Superpositioning of behaviors learned through teleoperation

Campbell, C.L.; Peters, Richard Alan; Bodenheimer, Robert E.; Bluethmann, William; Huber, Eric; Ambrose, Robert O.

doi:10.1109/tro.2005.861485

Cited by 26 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because their robot did not have a hand, they caught the ball with a funnel; thus exact orienting of the end-effector was not required for grasping. Another approach to generate human-like trajectories is to teach the robot via teleoperation, as successfully realized by Campbell et al [3]. Here we set out to further identify characteristics of human catching movements, in the context of current theories of human motor control.…”

Section: Introductionmentioning

confidence: 99%

Minimum jerk for human catching movements in 3D

Fligge¹,

McIntyre²,

Smagt³

2012

2012 4th IEEE RAS &Amp; EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

View full text Add to dashboard Cite

Abstract-To investigate fast human reaching movements in 3D, we asked 11 right-handed persons to catch a tennis ball while we tracked the movements of their arms. To ensure consistent trajectories of the ball, we used a catapult to throw the ball from three different positions. Tangential velocity profiles of the hand were in general bell-shaped and hand movements in 3D coincided with well known results for 2D point-to-point movements such as minimum jerk theory or the 2/3rd power law. Furthermore, two phases, consisting of fast reaching and slower fine movements at the end of hand placement could clearly be seen. The aim of this study was to find a way to generate human-like (catching) trajectories for a humanoid robot.

show abstract

Section: Introductionmentioning

confidence: 99%

Minimum jerk for human catching movements in 3D

Fligge¹,

McIntyre²,

Smagt³

2012

2012 4th IEEE RAS &Amp; EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

View full text Add to dashboard Cite

show abstract

“…Later it was shown that sets of such learned trajectories could be interpolated to provide intermediate results [3]. The formation of low dimensional manifolds in the Robonaut SMSS as a consequence of task repetition was reported in [4].…”

Section: Previous Workmentioning

confidence: 99%

“…That classifier had 73% accuracy when applied to the vectors in the 7 trials not used for model, viz. 3,6,7,8,9,11, and 12, with trials 3 and 11 the successful ones. Fig.…”

Section: Manifold Learningmentioning

confidence: 99%

Sensory-Motor Manifold Structure Induced by Task Outcome: Experiments with Robonaut

Peters

Bodenheimer

Jenkins

2006

2006 6th IEEE-RAS International Conference on Humanoid Robots

View full text Add to dashboard Cite

Abstract-Experiments were performed with Robonaut to determine if repeated teleoperation through a task could delineate a manifold in the robot's sensory-motor state-space (SMSS) that was separable by the outcome of the task. A teleoperator guided the robot through 13 trials of a pick and place task. By design, in 5 of the trials were successful and 8 were not. A time series of instantaneous sensory-motor state vectors was recorded at 8Hz from the robot throughout the trials. Support Vector Machine (SVM) analysis suggested that the individual vectors were separable with a 70% probability if both sensory and motor information were used. The analysis revealed, however, little structural information beyond the promise of reasonable separability. Therefore, dimensionality reduction techniques were applied. These embed high-dimensional vectors into a lower dimensional space where patterns may be discernible. Singular Value Decomposition, Multidimensional Scaling, and SpatioTemporal Isomap (STI) analysis of the time series revealed a 3D structure within the SMSS that was dependent on, and separable by task outcome. An STI embedding generated by 2 successful and 4 unsuccessful trials was seen to be sufficient for the projection and classification of the remaining trials. A comparison of that result with the SVM classification demonstrated that STI outperformed SVM. It is conjectured that STI's reliance on the temporal evolution of the time-series gave it the advantage over the SVM analysis which was time independent. It was also found that Robonaut's haptic sensory data degraded the outcome separability if used without processing. However, lateral inhibition of the haptic signals significantly enhanced separability in both the SVM and STI analyses.

show abstract

“…A taxonomy of task-parameterized models is presented in [8], classifying existing methods in three broad cate-gories: 1) Approaches employing M models for the M demonstrations, performed in M different situations, see e.g. [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.…”

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

Superpositioning of behaviors learned through teleoperation

Cited by 26 publications

References 18 publications

Minimum jerk for human catching movements in 3D

Minimum jerk for human catching movements in 3D

Sensory-Motor Manifold Structure Induced by Task Outcome: Experiments with Robonaut

Robot Learning with Task-Parameterized Generative Models

Contact Info

Product

Resources

About