Construction of a human/robot coexistence system based on a model of human will-intention and desire

Yamada, Yoji; Umetani, Yoji; Daitoh, Haruyoshi; Sakai, Takayuki

doi:10.1109/robot.1999.774031

Cited by 28 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hidden Markov Models. There is a long history of using a Bayesian approach to estimate the intent of an operator interacting with a device (Yamada, Umetani, Daitoh, & Sakai, 1999;Schmid, Weede, & Worn, 2007;Takeda, Hirata, & Kosuge, 2007). As a probabilistic approach, it allows for reasoning under uncertainty.…”

Section: Problem Statement: Probabilistic Prediction Of Muscle Coordimentioning

confidence: 99%

A Model for Operator Endpoint Stiffness Prediction during Physical Human-Robot Interaction

Moualeu

Ueda

2015

Journal of Human-Robot Interaction

View full text Add to dashboard Cite

Physical contact established during interaction between a human operator and a haptic device creates a coupled system with stability and performance characteristics different than its individual subsystems taken in isolation. Proper incorporation of operator dynamics in physical human-robot interaction (pHRI) conditions requires knowledge of system variables and parameters, some of which are not directly measurable. Operator endpoint impedance, for instance, cannot be directly measured in typical haptic control conditions. Several endpoint impedance estimation techniques have been explored in previous literature, based on measured kinematics and/or other correlated metrics. Arm muscle activity, measured through surface electromyography (sEMG), has been used in previous literature to estimate endpoint stiffness, which is the static component of impedance. Co-activation (co-contraction) of antagonistic arm muscles forming a pair around a joint is known to be the driving factor in modulation of endpoint stiffness. However, previous work employing muscle co-contraction to predict endpoint stiffness has mainly been absent, due in part to the inefficacy of operator models to incorporate muscle co-activation into the prediction scheme. The current study proposes a method for prediction of operator endpoint stiffness based on measured co-contraction levels of a select group of muscles. The proposed methodology incorporates an upper extremity musculoskeletal model that accounts for muscle redundancy and the role of muscle co-contraction on arm stiffness modulation. The study hypothesizes that a free parameter, currently known in the literature to represent the nullspace of the mapping between muscle forces and joint torques, is a random variable of which probability density function can be estimated. Changes in this parameter directly affect changes in operator endpoint stiffness. Ten healthy subjects were asked to resist perturbations induced by a one degree of freedom (DOF) haptic paddle device while measurements, including muscle activities of four arm muscles, were being carried out. Direct derivation of stiffness values at the endpoint was compared to simulated endpoint stiffness values obtained using the proposed predictive methodology. Ten out of forty prediction trials resulted in a statistically significant correlation between predicted and actual stiffness values. Impressive stiffness prediction results, with over 99% peak accuracy in value, were found in only one trial using a combination of the proposed method along with a standard static optimization method for muscle force computation. Though the possibility of using a probabilistic approach to stiffness prediction was shown, robustness and generalizability of the proposed approach to multi-DOF systems remain to be addressed.

show abstract

Section: Problem Statement: Probabilistic Prediction Of Muscle Coordimentioning

confidence: 99%

A Model for Operator Endpoint Stiffness Prediction during Physical Human-Robot Interaction

Moualeu

Ueda

2015

Journal of Human-Robot Interaction

View full text Add to dashboard Cite

show abstract

“…The contribution of this approach is that the recognition process is applied on the frequency spectrum of the force-torque signal measured at the robot"s gripper. Previous works on intention recognition are mostly based on monitoring the human"s motion [Yamada, 1999] and have neglected the selection of the optimal robot motion that would create a true human-robot interaction, reducing robot slavery and promoting human-robot friendship. Thus, robots will be required not only to help and collaborate, but to do so in a friendly and caring way.…”

Section: Reflexive Motion Controlmentioning

confidence: 99%

Robot Arm-Child Interactions: A Novel Application Using Bio-Inspired Motion Control

Beran¹,

Ramírez-Serrano²

2011

Robot Arms

View full text Add to dashboard Cite

“…Field Impedance Equalizer (FIE) was a framework for operational feel adjustment proposed by Yamada et al [9].…”

Section: B Field Impedance Equalizer (Fie)mentioning

confidence: 99%

Operational Feel Adjustment for Power-Assisted Positioning by an Actor-Critic Method

Morizono

2010

2010 International Conference on Broadband, Wireless Computing, Communication and Applications

View full text Add to dashboard Cite

This paper proposes a method of operational feel adjustment using reinforcement learning for power-assisted positioning. To illustrate difference from the author's previous study and motivation of the study in this paper, two methods of reinforcement learning, Sarsa and actor-critic methods, are experimentally compared at first with a simple example. Then, operational feel adjustment using an actor-critic method is proposed and examined by experiment. Results obtained in experiment are observed for some discussion, and concluding remark makes mention of some future issues.

show abstract

Construction of a human/robot coexistence system based on a model of human will-intention and desire

Cited by 28 publications

References 15 publications

A Model for Operator Endpoint Stiffness Prediction during Physical Human-Robot Interaction

A Model for Operator Endpoint Stiffness Prediction during Physical Human-Robot Interaction

Robot Arm-Child Interactions: A Novel Application Using Bio-Inspired Motion Control

Operational Feel Adjustment for Power-Assisted Positioning by an Actor-Critic Method

Contact Info

Product

Resources

About