Learning position and orientation dynamics from demonstrations via contraction analysis

Ravichandar, Harish; Dani, Ashwin P.

doi:10.1007/s10514-018-9758-x

Cited by 24 publications

(20 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, [13], [14] can only adapt quaternions towards a new target with zero angular velocity due to the spring-damper dynamics that is inherited from the original DMP. Similar issue also arises in the contracting dynamics model [15]. Another solution of learning orientation was proposed in [16], where GMM was employed to model the distribution of quaternion displacements so as to avoid the quaternion constraint.…”

Section: Introductionmentioning

confidence: 95%

“…As an effective way to represent orientation in task space, quaternions have been studied extensively, e.g., [1], [13], [14], [15], [16], [17]. However, due to the unit norm constraint, the direct probabilistic modeling of quaternion trajectories becomes intractable.…”

Section: Learning Probabilistic Orientation Trajectoriesmentioning

confidence: 99%

“…Now, the desired quaternion statesD q can be transformed intoD (15) and (19), which can be further rewritten…”

Section: A Transform Desired Quaternion Statesmentioning

confidence: 99%

“…If we consider the problem of adapting quaternions and angular velocities to pass through arbitrary desired points (e.g., via-point and end-point), no previous work in the scope of imitation learning (e.g., [1], [12], [13], [14], [15], [16], [17]) provides an all-encompassing solution. In addition, as suggested in [7], [18], probability distributions of multiple demonstrations could facilitate learning of important motion features and the design of optimal controllers [19], [20], [21].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Generalized Orientation Learning in Robot Task Space

Huang

Abu‐Dakka

Silvério

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

In the context of imitation learning, several approaches have been developed so as to transfer human skills to robots, with demonstrations often represented in Cartesian or joint space. While learning Cartesian positions suffices for many applications, the end-effector orientation is required in many others. However, several crucial issues arising from learning orientations have not been adequately addressed yet. For instance, how can demonstrated orientations be adapted to pass through arbitrary desired points that comprise orientations and angular velocities? In this paper, we propose an approach that is capable of learning multiple orientation trajectories and adapting learned orientation skills to new situations (e.g., via-point and end-point), where both orientation and angular velocity are addressed. Specifically, we introduce a kernelized treatment to alleviate explicit basis functions when learning orientations. Several examples including comparison with the state-of-the-art dynamic movement primitives are provided to verify the effectiveness of our method.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Learning Probabilistic Orientation Trajectoriesmentioning

confidence: 99%

“…Now, the desired quaternion statesD q can be transformed intoD (15) and (19), which can be further rewritten…”

Section: A Transform Desired Quaternion Statesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generalized Orientation Learning in Robot Task Space

Huang

Abu‐Dakka

Silvério

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…Existing work in trajectory-based LfD has contributed a wide range of mathematical representations that encode skills from human demonstrations and then reproduce the learned skills at runtime. Proposed representations include Spring-damper systems with forcing functions [3], Gaussian Mixture Models (GMMs) [4]- [6], Neural Networks (NNs) [7], [8], Gaussian Processes (GPs) [9]- [11], and geometric objects [12], among others. Each of these representations is used to encode the demonstrations in a predefined space or coordinate system (e.g., Cartesian coordinates).…”

Section: Introductionmentioning

confidence: 99%

Skill Acquisition via Automated Multi-Coordinate Cost Balancing

Ravichandar

Ahmadzadeh

Rana

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We propose a learning framework, named Multi-Coordinate Cost Balancing (MCCB), to address the problem of acquiring point-to-point movement skills from demonstrations. MCCB encodes demonstrations simultaneously in multiple differential coordinates that specify local geometric properties. MCCB generates reproductions by solving a convex optimization problem with a multi-coordinate cost function and linear constraints on the reproductions, such as initial, target, and via points. Further, since the relative importance of each coordinate system in the cost function might be unknown for a given skill, MCCB learns optimal weighting factors that balance the cost function. We demonstrate the effectiveness of MCCB via detailed experiments conducted on one handwriting dataset and three complex skill datasets.

show abstract

Image-Based Estimation for Robotics and Autonomous Systems

Dani¹

2020

Encyclopedia of Systems and Control

View full text Add to dashboard Cite

Learning position and orientation dynamics from demonstrations via contraction analysis

Cited by 24 publications

References 41 publications

Generalized Orientation Learning in Robot Task Space

Generalized Orientation Learning in Robot Task Space

Skill Acquisition via Automated Multi-Coordinate Cost Balancing

Image-Based Estimation for Robotics and Autonomous Systems

Contact Info

Product

Resources

About