direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Ph.D Theses

On Decomposability in Robot Reinforcement Learning

Bild

Sebastian Höfer, 2017

Reinforcement learning is a computational framework that enables machines to learn from trial-and-error interaction with the environment. In recent years, reinforcement learning has been successfully applied to a wide variety of problem domains, including robotics. However, the success of the reinforcement learning applications in robotics relies on a variety of assumptions, such as the availability of large amounts of training data, highly accurate models of the robot and the environment as well as prior knowledge about the task. In this thesis, we study several of these assumptions and investigate how to generalize them. To that end, we look at these assumptions from different angles. On the one hand, we study them in two concrete applications of reinforcement learning in robotics: ball catching and learning to manipulate articulated objects. On the other hand, we develop an abstract explanatory framework that relates the assumptions to the decomposability of problems and solutions. Taken together, the concrete case studies and the abstract explanatory framework enable us to make suggestions on how to relax the previously stated assumptions and how to design more effective solutions to robot reinforcement learning problems.

more to: On Decomposability in Robot Reinforcement Learning

Soft Hands For Compliant Grasping

Bild

Raphael Deimel, 2017

Raphael Deimel's thesis reconsiders hand design from the perspective of providing first and foremost robust and reliable grasping, instead of precise control of posture and simple mechanical modelabilty. This results in a fundamentally different manipulator hardware, so called soft hands, that are made out of rubber and fibers which make them highly adaptable. His thesis covers not only hand designs, but also provides an elaborate collection of methods to design, simulate and rapidly prototype soft robots, referred to as the "PneuFlex toolkit".

more to: Soft Hands For Compliant Grasping

Leveraging Novel Information Sources for Protein Structure Prediction

Bild

Michael Bohlke-Schneider, 2015

Three-dimensional protein structures are an invaluable stepping stone towards the understanding of cellular processes. Not surprisingly, state-of-the-art structure prediction methods heavily rely on information. This thesis aims to leverage new information sources: Physicochemical information encoded in predicted structure models and experimental data from high-density cross-linking / mass spectrometry (CLMS) experiments. We demonstrate that these information sources allow improved structure prediction and the reconstruction of human serum albumin domain structures from experimental data collected in its native environment, human blood serum.

more to: Leveraging Novel Information Sources for Protein Structure Prediction

Multimodal human computer interaction in virtual realities based on an exoskeleton

Bild

Ingo Kossyk, 2012

The key features of this system are a high degree of immersion into the computer generated virtual environment and a large working volume. The high degree of immersion will be achieved by multimodal human-exoskeleton interaction based on haptic effects, audio and three- dimensional visualization. The large working volume will be achieved by a lightweight wearable construction that can be carried on the back of the user.

more to: Multimodal human computer interaction in virtual realities based on an exoskeleton

Efficient Motion Planning for Intuitive Task Execution in Modular Manipulation Systems

Bild

Markus Rickert, Mai 2011

Computationally efficient motion planning mus avoid exhaustive exploration of high-dimensional configuration spaces by leveraging the structure present in real-world planning problems. We argue that this can be accomplished most effectively by carefully balancing exploration and exploitation.

Exploration seeks to understand configuration space, irrespective of the planning problem, and exploitation acts to solve the problem, given the available information obtained by exploration. We present an exploring/exploiting tree (EET) planner that balances its exploration and exploitation behavior.

The planner acquires workspace information and subsequently uses this information for exploitation in configuration space. If exploitation fails in difficult regions the planner gradually shifts to its behavior towards exploration.

more to: Efficient Motion Planning for Intuitive Task Execution in Modular Manipulation Systems

Interactive Perception of Articulated Objects for Autonomous Manipulation

Bild

Dov Katz, 2011

This thesis develops robotic skills for manipulating novel articulated objects. The degrees of freedom of an articulated object describe the relationship among its rigid bodies, and are often relevant to the object's intended function. Examples of everyday articulated objects include scissors, pliers, doors, door handles, books, and drawers. Autonomous manipulation of articulated objects is therefore a prerequisite for many robotic applications in our everyday environments.

