Dynamic Movement Primitive based Motion Retargeting for Dual-Arm Sign Language Motions

Liang, Yuwei; Li, Weijie; Wang, Yue; Xiong, Rong; Mao, Yuan; Zhang, Jiafan

doi:10.1109/icra48506.2021.9561120

Cited by 17 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Dmps In Application Scenariosmentioning

confidence: 99%

“…Described approaches demonstrate that DMPs are a valuable option for gesture recognition especially for systems with limited computational power. Liang et al (2021) presented a solution to the motion retargeting problem for generating dual-arm sign language motions. Their approach involves an offline-constrained optimization technique that minimizes the deviation from trajectories generated by DMPs, which encodes the human demonstrations.…”

Section: Dmps In Application Scenariosmentioning

confidence: 99%

“…Liu et al (2020) proposed DMP-based trajectory generation to enable a full-body humanoid robot with 10-DoFs (for the two legs) to realize adaptive walking. Liang et al (2021) developed an efficient approach to enable service robots with 26 DoFs with the skill of performing sign language motions. Travers et al (2016Travers et al ( , 2018 proposed a framework that integrates DMP with Gaussian-shaped spatial activation windows in order to plan the motion for high DoF robotic systems (e.g., snake-like robot) in complex environments (with obstacles) by linking low-level controllers to highlevel planners.…”

Section: High Dof Robotsmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic movement primitives in robotics: A tutorial survey

Saveriano,

Abu-Dakka,

Kramberger

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

Biological systems, including human beings, have the innate ability to perform complex tasks in a versatile and agile manner. Researchers in sensorimotor control have aimed to comprehend and formally define this innate characteristic. The idea, supported by several experimental findings, that biological systems are able to combine and adapt basic units of motion into complex tasks finally leads to the formulation of the motor primitives’ theory. In this respect, Dynamic Movement Primitives (DMPs) represent an elegant mathematical formulation of the motor primitives as stable dynamical systems and are well suited to generate motor commands for artificial systems like robots. In the last decades, DMPs have inspired researchers in different robotic fields including imitation and reinforcement learning, optimal control, physical interaction, and human–robot co-working, resulting in a considerable amount of published papers. The goal of this tutorial survey is two-fold. On one side, we present the existing DMP formulations in rigorous mathematical terms and discuss the advantages and limitations of each approach as well as practical implementation details. In the tutorial vein, we also search for existing implementations of presented approaches and release several others. On the other side, we provide a systematic and comprehensive review of existing literature and categorize state-of-the-art work on DMP. The paper concludes with a discussion on the limitations of DMPs and an outline of possible research directions.

show abstract

Section: Dmps In Application Scenariosmentioning

confidence: 99%

Section: Dmps In Application Scenariosmentioning

confidence: 99%

Section: High Dof Robotsmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic movement primitives in robotics: A tutorial survey

Saveriano,

Abu-Dakka,

Kramberger

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…It is very effective to simplify a complicated robot motion planning problem via hierarchical RL [39]. DMP-facilitated RL has become a popular method for robot motion planning in recent work [40]- [42]. A survey on the application of DMP to robot manipulation problems is presented in [43].…”

Section: A Dynamic Movement Primitive (Dmp)mentioning

confidence: 99%

Motion generation for walking exoskeleton robot using multiple dynamic movement primitives sequences combined with reinforcement learning

Zhang

2022

Robotica

View full text Add to dashboard Cite

In order to assist patients with lower limb disabilities in normal walking, a new trajectory learning scheme of limb exoskeleton robot based on dynamic movement primitives (DMP) combined with reinforcement learning (RL) was proposed. The developed exoskeleton robot has six degrees of freedom (DOFs). The hip and knee of each artificial leg can provide two electric-powered DOFs for flexion/extension. And two passive-installed DOFs of the ankle were used to achieve the motion of inversion/eversion and plantarflexion/dorsiflexion. The five-point segmented gait planning strategy is proposed to generate gait trajectories. The gait Zero Moment Point stability margin is used as a parameter to construct a stability criteria to ensure the stability of human-exoskeleton system. Based on the segmented gait trajectory planning formation strategy, the multiple-DMP sequences were proposed to model the generation trajectories. Meanwhile, in order to eliminate the effect of uncertainties in joint space, the RL was adopted to learn the trajectories. The experiment demonstrated that the proposed scheme can effectively remove interferences and uncertainties.

show abstract

“…For the sake of whole-body stability, the waist is not convenient for teleoperation (Englsberger et al , 2014; McGill et al , 2017). A few bipedal service robots use retargeting techniques to achieve teleoperation control of both arms, legs, torso and head (Darvish et al , 2019; Koenemann et al , 2014), but retargeting techniques are more concerned with the similarity of robot and human motion and the effect of the robot’s demonstration rather than performing specific tasks (Franzese et al , 2022; Liang et al , 2021). Centaur robots, tracked robots and mobile platform robots are more stable and convenient for waist control.…”

Section: Introductionmentioning

confidence: 99%

A humanoid robot teleoperation approach based on waist–arm coordination

Fan

Shu

et al. 2023

View full text Add to dashboard Cite

Purpose In the current teleoperation system of humanoid robots, the control between arms and the control between the waist and arms are individual and lack coordinated motion. This paper aims to solve the above problem and proposes a teleoperation control approach for a humanoid robot based on waist–arm coordination (WAC). Design/methodology/approach The teleoperation approach based on WAC comprises dual-arm coordination (DAC) and WAC. The DAC method realizes the coordinated motion of both arms through one hand by establishing a mapping relationship between a single hand controller and the manipulated object; the WAC method realizes the coordinated motion of both arms and waist by calculating the inverse kinematic input of robotic arms based on the desired velocity of the waist and the end of both arms. An integrated teleoperation control framework provides interfaces for the above methods, and users can switch control modes online to adapt to different tasks. Findings After conducting experiments on the dual-arm humanoid robot through the teleoperation control framework, it was found that the DAC method can save 27.2% of the operation time and reduce 99.9% of the posture change of the manipulated object compared with the commonly used individual control. The WAC method can accomplish a task that cannot be done by individual control. The experiments proved the improvement of both methods in terms of operation efficiency, operation stability and operation capability compared with individual control. Originality/value The DAC method better maintains the constraints of both arms and the manipulated object. The WAC method better maintains the constraints of the manipulated object itself. Meanwhile, the teleoperation framework integrates the proposed methods and enriches the teleoperation modes and control means.

show abstract

Dynamic Movement Primitive based Motion Retargeting for Dual-Arm Sign Language Motions

Cited by 17 publications

References 22 publications

Dynamic movement primitives in robotics: A tutorial survey

Dynamic movement primitives in robotics: A tutorial survey

Motion generation for walking exoskeleton robot using multiple dynamic movement primitives sequences combined with reinforcement learning

A humanoid robot teleoperation approach based on waist–arm coordination

Contact Info

Product

Resources

About