortment of phenomena, including some that are typically not associated with the spati...
While AlphaFold2 can predict accurate protein structures from the primary sequence, challenges remain for proteins that undergo conformational changes or for which few homologous sequences are known. Here we introduce AlphaLink, a modified version of the AlphaFold2 algorithm that incorporates experimental distance restraint information into its net...
In this article, we present the RBO Hand 3, a highly capable and versatile anthropomorphic soft hand based on pneumatic actuation. The RBO Hand 3 is designed to enable dexterous manipulation, to facilitate transfer of insights about human dexterity, and to serve as a robust research platform for extensive real-world experiments. It achieves these d...
We introduce a Learning from Demonstration (LfD) approach for contact-rich manipulation tasks with articulated mechanisms. The extracted policy from a single human demonstration generalizes to different mechanisms of the same type and is robust against environmental variations. The key to achieving such generalization and robustness from a single h...
We present a novel learning from demonstration approach which uses environmental constraints as the underlying representation to interpret and reproduce demonstrations. This representation based on environmental constraints separates the information that facilitates generalization from the information specific to object instances. Combined with ada...
Motivation: The quality of biological data crucially affects progress in science. This quality can be improved with better measurement devices, more sophisticated experimental designs, or repetitious measurements. Each of these options is associated with substantial costs. We present a simple computational tool as an alternative. This algorithmic t...
We want to understand how animals can learn to solve complex tasks. To achieve this, it makes sense to first hypothesize learning models and then compare these models to real biological learning data. But how to perform such a comparison is still unclear. We propose that yoking is an important component to such an analysis. In yoking, two agents ar...
We create a virtual 2D tactile array for soft pneumatic actuators using embedded audio components. We detect contact-specific changes in sound modulation to infer tactile information. We evaluate different sound representations and learning methods to detect even small contact variations. We demonstrate the acoustic tactile sensor array by the exam...
We propose a sensorization method for soft pneumatic actuators that uses an embedded microphone and speaker to measure different actuator properties. The physical state of the actuator determines the specific modulation of sound as it travels through the structure. Using simple machine learning, we create a computational sensor that infers the corr...
A gaze-fixating robot perceives distance to the fixated object and relative positions of surrounding objects immediately, accurately, and robustly. We show how fixation, which is the act of looking at one object while moving, exploits regularities in the geometry of 3D space to obtain this information. These regularities introduce rotation-translat...
Robotic manipulation behavior should be robust to disturbances that violate high-level task-structure. Such robustness can be achieved by constantly monitoring the environment to observe the discrete high-level state of the task. This is possible because different phases of a task are characterized by different sensor patterns and by monitoring the...
We present in-hand manipulation skills on a dexterous, compliant, anthropomorphic hand. Even though these skills were derived in a simplistic manner, they exhibit surprising robustness to variations in shape, size, weight, and placement of the manipulated object. They are also very insensitive to variation of execution speeds, ranging from highly d...
We present the RBO Hand 3, a highly capable and versatile anthropomorphic soft hand based on pneumatic actuation. The RBO Hand 3 is designed to enable dexterous manipulation, to facilitate transfer of insights about human dexterity, and to serve as a robust research platform for extensive real-world experiments. It achieves these design goals by co...
Soft robotics is an emerging field that yields promising results for tasks that require safe and robust interactions with the environment or with humans, such as grasping, manipulation, and human-robot interaction. Soft robots rely on intrinsically compliant components and are difficult to equip with traditional, rigid sensors which would interfere...
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning methods to a particular problem set has become an established and valuable modus operandi to advance a particular field. In this article we argue that such an approach does no...
In the original publication of the article, the incorrect author photo was displayed in biography section.
In this work, we investigate the behavior of artificial hands under impulsive load conditions. Resilience to impacts has been seldom considered in grasp and manipulation literature and benchmarks, although it is one of the most relevant issues in a number of applications involving physical interactions with unstructured environments, in prosthetic...
We introduce Recurrent State Representation Learning (RSRL) to tackle the problem of state representation learning in robotics for partially observable environments. To learn low-dimensional state representations, we combine a Long Short Term Memory network with robotic priors. RSRL introduces new priors with landmarks and combines them with existi...
Reports on events, meetings, and activities that were part of the 2019 IEEE International Conference on Robotics and Automation (ICRA).
We present online multi-modal perception systems for extracting kinematic and dynamic models of articulated objects from physical interactions with the environment. The systems rely on a RGB-D stream, contact wrenches, and proprioception. The proposed systems share an algorithmic foundation: they are based on an architecture of coupled recursive es...
We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background)....
A robot with contact sensing capability can reduce uncertainty relative to the environment by deliberately moving into contact and matching the resulting contact measurement to different possible states in the world. We present a manipulation planner that finds and sequences these actions by reasoning explicitly about the uncertainty over the robot...
Automated grasping has a long history of research that is increasing due to interest from industry. One grand challenge for robotics is Universal Picking: the ability to robustly grasp a broad variety of objects in diverse environments for applications from warehouses to assembly lines to homes. Although many researchers now openly share code and d...
We describe the winning entry to the Amazon Picking Challenge 2015. From the experience of building this system and competing in the Amazon Picking Challenge, we derive several conclusions: (1) We suggest to characterize robotic system building along four key aspects, each of them spanning a spectrum of solutions—modularity versus integration, gene...
We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background)....
Comparison of Cartesian and angular control: Supplementary material for experiments.
Formal explanation of the moving averaging computation and parameters for LQG, iLQG and MPC control strategies used in Section 4.4.
(PDF)
Comparison of Cartesian and angular control: Results from 3D experiments.
Comparison of ball catching strategies in 3D; sensitivity to individual perturbations and a combination of perturbations.
