Task-level imitation learning using variance-based movement optimization
Manuel Mühlig,Michael Gienger,Sven Hellbach,Jochen J. Steil,Christian Goerick +4 more
- pp 1635-1642
Reads0
Chats0
TLDR
An imitation learning framework is presented, which allows the robot to learn the important elements of an observed movement task by application of probabilistic encoding with Gaussian Mixture Models and shows that the proposed system is suitable for transferring information from a human demonstrator to the robot.Abstract:
Recent advances in the field of humanoid robotics increase the complexity of the tasks that such robots can perform. This makes it increasingly difficult and inconvenient to program these tasks manually. Furthermore, humanoid robots, in contrast to industrial robots, should in the distant future behave within a social environment. Therefore, it must be possible to extend the robot's abilities in an easy and natural way. To address these requirements, this work investigates the topic of imitation learning of motor skills. The focus lies on providing a humanoid robot with the ability to learn new bi-manual tasks through the observation of object trajectories. For this, an imitation learning framework is presented, which allows the robot to learn the important elements of an observed movement task by application of probabilistic encoding with Gaussian Mixture Models. The learned information is used to initialize an attractor-based movement generation algorithm that optimizes the reproduced movement towards the fulfillment of additional criteria, such as collision avoidance. Experiments performed with the humanoid robot ASIMO show that the proposed system is suitable for transferring information from a human demonstrator to the robot. These results provide a good starting point for more complex and interactive learning tasks.read more
Citations
More filters
Journal ArticleDOI
Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models
TL;DR: A learning method is proposed, which is called Stable Estimator of Dynamical Systems (SEDS), to learn the parameters of the DS to ensure that all motions closely follow the demonstrations while ultimately reaching and stopping at the target.
Journal ArticleDOI
Learning and Reproduction of Gestures by Imitation
TL;DR: An approach based on HMM, GMR, and dynamical systems to allow robots to acquire new skills by imitation was presented and evaluated and applications on different kinds of robots were presented to highlight the flexibility of the proposed approach.
Journal ArticleDOI
Robot Learning from Demonstration in Robotic Assembly: A Survey
Zuyuan Zhu,Huosheng Hu +1 more
TL;DR: The main focus is placed on how to demonstrate the example behaviors to the robot in assembly operations, and how to extract the manipulation features for robot learning and generating imitative behaviors.
Proceedings ArticleDOI
Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification
TL;DR: In this paper, the authors present a data-driven approach that synthesizes anticipatory knowledge of both human motions and subsequent action steps in order to predict in real-time the intended target of a human performing a reaching motion.
Proceedings ArticleDOI
Robot Programming by Demonstration with Interactive Action Visualizations
TL;DR: This work proposes an alternative PbD framework that involves demonstrating the task once and then providing additional task information explicitly, through interactions with a visualization of the action, and presents a simple action representation that supports this framework.
References
More filters
Journal ArticleDOI
Estimating the Dimension of a Model
TL;DR: In this paper, the problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion.
Estimating the dimension of a model
TL;DR: In this paper, the problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion.
Journal ArticleDOI
On Learning, Representing, and Generalizing a Task in a Humanoid Robot
TL;DR: A programming-by-demonstration framework for generically extracting the relevant features of a given task and for addressing the problem of generalizing the acquired knowledge to different contexts is presented.
Everything you know about Dynamic Time Warping is Wrong
TL;DR: The Dynamic Time Warping distance measure is a technique that has long been known in speech recognition community and has been applied to a variety of problems in various disciplines, particularly in the last three years.
Journal ArticleDOI
Embodied Symbol Emergence Based on Mimesis Theory
TL;DR: A mathematical model based on hidden Markov models is proposed in order to integrate four abilities: (1) symbol emergence; (2) behavior recognition; (3) self-behavior generation; (4) acquiring the motion primitives.