Korssen, T, Soute, IAC Iris · TU/e Research Portal (Eindhoven University of Technology) · 2013
Dit verslag beschrijft hoe Programming by Demonstration (PbD) kan worden toegepast om een systeem met één vrijheidsgraad. PbD stelt ons in staat om een robot te programmeren door de beweging meerdere malen voor te doen. Er wordt van deze demonstratiedata een Gaussian Mixture Model (GMM) gemaakt en via Gaussian Mixture Regression (GMR) wordt een ‘geleerde’ curve bepaald. In dit verslag is gekeken naar parameters die van invloed zijn op het genereren van een nauwkeurige GMM en GMR en hoe deze parameters gekozen kunnen worden om een optimaal eindresultaat te behalen.
Cited by 0
2021
Cited by 1
Pierre Flener, Ute Schmid · Encyclopedia of Machine Learning and Data Mining · 2016
Cited by 0
Pierre Flener, Ute Schmid · Encyclopedia of Machine Learning · 2010
Cited by 0
Tessa Lau, Daniel S. Weld · 1998
(PBD) has the potential to improve the productivity of unsophisticated users, previous PBD systems have used brittle, heuristic, domain-specific approaches to execution-trace generalization.
Cited by 69Open access
Craig Nevill-manning · 1993
Programming by demonstration seeks to allow people to communicate algorithms easily to computers. The world in which the communication takes place, and the set of actions that can be performed in that world, both influence the efficiency and correctness of the transmitted algorithms, and the extent to which efficiency and correctness can be guaranteed. This paper discusses the effects of different worlds and action sets on the effectiveness of a programming by demonstration system, and examines two specific questions: what effect does the absence of programming metaphors from the action set have on the efficiency of the induced algorithm, and what effect does the introduction of variables into the action set have on the ease of algorithm induction? 1 Introduction Computers operate by executing algorithms on data. People operate by executing algorithms, in some form, on data. There are many advantages in having a computer execute an algorithm on behalf of a person. The main problem is ...
Cited by 0
2012
Cited by 44
Hollmann, Rebecca · Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) · 2007
Es wird ein Lösungsansatz zur intuitiven Programmierung von Industrierobotern mittels haptischer, graphischer und sprachlicher Interaktion vorgestellt. Es handelt sich um eine modular angelegte Programmierumgebung, sowie die Teilkomponenten Bahnprogrammierung, graphische Darstellung und Nachbearbeitung sowie Sprachinteraktion für industrielle Umgebungen.
Cited by 0
Alper Denasi, B Boudewijn Verhaar, Dragan Kostić et al. · Data Archiving and Networked Services (DANS) · 2009
The presented paper shows a pilot development of a robot ‘task programming method’. In this method, the user programs the robot task by demonstrating it (Programming by Demonstration, PbD). PbD is applied on a robotic arm with two degrees-of-freedom for programming a constrained motion task.
Cited by 12Open access
Kuncak, Viktor, Mayer, Mikael · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2013
The increasing adoption of smartphones and tablets has pro-vided tens of millions of users with substantial resources for computation, communication and sensing. The availability of these resources has a huge potential to positively trans-form our society and empower individuals. Unfortunately, although the number of users has increased dramatically, the number of developers is still limited by the high barrier that existing programming environments impose. To understand possible directions for helping end users to program, we present Pong Designer, an environment for de-veloping 2D physics games through direct manipulation of object behaviors. Pong Designer is built using Scala and runs on Android tablets with the multi-touch screen as the main input. We show that Pong Designer can create simple games in a few steps. This includes (multi-player and multi-screen) Pong, Brick Breaker, Pacman, Tilting maze. We have made an open release of Pong Designer and editable games that we created using it. This paper describes the main principles be-hind pong designer, and illustrate the process of developing and customizing behavior in this approach.
Cited by 0Open access
Krishna Kumar Narayanan, Luis Felipe Posada, Frank Hoffmann et al. · Lecture notes in computer science · 2010
Cited by 15
Tessa Lau, Lawrence Bergman, Vittorio Castelli et al. · 2004
Command-line interfaces are heavily used by system administrators to manage computer systems. Tasks performed at a command line may often be repetitive, leading to a desire for automation. However, the critical nature of system administration suggests that humans also need to supervise an automated system’s behavior. This paper presents a programming by demonstration approach to capturing repetitive commandline procedures, which is based on a machine learning technique called version space algebra. The interactive design of this learning system enables the user to supervise the system’s training process, as well as allowing the user and system to alternate control of the learned procedure’s execution.