(PDF)
How to run most effectively to catch a projectile, such as a baseball, that is flying in the air for a long period of time? The question about the best solution to the ball catching problem has been subject to intense scientific debate for almost 50 years. It turns out that this scientific debate is not focused on the ball catching problem alone, b...
Proofs: Angular representations violate Markov property.
Formal proofs of the result stated in Section 4.3.8.
(PDF)
Introduction to Linear-quadratic Gaussian control.
A concise and formal introduction to Linear-Quadratic Gaussian control (LQG), including linear-quadratic regulators, Kalman filters and its nonlinear extensions iterative LQG (iLQG) and extended Kalman filters, respectively.
(PDF)
On the optimality of Chapman’s strategy: Supplementary material for experiments.
Detailed explanation of camera simulation used in Section 5, as well as how the baseline policies in this section are computed and compared to the learned policies.
(PDF)
We present differentiable particle filters (DPFs): a differentiable implementation of the particle filter algorithm with learnable motion and measurement models. Since DPFs are end-to-end differentiable, we can efficiently train their models by optimizing end-to-end state estimation performance, rather than proxy objectives such as model accuracy....
The application of deep learning in robotics leads to very specific problems and research questions that are typically not addressed by the computer vision and machine learning communities. In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning. We explain the need for better evaluati...
In many robotic applications, softness leads to improved performance, robustness, and safety, while lowering manufacturing cost, increasing versatility, and simplifying control. The advantages of soft robots derive from the fact that their behavior partially results from interactions of the robot's morphology with its environment, which is commonly...
To leverage soft hands to their full potential for grasping, we propose to design their morphology and control signals together.
Considering both parameter domains makes it easier and faster to find solutions compared to fixing parameters of either domain.
Additionally, the approach scales well to high-dimensional parameter spaces, which is a preco...
We present a novel elastic network model, lmcENM, to determine protein motion even for localized functional motions that involve substantial changes in the protein’s contact topology. Existing elastic network models assume that the contact topology remains unchanged throughout the motion and are thus most appropriate to simulate highly collective f...
Used features, supplementary tables, and figures.
Graphs for modeling physicochemical context, detailed informations about the features and their generation, tables and plots reporting supplementary performance overviews of ENM variants and the SVM, and supplementary figures.
(PDF)
Datasets, supplementary tables with raw performance data and most relevant features.
Dataset of proteins used to obtain the theoretical upper bound (mcENM), to train and test the SVM and to evaluate lmcENM, raw SVM performance data, breaking contact statistics, raw performance data of ENM variants, dataset of conformational ensembles, Top20 and Bot...
Recent approaches in robot perception follow the insight that perception is facilitated by interaction with the environment. These approaches are subsumed under the term Interactive Perception (IP). This view of perception provides the following benefits. First, interaction with the environment creates a rich sensory signal that would otherwise not...
We describe the winning entry to the Amazon Picking Challenge 2015. From the experience of building this system and competing, we derive several conclusions: (1) We suggest to characterize robotic system building along four key aspects, each of them spanning a spectrum of solutions - modularity vs. integration, generality vs. assumptions, computati...
Background:
Accurately predicted contacts allow to compute the 3D structure of a protein. Since the solution space of native residue-residue contact pairs is very large, it is necessary to leverage information to identify relevant regions of the solution space, i.e. correct contacts. Every additional source of information can contribute to narrowi...
Interactive perception methods exploit the correlation between robot actions and changes in the sensor signals to extract task-relevant information from the sensor stream. These interactions can have effects in one or multiple sensor modalities. In this work we propose an interactive perception system to build kinematic and dynamic models of articu...
Determining the structure of a protein by any method requires various contributions from experimental and computational sides. In a recent study, high-density cross-linking/mass spectrometry (HD-CLMS) data in combination with ab initio structure prediction determined the structure of human serum albumin (HSA) domains, with an RMSD to X-ray structur...
This paper presents an overview of the inaugural Amazon Picking Challenge along with a summary of a survey conducted among the 26 participating teams. The challenge goal was to design an autonomous robot to pick items from a warehouse shelf. This task is currently performed by human workers, and there is hope that robots can someday help increase e...
We assume that for perception for manipulation the relevant structure lies in the combined S ×A×t space, the space of changing sensor signals and actions. We also assume that if we can find the right structure we achieve robustness, resilience to noise and disturbances and generalization. If our hypothesis is right and S × A × t is strongly structu...
Determining the structure of a protein by any method requires varies contributions from experimental and computational sides. In a recent study, high-density cross-linking/mass spectrometry data in combination with ab initio structure prediction by conformational space search determined the structure of human serum albumin (HSA) domains, with an RM...
Hybrid methods combine experimental data and computational modeling to analyze protein structures that are elusive to structure determination. To spur the development of hybrid methods, we propose to test them in the context of the CASP experiment and would like to invite experimental groups to participate in this initiative.
This work was supported by the Alexander von Humboldt foundation through an Alexander von Humboldt professorship (funded by the German Federal Ministry of Education and Research), the Soma project (European Commission, H2020-ICT-645599), and the German Research Foundation (DFG, BR 2248/3-1) to OB, and through grants from the National Institutes of...
Recent approaches in robotics follow the insight that perception is facilitated by interactivity with the environment. These approaches are subsumed under the term of Interactive Perception (IP). We argue that IP provides the following benefits: (i) any type of forceful interaction with the environment creates a new type of informative sensory sign...
Hybrid approaches combine computational methods with experimental data. The information contained in the experimental data can be leveraged to probe the structure of proteins otherwise elusive to computational methods. Compared with computational methods, the structures produced by hybrid methods exhibit some degree of experimental validation. In s...
