Estimation of perturbations in robotic behavior using dynamic mode decomposition

Berger, Erik; Sastuba, Mark; Vogt, David; Jung, Bernhard; Amor, Heni Ben

doi:10.1080/01691864.2014.981292

Cited by 110 publications

(62 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Owing to its applicability in modeling nonlinear systems and to its demonstrated success in analyzing complex fluid flows, DMD has gained increasing popularity in fluid mechanics and beyond. For instance, DMD has been utilized in the fields of epidemiology [7], medicine [8], neuroscience [9], power systems [10], robotics [11], sustainable buildings [10], and video processing [12].…”

Section: Introductionmentioning

confidence: 99%

De-biasing the dynamic mode decomposition for applied Koopman spectral analysis of noisy datasets

Hemati

Rowley

Deem³

et al. 2017

Theor. Comput. Fluid Dyn.

301

209

View full text Add to dashboard Cite

The Dynamic Mode Decomposition (DMD)-a popular method for performing data-driven Koopman spectral analysis-has gained increased adoption as a technique for extracting dynamically meaningful spatiotemporal descriptions of fluid flows from snapshot measurements. Often times, DMD descriptions can be used for predictive purposes as well, which enables informed decision-making based on DMD modelforecasts. Despite its widespread use and utility, DMD regularly fails to yield accurate dynamical descriptions when the measured snapshot data are imprecise due to, e.g., sensor noise. Here, we express DMD as a two-stage algorithm in order to isolate a source of systematic error. We show that DMD's first stage, a subspace projection step, systematically introduces bias errors by processing snapshots asymmetrically. To remove this systematic error, we propose utilizing an augmented snapshot matrix in a subspace projection step, as in problems of total least-squares, in order to account for the error present in all snapshots. The resulting unbiased and noise-aware total DMD (TDMD) formulation reduces to standard DMD in the absence of snapshot errors, while the two-stage perspective generalizes the de-biasing framework to other related methods as well. TDMD's performance is demonstrated in numerical and experimental fluids examples.

show abstract

Section: Introductionmentioning

confidence: 99%

De-biasing the dynamic mode decomposition for applied Koopman spectral analysis of noisy datasets

Hemati

Rowley

Deem³

et al. 2017

Theor. Comput. Fluid Dyn.

301

209

View full text Add to dashboard Cite

show abstract

“…For this, Dynamic Mode Decomposition (DMD) [7] is utilized . A detailed explanation of DMD and how it is used in the context of sensor data interpolation can be found in [8].…”

Section: A Data Acquisitionmentioning

confidence: 99%

“…, x t ). In previous work [8], the Subsequence Dynamic Time Warping technique (SDTW) [10] was used for measuring the similarity between two sequences. In the case presented here, the low dimensional sequence X is compared with the low dimensional training data in the rows of the P-FS Y =    y 1,1 · · · y 1,n .…”

Section: Phase Estimationmentioning

confidence: 99%

Experience-based torque estimation for an industrial robot

Berger

Grehl

Vogt

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Robotic manipulation tasks often require the control of forces and torques exerted on external objects. This paper presents a machine learning approach for estimating forces when no force sensors are present on the robot platform. In the training phase, the robot executes the desired manipulation tasks under controlled conditions with systematically varied parameter sets. All internal sensor data, in the presented case from more than 100 sensors, as well as the force exerted by the robot are recorded. Using Transfer Entropy, a statistical model is learned that identifies the subset of sensors relevant for torque estimation in the given task. At runtime, the model is used to accurately estimate the torques exerted during manipulations of the demonstrated kind. The feasibility of the approach is shown in a setting where a robotic manipulator operates a torque wrench to fasten a screw nut. Torque estimates with an accuracy of well below ±1 N m are achieved. A strength of the presented model is that no prior knowledge of the robot's kinematics, mass distribution or sensor instrumentation is required.

show abstract

“…In addition, nonlinearities underlying the current robot or task can often lead to instabilities in the system [21]. To circumvent such challenges, several approaches have been proposed for learning perturbation filters using a datadriven machine learning method [3,4,5]. An alternative, bio-inspired approach was proposed in [19].…”

Section: Related Workmentioning

confidence: 99%

Robots that anticipate pain: Anticipating physical perturbations from visual cues through deep predictive models

Sur

Amor

2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

To ensure system integrity, robots need to proactively avoid any unwanted physical perturbation that may cause damage to the underlying hardware. In this thesis work, we investigate a machine learning approach that allows robots to anticipate impending physical perturbations from perceptual cues. In contrast to other approaches that require knowledge about sources of perturbation to be encoded before deployment, our method is based on experiential learning. Robots learn to associate visual cues with subsequent physical perturbations and contacts. In turn, these extracted visual cues are then used to predict potential future perturbations acting on the robot. To this end, we introduce a novel deep network architecture which combines multiple subnetworks for dealing with robot dynamics and perceptual input from the environment.We present a self-supervised approach for training the system that does not require any labeling of training data. Extensive experiments in a human-robot interaction task show that a robot can learn to predict physical contact by a human interaction partner without any prior information or labeling. Furthermore, the network is able to successfully predict physical contact from either depth stream input or traditional video input or using both modalities as input.

show abstract

Estimation of perturbations in robotic behavior using dynamic mode decomposition

Cited by 110 publications

References 27 publications

De-biasing the dynamic mode decomposition for applied Koopman spectral analysis of noisy datasets

De-biasing the dynamic mode decomposition for applied Koopman spectral analysis of noisy datasets

Experience-based torque estimation for an industrial robot

Robots that anticipate pain: Anticipating physical perturbations from visual cues through deep predictive models

Contact Info

Product

Resources

About