Learning of generalized manipulation strategies in the context of Programming by Demonstration

Jäkel, Rainer; Schmidt-Rohr, Sven R.; Lösch, Martin; Kasper, Alexander; Dillmann, Rüdiger

doi:10.1109/ichr.2010.5686305

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human demonstrations and objects [9]: chair, cup, measuring cup, bottle, cup with handle, saucer, keyboard, bottle crate, fridge consists of three subproblems: learning the network structure, automatic generation of constraints and learning the parameters, e.g. pose and limits, of constraints, see [1].…”

Section: Pbd Of Planning Models: Overviewmentioning

confidence: 99%

“…pour-in, it is impossible to capture all the variance in the task. More details are available in [1].…”

Section: Pbd Of Planning Models: Overviewmentioning

confidence: 99%

“…In the first experiment, the planning model was defined manually. In the other experiments, the planning model was learned using the algorithm in [1]. The demonstrated problems were divided into the set of tests and a validation set.…”

Section: Chosenmentioning

confidence: 99%

“…The planning models, which are composed of a large set of task constraints, are learned initially using the learning algorithm described in [1]. In contrast to [1], the human teacher demonstrates a test, e.g. different sets of object poses and states, by placing and moving the objects in a sensory environment.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Distributed generalization of learned planning models in robot programming by demonstration

Jäkel

Meißner

Schmidt-Rohr

et al. 2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

In Programming by Demonstration (PbD), one of the key problems for autonomous learning is to automatically extract the relevant features of a manipulation task, which has a significant impact on the generalization capabilities. In this paper, task features are encoded as constraints of a learned planning model. In order to extract the relevant constraints, the human teacher demonstrates a set of tests, e.g. a scene with different objects, and the robot tries to execute the planning model on each test using constrained motion planning. Based on statistics about which constraints failed during the planning process multiple hypotheses about a maximal subset of constraints, which allows to find a solution in all tests, are refined in parallel using an evolutionary algorithm. The algorithm was tested on 7 experiments and two robot systems.

show abstract

Section: Pbd Of Planning Models: Overviewmentioning

confidence: 99%

“…pour-in, it is impossible to capture all the variance in the task. More details are available in [1].…”

Section: Pbd Of Planning Models: Overviewmentioning

confidence: 99%

Section: Chosenmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Distributed generalization of learned planning models in robot programming by demonstration

Jäkel

Meißner

Schmidt-Rohr

et al. 2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Jakel et al [8] present an approach to action learning and geometric constraint learning in the context of Programming by Demonstration. After segmenting logs of human demonstrated actions, constraints on the possible motion of the robot arm are learnt.…”

Section: A Related Workmentioning

confidence: 99%

Learning operators for manipulation planning

Burbridge

Saigol

Schmidt

et al. 2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-We describe a method for learning planning operators for manipulation tasks from hand-written programs to provide a high-level command interface to a robot manipulator that allows tasks to be specified simply as goals. This is made challenging by the fact that a manipulator is a hybrid system-any model of it consists of discrete variables such as "holding cup" and continuous variables such as the poses of objects and position of the robot. The approach relies on three novel techniques: the action learning from annotated code uses simulation to find PDDL action models corresponding to code fragments. To provide the geometric information needed we use supervised learning to produce a mapping from geometric to symbolic state. The mapping can also be used in reverse to produce a geometric state that makes a set of predicates true, thus allowing desired object positions to be generated during planning. Finally, during execution of the plan we use a partially observable Markov decision problem-based planner to repair the initial plan when unforeseen geometric constraints prevent actions from being executed.

show abstract

Introduction

Meißner¹

2019

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

Learning of generalized manipulation strategies in the context of Programming by Demonstration

Cited by 11 publications

References 10 publications

Distributed generalization of learned planning models in robot programming by demonstration

Distributed generalization of learned planning models in robot programming by demonstration

Learning operators for manipulation planning

Introduction

Contact Info

Product

Resources

About