Cited by 0
A. Billard, S. Calinon, R. Dillmann et al. · 2010
Robot programming by demonstration (PbD) has become a central topic of robotics that spans across general research areas such as humanrobot interaction, machine learning, machine vision and motor control. Robot PbD started about 30 years ago, and has grown importantly during the past decade. The rationale for moving from purely preprogrammed robots to very flexible user-based interfaces for training robots to perform a task is three-fold. First and foremost, PbD, also referred to as imitation learning, is a powerful mechanism for reducing the complexity of search spaces for learning. When observing either good or bad examples, one can reduce the search for a possible solution,
Cited by 0
A. A. Nippun Kumaar, T. S. B. Sudarshan · 2011
Programming by demonstration is an End-user development technique for teaching a computer or a robot new behavior by demonstrating the task to transfer directly instead of programming it through machine commands. In this paper we propose two new techniques to obtain the control code for a mobile robot through "programming by demonstration". Initially, a robot is controlled by a human operator who manually guides the robot through a desired path this is called teaching phase, and then the robot will navigate autonomously with taught information this is called execution phase. In contrast to traditional robot programming techniques, these methods does not require specialized technical or programming skills, but translates demonstrated behavior immediately into executable code. This has obvious implications for the widespread use of personal service robots.
Cited by 18
Prof. Dr. Norbert M. Seel · 2012
Cited by 0
José Oscar Olmedo-Aguirre, Marisol Vázquez-Tzompantzi, Giner Alor‐Hernández · Research in Computing Science · 2015
Cited by 0
Bagge Carlson, Fredrik · Lund University Publications Student Papers (Lund University) · 2013
An intuitive programming method for industrial robots is proposed and investigated. The main goal is to reduce the time required to program an industrial robot without the use of expensive reverse engineering equipment. Using a pen shaped tool and an optical tracking system, the user indicates the desired robot trajectory, whereafter a 3D scanner is used to gain knowledge of the work piece. The indicated path and 3D scan is then fused together in order to automatically generate an executable robot program.
Cited by 0Open access
Jiafan Zhang, Yue Wang, Rong Xiong · 2016
With the increasing demands in robotized production, easy programming of industrial robots becomes a keen market requirement because the traditional machine-coding level programming methods are usually time consuming, complex to handle, and high technical skill demanding. In past years, the expectation in using artificial intelligence to make robot program to be easy has led many progresses in related technologies in this area. Among them, Programming by Demonstration (PbD) is outlined, by which the robot enables to learn from observing how human performs a task, and then translate as much information as possible from the demonstration into the movement of itself in an automatic way. It frees human from coding the robot through any machine language level programming. In this work, a framework for industrial robot programming by demonstration is introduced where the perception of assembly tree, action identification and segmentation, skill sequence formulation, and robot movement mapping and optimization are included. The encouraging results in the final experiments with LEGO blocks in RobotStudio™, an industrial robot simulation environment from ABB, verify the feasibility of the proposed PbD solution.
Cited by 15
Billard, A., Calinon, S., Dillmann, R. et al. · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2008
Robot PbD started about 30 years ago, growing importantly during the past decade. The rationale for moving from purely preprogrammed robots to very flexible user-based interfaces for training the robot to perform a task is three-fold. First and foremost, PbD, also referred to as {\\em imitation learning} is a powerful mechanism for reducing the complexity of search spaces for learning. When observing either good or bad examples, one can reduce the search for a possible solution, by either starting the search from the observed good solution (local optima), or conversely, by eliminating from the search space what is known as a bad solution. Imitation learning is, thus, a powerful tool for enhancing and accelerating learning in both animals and artifacts. Second, imitation learning offers an implicit means of training a machine, such that explicit and tedious programming of a task by a human user can be minimized or eliminated (Figure \\ref{fig:what-how}). Imitation learning is thus a ``natural'' means of interacting with a machine that would be accessible to lay people. And third, studying and modeling the coupling of perception and action, which is at the core of imitation learning, helps us to understand the mechanisms by which the self-organization of perception and action could arise during development. The reciprocal interaction of perception and action could explain how competence in motor control can be grounded in rich structure of perceptual variables, and vice versa, how the processes of perception can develop as means to create successful actions. PbD promises were thus multiple. On the one hand, one hoped that it would make the learning faster, in contrast to tedious reinforcement learning methods or trials-and-error learning. On the other hand, one expected that the methods, being user-friendly, would enhance the application of robots in human daily environments. Recent progresses in the field, which we review in this chapter, show that the field has make a leap forward the past decade toward these goals and that these promises may be fulfilled very soon.
Cited by 18Open access
Nathan Pierre Deom, Olivier Brüls, Thierry Jacques · Open Repository and Bibliography (University of Liège) · 2019
The programming by demonstration is a method that allows one to register a trajectory and to reproduce it by a robot. It could be used to speed up the programming of robots using the practical skills of workers without the time consuming code development part of classical robotic applications. This article exposes a methodology based on fiducial markers and only one classical camera which is an inexpensive solution. The fiducial markers are based on binary symbols generally used for augmented reality applications. It also presents the experimental setup created at the laboratory of human motion analysis and used to analyze the repeatability and the precision of this solution. The primary results show a promising technology and following developments will be done.
Cited by 1Open access