Towards physical interaction-based sequential mobility assistance using latent generative model of movement state

Itadera, Shunki; Kobayashi, Taisuke; Nakanishi, Jun; Aoyama, Tadayoshi; Hasegawa, Yasuhisa

doi:10.1080/01691864.2020.1844797

Cited by 12 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For handling physical interaction, robot is often controlled with a virtual impedance model [5]- [7]. It enables robot to follow to human easily, but there are strong limitations on the contact points and the actions that can be generated.…”

Section: Introductionmentioning

confidence: 99%

“…Methods for extracting the latent state space hidden in high-dimensional observation data have been established [11], [12]. They have been applied to, for example, control applications based on learning of dynamics model [13], [14] and motion classification in the extracted space [7], [15].…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, we focus on the fact that most of the pHRI tasks show periodicity: such as, polishing [5], brushing [6], walking [7], dancing [8], and so on. For simplifying the computational graph as mentioned above, reservoir computing (RC) [19]- [22], a type of RNNs consisting of numerous neurons connected each other by random and fixed parameters, is first employed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics

Kobayashi,

Murata,

Inamura

2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a new data-driven framework for analyzing periodic physical human-robot interaction (pHRI) in latent state space. To elaborate human understanding and/or robot control during pHRI, the model representing pHRI is critical. Recent developments of deep learning technologies would enable us to learn such a model from a dataset collected from the actual pHRI. Our framework is developed based on variational recurrent neural network (VRNN), which can inherently handle time-series data like one pHRI generates. This paper modifies VRNN in order to include the latent dynamics from robot to human explicitly. In addition, to analyze periodic motions like walking, we integrate a new recurrent network based on reservoir computing (RC), which has random and fixed connections between numerous neurons, with VRNN. By augmenting RC into complex domain, periodic behavior can be represented as the phase rotation in complex domain without decaying the amplitude. For verification of the proposed framework, a rope-rotation/swinging experiment was analyzed. The proposed framework, trained on the dataset collected from the experiment, achieved the latent state space where the differences in periodic motions can be distinguished. Such a well-distinguished space yielded the best prediction accuracy of the human observations and the robot actions.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics

Kobayashi,

Murata,

Inamura

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…For such next-generation robot control problems, traditional modelbased control like [1] seems to reach its limit due to the difficulty of modeling complex systems. Model-free or learning-based control like [2] is expected to resolve these problems in recent year. In particular, reinforcement learning (RL) [3] is one of the most promising approaches to this end, and indeed, RL integrated with deep neural networks [4], so-called deep RL [5], achieved several complex tasks: e.g.…”

Section: Introductionmentioning

confidence: 99%

Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures

Kobayashi,

Yoshizawa

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background and problem statement: Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of feedback (FB) controllers. Due to the necessity of correct state observation in such a FB controller, it is sensitive to sensing failures. To alleviate this drawback of the FB controllers, feedback error learning integrates one of them with a feedforward (FF) controller. RL can be improved by dealing with the FB/FF policies, but to the best of our knowledge, a methodology for learning them in a unified manner has not been developed. Contribution:In this paper, we propose a new optimization problem for optimizing both the FB/FF policies simultaneously. Inspired by control as inference, the optimization problem considers minimization/maximization of divergences between trajectory, predicted by the composed policy and a stochastic dynamics model, and optimal/non-optimal trajectories. By approximating the stochastic dynamics model using variational method, we naturally derive a regularization between the FB/FF policies. In numerical simulations and a robot experiment, we verified that the proposed method can stably optimize the composed policy even with the different learning law from the traditional RL. In addition, we demonstrated that the FF policy is robust to the sensing failures and can hold the optimal motion.

show abstract

“…While most such work focuses on physical joint interaction, i.e. manipulating heavy objects in an industrial setting [5,6] or helping mobility reduced people [7,8] among others, the important topic of joint cognitive interaction has only been getting attention recently [9,10,11]. In this setting the robot needs to collaborate with the human for solving a problem or making a decision.…”

mentioning

confidence: 99%

Utility Functions for Human/Robot Interaction

Yun¹,

Oren²,

Croitoru³

2022

Preprint

View full text Add to dashboard Cite

In this paper, we place ourselves in the context of human robot interaction and address the problem of cognitive robot modelling. More precisely we are investigating properties of a utility-based model that will govern a robot's actions. The novelty of this approach lies in embedding the responsibility of the robot over the state of affairs into the utility model via a utility aggregation function. We describe desiderata for such a function and consider related properties.

show abstract

Towards physical interaction-based sequential mobility assistance using latent generative model of movement state

Cited by 12 publications

References 32 publications

Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics

Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics

Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures

Utility Functions for Human/Robot Interaction

Contact Info

Product

Resources

About