more to: Interactive Perception of Articulated Objects for Autonomous Manipulation

Adaptive Balancing of Exploitation with Exploration to Improve Protein Structure Prediction

Bild

TJ Brunette, 2011

The most significant impediment for protein structure prediction is the inadequacy of conformation space search. Conformation space is too large and the energy landscape too rugged for existing search methods to consistently find near-optimal minima.

more to: Adaptive Balancing of Exploitation with Exploration to Improve Protein Structure Prediction

Exploiting Structure: A Guided Approach to Sampling-Based Robot Motion Planning

Bild

Brendan Burns, 2007

Robots already impact the way we understand our world and live our lives. However, their impact and use is limited by the skills they possess. Currently deployed autonomous robots lack the manipulation skills possessed by humans. To achieve general autonomy and applicability in the real world, robots must possess such skills.

more to: Exploiting Structure: A Guided Approach to Sampling-Based Robot Motion Planning

Diploma / Master Theses

Predicting protein contacts by combining information from sequence and physicochemistry

Bild

Kolja Stahl, February 2016

In this thesis we present a new contact predictor that combines evolutionary, sequence-based and physicochemical information. The contact predictor uses a new and refined feature set with drastically reduced dimensionality.

more to: Predicting protein contacts by combining information from sequence and physicochemistry

Force-Controlled Action Primitives for Interactive Perception

Bild

Georg Flick, Oct 2015

Interactive Perception exploits the robot capabilities to interact with the environment to reveal hidden properties, like the kinematic structures of articulated objects. However, when the robot faces a new environment, it needs to decide on how to interact to maximize the information gain based on sensor data, and use compliant controllers that allow the articulation to guide the motion...

more to: Force-Controlled Action Primitives for Interactive Perception

Increasing the Stiffness of a Pneumatic Actuator with Granular and Layer Jamming

Bild

Vincent Wall, May 2014

The ability to selectively stiffen otherwise compliant soft actuators increases their versatility and dexterity. The thesis investigates granular jamming and layer jamming as two possible methods to achieve stiffening with PneuFlex actuators, a type of soft continuum actuator. It details five designs of jamming compartments that can be attached to an actuator. The strength of the most effective prototype based on layer jamming is also validated in the context of pushing buttons.

more to: Increasing the Stiffness of a Pneumatic Actuator with Granular and Layer Jamming

Searching for objects through location reasoning in a probabilistic, relational world

Bild

Malte Lorbach, April 2014

In this thesis, we present a novel probabilistic representation for object relationships, and apply it to object search.

more to: Searching for objects through location reasoning in a probabilistic, relational world

Motion planning in dynamic environments with probabilistic connectivity roadmaps

Bild

Peter Lehner

We present an incremental method for motion generation in environments with unpredictably moving and initially unknown obstacles. The key to the method is its incremental nature: it locally augments and adapts global motion plans in response to changes in the environment, even if they significantly change the connectivity of the world.

more to: Motion planning in dynamic environments with probabilistic connectivity roadmaps

Shifting the Boundary between Planning and Control - Task-Consistent Motion Generation in Unstructured Environments

Bild

Nicolas Kuhnen, October 2012

In this thesis we present a motion generation approach that shifts the boundary between planning and control methods to generate task-consistent motion under uncertainty.

more to: Shifting the Boundary between Planning and Control - Task-Consistent Motion Generation in Unstructured Environments

Using recurring spatially contiguous substructures in the Protein Database for protein structure prediction

Bild

Mahmoud Mabrouk, 2012

In this thesis, we use sequentially non-continuous, but structurally contiguous, structural motifs in protein structure prediction more to: Using recurring spatially contiguous substructures in the Protein Database for protein structure prediction

Aligning a Sequence to Non-contiguous Sequence Fragments

Bild

Stefan Dörr

Sequence alignment methods are frequently used in protein structure prediction to identify homologous protein structures. The existing methods make local and global alignments between sequentially contiguous protein sequences. However, in our ongoing protein structure prediction research, we have a unique sequence to sequence alignment problem. The potential sequence alignments need to be made between a target sequence and the sets of sequence fragments, where the sequence fragments may not be sequentially contiguous.

