Robot learning from multiple demonstrations with dynamic movement primitive

Chen, Chuize; Yang, Chenguang; Zeng, Chao; Wang, Ning; Li, Zhijun

doi:10.1109/icarm.2017.8273217

Cited by 17 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BC formulates a supervised learning problem where human actions serve as the ground truth labels of the states. Then, the policy to be cloned can be trained using deep neural networks (DNN) [53] or Gaussian mixture models (GMM) [54]. When human demonstrations are recorded as movement trajectories, states refer to the position and velocity of human trajectories at a certain time and action is the corresponding acceleration [28].…”

Section: Behavior Cloning (Bc)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

Section: Behavior Cloning (Bc)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

show abstract

“…Traditional demonstration learning methods mainly fall into two categories: those based on mathematical models and those based on neural networks. Mathematical model-based methods, such as Dynamic Movement Primitives (DMP) (Chen et al, 2017;Liu et al, 2020), ProMPs (Paraschos et al, 2018), and Task-Parameterized Gaussian Mixture Model (TP-GMM) (Rozo et al, 2015(Rozo et al, , 2016Silvério et al, 2019), model demonstration data by establishing trajectory models. These methods learn operational knowledge by adjusting and optimizing the parameters of mathematical models, similar to how humans adjust and refine their modeling process based on relevant experience.…”

mentioning

confidence: 99%

Peg-in-hole assembly skill imitation learning method based on ProMPs under task geometric representation

Zang,

Wang,

Zha

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

IntroductionBehavioral Cloning (BC) is a common imitation learning method which utilizes neural networks to approximate the demonstration action samples for task manipulation skill learning. However, in the real world, the demonstration trajectories from human are often sparse and imperfect, which makes it challenging to comprehensively learn directly from the demonstration action samples. Therefore, in this paper, we proposes a streamlined imitation learning method under the terse geometric representation to take good advantage of the demonstration data, and then realize the manipulation skill learning of assembly tasks.MethodsWe map the demonstration trajectories into the geometric feature space. Then we align the demonstration trajectories by Dynamic Time Warping (DTW) method to get the unified data sequence so we can segment them into several time stages. The Probability Movement Primitives (ProMPs) of the demonstration trajectories are then extracted, so we can generate a lot of task trajectories to be the global strategy action samples for training the neural networks. Notalby, we regard the current state of the assembly task as the via point of the ProMPs model to get the generated trajectories, while the time point of the via point is calculated according to the probability model of the different time stages. And we get the action of the current state according to the target position of the next time state. Finally, we train the neural network to obtain the global assembly strategy by Behavioral Cloning.ResultsWe applied the proposed method to the peg-in-hole assembly task in the simulation environment based on Pybullet + Gym to test its task skill learning performance. And the learned assembly strategy was also executed on a real robotic platform to verify the feasibility of the method further.DiscussionAccording to the result of the experiment, the proposed method achieves higher success rates compared to traditional imitation learning methods while exhibiting reasonable generalization capabilities. It shows that the ProMPs under geometric representation can help the BC method make better use of the demonstration trajectory and thus better learn the task skills.

show abstract

The Generalization of Robot Skills Based on Dynamic Movement Primitives

Yang

Feng

2020

IFAC-PapersOnLine

View full text Add to dashboard Cite

Robot learning from multiple demonstrations with dynamic movement primitive

Cited by 17 publications

References 16 publications

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

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

Peg-in-hole assembly skill imitation learning method based on ProMPs under task geometric representation

The Generalization of Robot Skills Based on Dynamic Movement Primitives

Contact Info

Product

Resources

About