A novel DMP formulation for global and frame independent spatial scaling in the task space

Koutras, Leonidas; Doulgeri, Zoe

doi:10.1109/ro-man47096.2020.9223500

Cited by 19 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original DMPs allow translation and scaling of the trajectory, but the rotation in space causes distortion of its shape, because its nonlinearity in the three directions in space is learned separately and performed separately. To solve this problem, Koutras and Doulgeri (2020) modified the original DMPs, which allows the trajectory to be arbitrarily rotated, translated and scaled in space while keeping the shape unchanged. Si et al (2021a) further proposed the following forms of DMPs: This is the representation of a three-dimensional trajectory, where f(s) is the same as the original DMPs, obtained by the demonstration trajectory, and s g is the proportional coefficient, which can be obtained by the following formula: where g and bold-italicxbold-italic0 are the end point and start point of the demonstration trajectory, respectively, and bold-italicgbold-italicd and bold-italicx0,d are the end point and start point of the recreation trajectory, respectively.…”

Section: Methodsmentioning

confidence: 99%

A novel human-robot skill transfer method for contact-rich manipulation task

Dong

Yang

2023

RIA

View full text Add to dashboard Cite

Purpose The purpose of this paper is to enhance the robot’s ability to complete multi-step contact tasks in unknown or dynamic environments, as well as the generalization ability of the same task in different environments. Design/methodology/approach This paper proposes a framework that combines learning from demonstration (LfD), behavior tree (BT) and broad learning system (BLS). First, the original dynamic motion primitive is modified to have a better generalization ability for representing motion primitives. Then, a BT based on tasks is constructed, which will select appropriate motion primitives according to the environment state and robot ontology state, and then the BLS will generate specific parameters of the motion primitives based on the state. The weights of the BLS can also be optimized after each successful execution. Findings The authors carried out the tasks of cleaning the desktop and assembling the shaft hole on Baxter and Elite robots, respectively, and both tasks were successfully completed, which proved the effectiveness of the framework. Originality/value This paper proposes a framework that combines LfD, BT and BLS. To the best of the authors’ knowledge, no similar methods were found in other people’s work. Therefore, the authors believe that this work is original.

show abstract

Section: Methodsmentioning

confidence: 99%

A novel human-robot skill transfer method for contact-rich manipulation task

Dong

Yang

2023

RIA

View full text Add to dashboard Cite

show abstract

“…For producing λ tar , the dynamical systems including external wrenches with learned weights are numerically solved, resulting in a continuous model representation in SE(3). In our work, we applied the revised bio-inspired formulation by Koutras et al [23], [24]. For an in-depth explanation of DMPs see [25].…”

Section: Task Modelmentioning

confidence: 99%

“…1). For encoding and reproducing demonstrated motions, we use Cartesian space Dynamic Movement Primitives (CDMPs) [23] which facilitate a common representation space.…”

Section: Introductionmentioning

confidence: 99%

Guided Learning from Demonstration for Robust Transferability

Sukkar¹,

Moreno²,

Vidal-Calleja³

et al. 2023

Preprint

View full text Add to dashboard Cite

Learning from demonstration (LfD) has the potential to greatly increase the applicability of robotic manipulators in modern industrial applications. Recent progress in LfD methods have put more emphasis in learning robustness than in guiding the demonstration itself in order to improve robustness. The latter is particularly important to consider when the target system reproducing the motion is structurally different to the demonstration system, as some demonstrated motions may not be reproducible. In light of this, this paper introduces a new guided learning from demonstration paradigm where an interactive graphical user interface (GUI) guides the user during demonstration, preventing them from demonstrating non-reproducible motions. The key aspect of our approach is determining the space of reproducible motions based on a motion planning framework which finds regions in the task space where trajectories are guaranteed to be of bounded length. We evaluate our method on two different setups with a six-degree-of-freedom (DOF) UR5 as the target system. First our method is validated using a seven-DOF Sawyer as the demonstration system. Then an extensive user study is carried out where several participants are asked to demonstrate, with and without guidance, a mock weld task using a hand held tool tracked by a VICON system. With guidance users were able to always carry out the task successfully in comparison to only 44% of the time without guidance.

show abstract

“…Moreover e a = 0 implies = 0, (which in turn implies Q = Q d ) or η = 0; when η = 0 ( θ = −π), = 0 and hence Q does not track Q d . The logarithmic error ( 25) is gaining popularity in recent research works [16]- [19] as it offers a more mathematically sound approach utilizing the Lie Algebra of S 3 by employing the distance preserving logarithmic mapping.…”

Section: Tracking Control Variantsmentioning

confidence: 99%

Exponential stability of trajectory tracking control in the orientation space utilizing unit quaternions

Koutras

Doulgeri

2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Trajectory tracking in the orientation space utilizing unit quaternions yields non linear error dynamics as opposed to Cartesian position. In this work, we study trajectory tracking in the orientation space utilizing the most popular quaternion error representations and angular velocity errors. By selecting error functions carefully we show exponential convergence in a region of attraction containing large initial errors. We further show that under certain conditions frequently encountered in practice, the formulation respecting the geometric characteristics of the quaternion manifold and its tangent space yields linear tracking dynamics allowing us to guarantee a desired tracking performance by gain selection without tuning. Simulation and experimental results are provided.

show abstract

A novel DMP formulation for global and frame independent spatial scaling in the task space

Cited by 19 publications

References 21 publications

A novel human-robot skill transfer method for contact-rich manipulation task

A novel human-robot skill transfer method for contact-rich manipulation task

Guided Learning from Demonstration for Robust Transferability

Exponential stability of trajectory tracking control in the orientation space utilizing unit quaternions

Contact Info

Product

Resources

About