Learning, Generation and Recognition of Motions by Reference-Point-Dependent Probabilistic Models

Sugiura, Komei; Iwahashi, Naoto; Kashioka, Hideki; Nakamura, Satoshi

doi:10.1163/016918611x563328

Cited by 35 publications

(30 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An option is to encode both static and dynamic features in the mixture model to retrieve continuous behaviors [51,39,22]. An alternative option is to encode time as additional feature in the GMM, and use Gaussian mixture regression (GMR) [18] to retrieve continuous behaviors.…”

Section: Example With a Single Gaussianmentioning

confidence: 99%

Robot Learning with Task-Parameterized Generative Models

Calinon

2017

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

Task-parameterized models provide a representation of movement/behavior that can adapt to a set of task parameters describing the current situation encountered by the robot, such as location of objects or landmarks in its workspace. This paper gives an overview of the taskparameterized Gaussian mixture model (TP-GMM) presented in previous publications, and introduces a number of extensions and ongoing challenges required to move the approach toward unconstrained environments. In particular, it discusses its generalization capability and the handling of movements with a high number of degrees of freedom. It then shows that the method is not restricted to movements in task space, but that it can also be exploited to handle constraints in joint space, including priority constraints.

show abstract

Section: Example With a Single Gaussianmentioning

confidence: 99%

Robot Learning with Task-Parameterized Generative Models

Calinon

2017

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…In speech processing, these parameters usually correspond to the evolution of mel-frequency cepstral coefficients characterizing the power spectrum of a sound, but the same approach can be used with any form of continuous signals. In robotics, this approach has rarely been exploited, at the exception of the work from Sugiura et al (2011) employing it to represent object manipulation movements. We take advantage of this formulation for retrieving a reference trajectory with associated covariance that will govern the robot motions according to the behavior determined by the ADHSMM.…”

Section: Trajectory Retrieval Using Dynamic Featuresmentioning

confidence: 99%

Learning Controllers for Reactive and Proactive Behaviors in Human–Robot Collaboration

2016

View full text Add to dashboard Cite

Designed to safely share the same workspace as humans and assist them in various tasks, the new collaborative robots are targeting manufacturing and service applications that once were considered unattainable. The large diversity of tasks to carry out, the unstructured environments, and the close interaction with humans call for collaborative robots to seamlessly adapt their behaviors, so as to cooperate with the users successfully under different and possibly new situations (characterized, for example, by positions of objects/landmarks in the environment or by the user pose). This paper investigates how controllers capable of reactive and proactive behaviors in collaborative tasks can be learned from demonstrations. The proposed approach exploits the temporal coherence and dynamic characteristics of the task observed during the training phase to build a probabilistic model that enables the robot to both react to the user actions and lead the task when needed. The method is an extension of the hidden semi-Markov model where the duration probability distribution is adapted according to the interaction with the user. This adaptive duration hidden semi-Markov model (ADHSMM) is used to retrieve a sequence of states governing a trajectory optimization that provides the reference and gain matrices to the robot controller. A proof-of-concept evaluation is first carried out in a pouring task. The proposed framework is then tested in a collaborative task using a 7-DOF backdrivable manipulator.

show abstract

“…There has been a lot of work in the field of intelligent systems on developing formalisms for learning and representing actions, ranging from task-space representations [1] to high-level symbolic description of actions and their effects on objects [2]. Many approaches work directly on raw video streams, which is a challenging problem due to high variance in the video emanating from e.g.…”

Section: Related Workmentioning

confidence: 99%

Comparing Hidden Markov Models and Long Short Term Memory Neural Networks for Learning Action Representations

Panzner

Cimiano

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we are concerned with learning models of actions and compare a purely generative model based on Hidden Markov Models to a discriminatively trained recurrent LSTM network in terms of their properties and their suitability to learn and represent models of actions. Specifically we compare the performance of the two models regarding the overall classification accuracy, the amount of training sequences required and how early in the progression of a sequence they are able to correctly classify the corresponding sequence. We show that, despite the current trend towards (deep) neural networks, traditional graphical model approaches are still beneficial under conditions where only few data points or limited computing power is available.

show abstract

Learning, Generation and Recognition of Motions by Reference-Point-Dependent Probabilistic Models

Cited by 35 publications

References 17 publications

Robot Learning with Task-Parameterized Generative Models

Robot Learning with Task-Parameterized Generative Models

Learning Controllers for Reactive and Proactive Behaviors in Human–Robot Collaboration

Comparing Hidden Markov Models and Long Short Term Memory Neural Networks for Learning Action Representations

Contact Info

Product

Resources

About