Action Representations in Robotics.

Abstract: Understanding and defining the meaning of ``action'' is substantial for robotics research. This becomes utterly evident when aiming at equipping autonomous robots with robust manipulation skills for action execution. Unfortunately, to this day we still lack both a clear understanding of the concept of an action and a set of established criteria that ultimately characterize an action. In this survey we thus first review existing ideas and theories on the notion and meaning of action. Subsequently we discuss the role of action in robotics and attempt to give a seminal definition of action in accordance with its use in robotics research. Given this definition we then introduce a taxonomy for categorizing action representations in robotics along various dimensions. Finally, we provide a systematic literature survey on action representations in robotics where we categorize relevant literature along our taxonomy. After discussing the current state of the art we conclude with an outlook towards promising research directions.

Original publication: IJRR (open access)

Download the data as MS Excel file (50 KB): Download»

Show entries

Search:

Title	Author	Year	Perspective	Stimuli	Selective Attention	Granularity	Abstraction	Competition	Sequencing	Generalization	Motivation	Acquisition	Prediction	Exploitation	Learning	Discretization	Grounding	Associativity	Effect Correspondence	Formulation	Method	Features	Training	Evaluation	Datasets	Actions	Date Added

A biomimetic approach to robot table tennis	Mülling et al.	2011	agent	extroceptive	no	meso	atomic	no	yes	yes	not specified	Hard coded	optimization	Single-/Multi-step prediction	not specified	continuous	no	unidirectional	environment	biomimetic	FSM	points in 3D	not specified	Real Robot		tennis strokes	Aug 2018
A framework for heading-guided recognition of human activity	Rosales & Sclaroff	2003	observer	extroceptive	yes	global	atomic	no	no	yes	not specified	Demonstration	optimization	Recognition	offline	continuous	no	unidirectional	body	mathematical	EKF, PCA, EM	3D trajectories	unsupervised	Benchmark		walking, running, r.blading, biking	Aug 2018
A generative model for developmental understanding of visuomotor experience	Noda; K. Kawamoto; T. Hasuo; K. Sabe	2011	limb	extroceptive	yes	global	atomic	no	no	no	extrinsic	Exploration	classification	Effect prediction	online	continuous	no	unidirectional	both	biomimetic	HMM	appearance in the vision, motor of arm and camera	unsupervised	Simulation		reaching, interacting	Aug 2018
A Multi-Scale Hierarchical Codebook Method for Human Action Recognition in Videos Using a Single Example	Roshtkhari; M. D. Levine	2012	observer	extroceptive	no	global	atomic	no	no	yes	intrinsic	Exploration	classification	Recognition	online	not specified	not specified	not specified	not specified	mathematical	Bag of video words, Code book	STV	supervised	Benchmark	KTH, Weizmann, MSR II		Aug 2018
A New Framework for View-Invariant Human Action Recognition	Ji et al.	2010	observer	extroceptive	no	global	atomic	yes	no	yes	not specified	Demonstration	classification	Recognition	offline	continuous	no	unidirectional	body	mathematical	HMM	body key poses, contour shape features	unsupervised	Benchmark	IXMAS		Aug 2018
A new invariant descriptor for action recognition based on spherical harmonics	Razzaghi et al.	2012	observer	extroceptive	no	global	atomic	yes	no	yes	not specified	Demonstration	classification	Recognition	offline	categorical	no	unidirectional	body	mathematical	SVM, spherical harmonics	spatio-temporal volume	supervised	Benchmark	KTH, Weizmann, IXMAS, Robust		Aug 2018
A novel hierarchical Bag-of-Words model for compact action representation	Sun et al.	2016	observer	extroceptive	yes	global	atomic	no	no	yes	not specified	Ground truth	classification	Recognition	offline	categorical	no	unidirectional	body	mathematical	Hierarchical BOW, SVM	2D images	supervised	Benchmark	Hollywood2, Olympic Sports, YouTube, HMDB		Aug 2018
A Simple Ontology of Manipulation Actions Based on Hand-Object Relations	Wörgötter et al.	2013	observer	extroceptive	no	meso	atomic	no	no	yes	not specified	Demonstration	classification	Recognition	offline	categorical	no	unidirectional	environment	mathematical	SEC, Ontologies	object and hand poses	supervised	Benchmark		manipulation	Aug 2018
A Spiking Neural Network Model of Multi-modal Language Processing of Robot Instructions	Panchev	2005	agent	both	yes	global	atomic	yes	yes	yes	extrinsic	combination	regression	Single-/Multi-step prediction	offline	continuous	yes	unidirectional	body	biomimetic	Spiking Neural Network	object features, frequency map, tactile readings	unsupervised	Simulation		navigation, manipulation	Aug 2018
A sub-symbolic process underlying the usage-based acquisition of a compositional representation: Results of robotic learning experiments of goal-directed actions	Sugita; J. Tani	2008	agent	extroceptive	no	local	atomic	no	yes	yes	extrinsic	Demonstration	regression	Single-/Multi-step prediction	offline	categorical	yes	bidirectional	body	biomimetic	NN	colored patches, speed of wheel	supervised	Simulation		reaching	Aug 2018
Title	Author	Year	Perspective	Stimuli	Selective Attention	Granularity	Abstraction	Competition	Sequencing	Generalization	Motivation	Acquisition	Prediction	Exploitation	Learning	Discretization	Grounding	Associativity	Effect Correspondence	Formulation	Method	Features	Training	Evaluation	Datasets	Actions	Date Added

Showing 1 to 10 of 152 entries

First Previous1 2 3 4 5…16Next Last

Please cite as follows:
@Article{Zech-2019-IJRR,
    title = {{Action representations in robotics: A taxonomy and systematic Classification}},
    author = {Zech, Philipp and Renaudo, Erwan and Haller, Simon and Zhang, Xiang and Piater, Justus},
    journal = {{International Journal of Robotics Research}},
    year = 2019,
    publisher = {SAGE},
    doi = {10.1177/0278364919835020},
    url = {http://dx.doi.org/10.1177/0278364919835020}
}

Updates:

Initial release of this page (08/2018)
Update Publication (03/2019)