On Decomposability in Robot Reinforcement Learning
- © S. Höfer
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
- © RBO
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
- © Robotics
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
Efficient Motion Planning for Intuitive Task Execution in Modular Manipulation Systems
- © RBO
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
Hi, I have IELTS in a week, last time i scored 6.5 in writing. However I have to score 7. Im glad if you help me by giving your valuable points.
Topic: Technology is becoming increasingly prevalent in the world today. Given time, technology will completely replace the teacher in the classroom. Do you agree or disagree with this statement?
In today's world, the use of technology is ever increasing. Even in classrooms,technology can be commonly seen.It is disagreed that technology will completely replace the real teacher in a classroom. It is shown by analyzing the inability of a robotic teacher to discipline a misbehaving student in a classroom as well as a robotic teacher hindrance to the learning process of a student.
To begin with, a teacher powered by artificial intelligence would have little or no control over it's students.For example,it is commonly understood that children require the watchful eye of a teacher to ensure that they are Indeed doing their classwork,instead of fooling around during class time. Unfortunately this is something that a technology driven teacher simply cannot provide. Thus,this makes it clear why technology will never completely replace a teacher in the classroom.
Secondly, a robotic teacher would disrupt a student's learning process and in effect slow the ability of a student to absorb the information from the lessons. For instance, kids require motivation to be taught effectively. Such is a quality a human teacher possess but a technology driven instructor do not. From this it becomes quite evident that robotic instructor will never take the place of a real teacher in a classroom.
To summarize, a robotic teacher lacks the discipline needed to instruct students properly and actually operates to retard the student ability to learn new information. Thus it is clear that why the idea of having a classroom run entirely by a machine is not supported. After analyzing this subject,it is predicted that the negative aspects of the debate over computerized teaching will forever be stronger than the positive ones and because of this, computers will never replace teachers.