more to: Aligning a Sequence to Non-contiguous Sequence Fragments

Grasping using Visual Feedback

Bild

Georg Bartels

Interactively explore and grasp real-world objects using visual feedback.

more to: Grasping using Visual Feedback

3D Perception for Grasping

Bild

Stefan Schrandt

Allow Robots to grasp unknown objects while perceive the environment and the objects with a 3D sensors.

more to: 3D Perception for Grasping

A Rendering Framework for Wearable Haptics in Large Virtual Environments

Bild

Jonas Dörr

A novel wearable haptic interface based on an exoskelett was developed at RBO.

more to: A Rendering Framework for Wearable Haptics in Large Virtual Environments

Using tree-based robot motion planning algorithms for protein loop closure

Bild

Florian Kamm

A novel approach for the protein loop closure problem inspired from robot modeling is developed using the kinematic chain representation of the loop chain and a motion planning technique.

more to: Using tree-based robot motion planning algorithms for protein loop closure

Simulating Physical Dynamics of Virtual Objects with a Wearable Haptic Interface

Bild

Lars Raschendörfer

Haptic devices enhance the range of multi-modal interaction in virtual reality environments. With the wearable haptic device, developed at the RBO Lab, this interaction is not limited to a small workspace any longer. The wider range of motion allows for new application scenarios.

more to: Simulating Physical Dynamics of Virtual Objects with a Wearable Haptic Interface

Evaluation of Three Sensor Technologies for Use in Soft Robot Fingers

Bild

Stefan Schirmeister, März 2016.

Sensing for soft continuum actuators as a necessary technology has emerged recently with the development of so called soft hands, which exploit the high deformability of soft structures and materials. Unfortunately, soft, stretchable sensors capable of withstanding a stretch of 100% are commercially not available. At the same time their tight integration into actuators is required to address the specific challenges of continuously deforming actuators. The thesis evaluates three potential sensor technologies for their suitability in soft hands. The thesis investigates their robustness, ease of use, long term stability and responsiveness with respect to the intended application in soft hands.

more to: Evaluation of Three Sensor Technologies for Use in Soft Robot Fingers

Bachelor Theses

Characterizing PneuFlex Actuator Deformations Using Liquid Metal Strain Sensors

Bild

Gabriel Zöller, August 2016

Deformations of soft actuators contain valuable information about their interactions with the environment. This thesis develops a methodical approach to enable limited shape sensing of the PneuFlex actuator used for the RBO Hand 2. more to: Characterizing PneuFlex Actuator Deformations Using Liquid Metal Strain Sensors

Position-Based Servoing via Probabilistic Part-Based Object Models

Bild

Manuel Wöllhaf, January 2015

To extend the field of application of robots in unstructured environments it is necessary to develop new techniques of environment perception and interpretation. These methods must give machines the capability to generate sufficient information, which enables them to fulfil their tasks with the aid of their sensors. Therefore it is required to extract local and task dependent invariant structure out of the unstructured environment. more to: Position-Based Servoing via Probabilistic Part-Based Object Models

Three dimensional Joint Detection

Bild

Andreas Orthey, September 2012

Enable a robot to infer the type of joint between moving clusters of 3d features. This can further be used to build a kinematic structure of an observed object. more to: Three dimensional Joint Detection

Extended Visual Servoing for Manipulation

Bild

Sebastian Koch, February 2011

The interest in robots that are able to act in unstructured environments is increasing. more to: Extended Visual Servoing for Manipulation

A Practical Guide to Transformed Predictive State Representations

Bild

Niklas Gebauer, September 2015

Predictive state representations (PSRs) are gaining a lot of attention in the robotics community lately because, in theory, they promise a powerful model that might be learned directly from data. But the practical application of PSRs remains a difficult procedure. In this practical guide we aim to ease and encourage practical work with PSRs. more to: A Practical Guide to Transformed Predictive State Representations

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe