Learning and Recognition of Hybrid Manipulation Motions in Variable Environments Using Probabilistic Flow Tubes

Dong, Shuonan; Williams, Brian P.

doi:10.1007/s12369-012-0155-x

Cited by 28 publications

(33 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[16,23,29,25,45,12,21]; 2) Approaches employing P models for the P frames of reference that are possibly relevant for the task, see e.g. [32,13]; 3) Approaches employing a single model whose parameters are modulated by task parameters, see e.g. [49,26,20].…”

Section: Adaptive Models Of Movementsmentioning

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: Adaptive Models Of Movementsmentioning

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

“…The generated funnels illustrate a similar representation to our approach, however, we do not require extensive off-line computation. Dong and Williams proposed probabilistic flow tubes to represent trajectories by extracting covariance data [10]. The learned flow tube consists of a spine trajectory and 2D covariance data at each corresponding time-step.…”

Section: Related Workmentioning

confidence: 99%

Generalized Cylinders for Learning, Reproduction, Generalization, and Refinement of Robot Skills

Ahmadzadeh¹,

Rana²,

Chernova³

2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-This paper presents a novel geometric approach for learning and reproducing trajectory-based skills from human demonstrations. Our approach models a skill as a Generalized Cylinder, a geometric representation composed of an arbitrary space curve called spine and a smoothly varying cross-section. While this model has been utilized to solve other robotics problems, this is the first application of Generalized Cylinders to manipulation. The strengths of our approach are the model's ability to identify and extract the implicit characteristics of the demonstrated skill, support for reproduction of multiple trajectories that maintain those characteristics, generalization to new situations through nonrigid registration, and interactive human refinement of the resulting model through kinesthetic teaching. We validate our approach through several real-world experiments with a Jaco 6-DOF robotic arm.

show abstract

“…In [2], the probabilistic flow tubes (PFT) algorithm was designed to learn and recognize (or classify) tasks demonstrated by a human operator who is physically moving the end-effector of a robotic manipulator. The main goal is to teach the robot how to execute manipulation tasks in variable environments.…”

Section: Related Workmentioning

confidence: 99%

“…Full DTW requires the complete time series to be aligned, as we do at the library stage, and runs in O(n 2 ) time and space. Then, from T t , we build a library at the motion level, L, with a probabilistic representation for each task L t based on the mean, µ, and the covariance, Σ, of all the features, as opposed to the task-level probabilistic flow tubes used in [2].…”

Section: Learning a Library Of Motionsmentioning

confidence: 99%

“…We adapt the Bayesian approach proposed in [2] to compute the probability of being in the presence of one of the motion classes t, given the partial segment of the trajectory being executed by the human f h [1 : k], as expressed en Eq.5 using the Bayes rule. We further incorporate tasklevel knowledge through the inclusion of a hyperparameter that leverages structured information from a customized task level predictor T (·), which takes the set of previous actions a and computes a distribution over the possible motion classes t.…”

Section: Time Series Classification Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification

Pérez-D’Arpino

Shah

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

126

View full text Add to dashboard Cite

Abstract-Interest in human-robot coexistence, in which humans and robots share a common work volume, is increasing in manufacturing environments. Efficient work coordination requires both awareness of the human pose and a plan of action for both human and robot agents in order to compute robot motion trajectories that synchronize naturally with human motion. In this paper, we 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. Motion-level anticipatory models are constructed using multiple demonstrations of human reaching motions. We produce a library of motions from human demonstrations, based on a statistical representation of the degrees of freedom of the human arm, using time series analysis, wherein each time step is encoded as a multivariate Gaussian distribution. We demonstrate the benefits of this approach through offline statistical analysis of human motion data. The results indicate a considerable improvement over prior techniques in early prediction, achieving 70% or higher correct classification on average for the first third of the trajectory (< 500msec).We also indicate proof-of-concept through the demonstration of a human-robot cooperative manipulation task performed with a PR2 robot. Finally, we analyze the quality of tasklevel anticipatory knowledge required to improve prediction performance early in the human motion trajectory.

show abstract

Learning and Recognition of Hybrid Manipulation Motions in Variable Environments Using Probabilistic Flow Tubes

Cited by 28 publications

References 10 publications

Robot Learning with Task-Parameterized Generative Models

Robot Learning with Task-Parameterized Generative Models

Generalized Cylinders for Learning, Reproduction, Generalization, and Refinement of Robot Skills

Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification

Contact Info

Product

Resources

About