scholarly journals Robot Learning from Demonstration Using Predictive Sequence Learning

10.5772/26165 ◽  
2012 ◽  
Author(s):  
Erik Billing ◽  
Thomas Hellstrm ◽  
Lars-Erik Janlert
Keyword(s):  
Sequence Learning ◽  
Robot Learning ◽  
Learning From Demonstration

scholarly journals Mirroring without Overimitation: Learning Functionally Equivalent Manipulation Actions

2019 ◽  
Vol 33 ◽  
pp. 8025-8033 ◽  
Author(s):  
Hangxin Liu ◽  
Chi Zhang ◽  
Yixin Zhu ◽  
Chenfanfu Jiang ◽  
Song-Chun Zhu
Keyword(s):  
Mirror Neurons ◽  
Haptic Feedback ◽  
Robot Learning ◽  
Learning From Demonstration ◽  
Fine Grained ◽  
Model Free ◽  
Simulation Engine ◽  
State Changes ◽  
Manipulation Task ◽  
Physics Based Simulation

This paper presents a mirroring approach, inspired by the neuroscience discovery of the mirror neurons, to transfer demonstrated manipulation actions to robots. Designed to address the different embodiments between a human (demonstrator) and a robot, this approach extends the classic robot Learning from Demonstration (LfD) in the following aspects:i) It incorporates fine-grained hand forces collected by a tactile glove in demonstration to learn robot’s fine manipulative actions; ii) Through model-free reinforcement learning and grammar induction, the demonstration is represented by a goal-oriented grammar consisting of goal states and the corresponding forces to reach the states, independent of robot embodiments; iii) A physics-based simulation engine is applied to emulate various robot actions and mirrors the actions that are functionally equivalent to the human’s in the sense of causing the same state changes by exerting similar forces. Through this approach, a robot reasons about which forces to exert and what goals to achieve to generate actions (i.e., mirroring), rather than strictly mimicking demonstration (i.e., overimitation). Thus the embodiment difference between a human and a robot is naturally overcome. In the experiment, we demonstrate the proposed approach by teaching a real Baxter robot with a complex manipulation task involving haptic feedback—opening medicine bottles.

Robot Learning from Demonstration Using 3D Computer Vision

2014 ◽  
Vol 875-877 ◽  
pp. 1994-1999
Author(s):  
James Aaron Debono ◽  
Gu Fang
Keyword(s):  
Object Recognition ◽  
Recognition Accuracy ◽  
Robot Learning ◽  
Learning From Demonstration ◽  
State Machines ◽  
Linear Motion ◽  
3D Computer Vision ◽  
Single Frame ◽  
Pick And Place ◽  
Finite State

For robot application to proliferate in industry, and in unregulated environments, a simple means of programming is required. This paper describes methods for robot Learning from Demonstration (LfD). These methods used an RGB-D sensor for demonstration observation, and used finite state machines (FSMs) for policy derivation. Particularly, a method for object recognition was developed, which required only a single frame of data for training, and was able to perform real-time recognition. A planning method for object grasping was also developed. Experiments with a pick-and-place robot show that the developed methods resulted in object recognition accuracy greater than 99% in cluttered scenes, and manipulation accuracies of below 3mm in linear motion and 2° in rotation.

Task-Level Learning from Demonstration and Generation of Action Examples for Hierarchical Control Structure

2014 ◽  
Vol 565 ◽  
pp. 194-197
Author(s):  
Anna Gorbenko
Keyword(s):  
Polynomial Time ◽  
Control Structure ◽  
Hierarchical Control ◽  
Polynomial Time Algorithm ◽  
Time Algorithm ◽  
Robot Learning ◽  
Experimental Results ◽  
Learning From Demonstration ◽  
Selection Of ◽  
Task Level

We consider the problem of the task-level robot learning from demonstration. In particular, we consider a model that uses the hierarchical control structure. For this model, we propose the problem of selection of action examples. We present a polynomial time algorithm for solution of this problem. Also, we consider some experimental results for task-level learning from demonstration.

scholarly journals Robot learning from demonstration by constructing skill trees

2011 ◽  
Vol 31 (3) ◽  
pp. 360-375 ◽  
Author(s):  
George Konidaris ◽  
Scott Kuindersma ◽  
Roderic Grupen ◽  
Andrew Barto
Keyword(s):  
Robot Learning ◽  
Learning From Demonstration

scholarly journals Recent Advances in Robot Learning from Demonstration

2020 ◽  
Vol 3 (1) ◽  
pp. 297-330 ◽  
Author(s):  
Harish Ravichandar ◽  
Athanasios S. Polydoros ◽  
Sonia Chernova ◽  
Aude Billard
Keyword(s):  
Optimization Problem ◽  
Robot Learning ◽  
Robot Programming ◽  
Learning From Demonstration ◽  
Learning Methods ◽  
Ideal Behavior ◽  
The Past ◽  
Machine Learning Methods ◽  
Number Of Publications

In the context of robotics and automation, learning from demonstration (LfD) is the paradigm in which robots acquire new skills by learning to imitate an expert. The choice of LfD over other robot learning methods is compelling when ideal behavior can be neither easily scripted (as is done in traditional robot programming) nor easily defined as an optimization problem, but can be demonstrated. While there have been multiple surveys of this field in the past, there is a need for a new one given the considerable growth in the number of publications in recent years. This review aims to provide an overview of the collection of machine-learning methods used to enable a robot to learn from and imitate a teacher. We focus on recent advancements in the field and present an updated taxonomy and characterization of existing methods. We also discuss mature and emerging application areas for LfD and highlight the significant challenges that remain to be overcome both in theory and in practice.

Robot learning from demonstration

2004 ◽  
Vol 47 (2-3) ◽  
pp. 65-67 ◽  
Author(s):  
Aude Billard ◽  
Roland Siegwart
Keyword(s):  
Robot Learning ◽  
Learning From Demonstration
Sign in / Sign up

Export Citation Format

Share Document