Humanoid Robot Motion Modeling Based on Time-Series Data Using Kernel PCA and Gaussian Process Dynamical Models

Mi, Jian; Takahashi, Yasutake

doi:10.20965/jaciii.2018.p0965

Cited by 3 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the issues that need to be addressed to implement kernel PCA are the storage of a large kernel matrix and the selection of the nonlinear kernel. The utilization of different kernels was investigated for modeling of humanoid robot motions in [24]. Given that we are dealing with a nonlinear task in a nonlinear world, we chose autoencoders for dimensionality reduction.…”

Section: Related Workmentioning

confidence: 99%

Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks

et al. 2021

View full text Add to dashboard Cite

Autonomous robot learning in unstructured environments often faces the problem that the dimensionality of the search space is too large for practical applications. Dimensionality reduction techniques have been developed to address this problem and describe motor skills in low-dimensional latent spaces. Most of these techniques require the availability of a sufficiently large database of example task executions to compute the latent space. However, the generation of many example task executions on a real robot is tedious, and prone to errors and equipment failures. The main result of this paper is a new approach for efficient database gathering by performing a small number of task executions with a real robot and applying statistical generalization, e.g., Gaussian process regression, to generate more data. We have shown in our experiments that the data generated this way can be used for dimensionality reduction with autoencoder neural networks. The resulting latent spaces can be exploited to implement robot learning more efficiently. The proposed approach has been evaluated on the problem of robotic throwing at a target. Simulation and real-world results with a humanoid robot TALOS are provided. They confirm the effectiveness of generalization-based database acquisition and the efficiency of learning in a low-dimensional latent space.

show abstract

Section: Related Workmentioning

confidence: 99%

Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The proposed humanoid robot motion learning is illustrated in Figure 4. Observed humanoid robot joint angles θ are reduced to x in a 3D state space using kernel PCA [14] as shown in Figure 7a. Then, 3D latent variables x are relearned using GPDM [20].…”

Section: Humanoid Robot Motion Learningmentioning

confidence: 99%

“…A dynamical mapping f x : x t → x t+1 is constructed as shown in Figure 7b. Moreover, a decoder mapping f θ : x t → θ t (Figure 7c) is learned to reconstruct high-dimensional joint angles (for details of GPDM learning, see [14]).…”

Section: Humanoid Robot Motion Learningmentioning

confidence: 99%

“…The learning hyperparameters were initially set to α = [1.0, 1.0, 1.0, exp(1.0)], β = [1.0, 1.0, exp(1.0)], and ω j = 1.0 (for more details, please see [14]) . The GPDM learned 3D motion models are illustrated in Figure 8a.…”

Section: Motion Learned Using Gaussian Process Dynamical Modelmentioning

confidence: 99%

“…Urtasunet et al [12] and Kim et al [13] proved that human dynamical motion models can be constructed in a low-dimensional latent space. Humanoid robot dynamical motion models were learned in the research by Mi and Takahashi [14] by using kernel PCA-GPDM. Compared with conventional neural network methods, GPDM has advantages over learning motion models with modest amounts of training data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Whole-Body Joint Angle Estimation for Real-Time Humanoid Robot Imitation Based on Gaussian Process Dynamical Model and Particle Filter

Takahashi

2019

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Real-time imitation enables a humanoid robot to mirror the behavior of humans, being important for applications of human–robot interaction. For imitation, the corresponding joint angles of the humanoid robot should be estimated. Generally, a humanoid robot comprises dozens of joints that construct a high-dimensional exploration space for estimating the joint angles. Although a particle filter can estimate the robot state and provides a solution for estimating joint angles, the computational cost becomes prohibitive given the high dimension of the exploration space. Furthermore, a particle filter can only estimate the joint angles accurately using a motion model. To realize accurate joint angle estimation at low computational cost, Gaussian process dynamical models (GPDMs) can be adopted. Specifically, a compact state space can be constructed through the GPDM learning of high-dimensional time-series motion data to obtain a suitable motion model. We propose a GPDM-based particle filter using a compact state space from the learned motion models to realize efficient estimation of joint angles for robot imitation. Simulations and real experiments demonstrate that the proposed method efficiently estimates humanoid robot joint angles at low computational cost, enabling real-time imitation.

show abstract

Materializing Architecture for Processing Multimodal Signals for a Humanoid Robot Control System

Akikawa¹,

Yamamura²

2021

JACIII

View full text Add to dashboard Cite

In recent years, many systems have been developed to embed deep learning in robots. Some use multimodal information to achieve higher accuracy. In this paper, we highlight three aspects of such systems: cost, robustness, and system optimization. First, because the optimization of large architectures using real environments is computationally expensive, developing such architectures is difficult. Second, in a real-world environment, noise, such as changes in lighting, is often contained in the input. Thus, the architecture should be robust against noise. Finally, it can be difficult to coordinate a system composed of individually optimized modules; thus, the system is better optimized as one architecture. To address these aspects, a simple and highly robust architecture, namely memorizing and associating converted multimodal signal architecture (MACMSA), is proposed in this study. Verification experiments are conducted, and the potential of the proposed architecture is discussed. The experimental results show that MACMSA diminishes the effects of noise and obtains substantially higher robustness than a simple autoencoder. MACMSA takes us one step closer to building robots that can truly interact with humans.

show abstract

Humanoid Robot Motion Modeling Based on Time-Series Data Using Kernel PCA and Gaussian Process Dynamical Models

Cited by 3 publications

References 24 publications

Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks

Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks

Whole-Body Joint Angle Estimation for Real-Time Humanoid Robot Imitation Based on Gaussian Process Dynamical Model and Particle Filter

Materializing Architecture for Processing Multimodal Signals for a Humanoid Robot Control System

Contact Info

Product

Resources

About