Motion Retargeting for Humanoid Robots Based on Simultaneous Morphing Parameter Identification and Motion Optimization

Ayusawa, Ko; Yoshida, Eiichi

doi:10.1109/tro.2017.2752711

Cited by 55 publications

(48 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective is to retain, as much as possible, the properties of the demonstrator's motion while making the motion feasible for the robot. This it typically done via optimization (e.g., [5,36]) or dynamic filtering [59].…”

Section: Manually Selected Featuresmentioning

confidence: 99%

Robot Expressive Motions

Venture

Kulić

2019

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

Robots that have different forms and capabilities are used in a wide variety of situations; however, one common point to all robots interacting with humans is their ability to communicate with them. In addition to verbal communication or purely communicative movements, robots can also use their embodiment to generate expressive movements while achieving a task, to convey additional information to its human partner. This article surveys state-of-the-art techniques that generate whole-body expressive movements in robots and robot avatars. We consider different embodiments such as wheeled, legged, or flying systems and the different metrics used to evaluate the generated movements. Finally, we discuss future areas of improvement and the difficulties to overcome to develop truly expressive motions in artificial agents.

show abstract

Section: Manually Selected Featuresmentioning

confidence: 99%

Robot Expressive Motions

Venture

Kulić

2019

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

show abstract

“…Active learning in robotics has recently been a topic of interest [6]- [10]. Much work has been done in active learning for parameter identification [11]- [14] as well as active learning for state-control mappings in reinforcement learning [9], [15]- [18] and adaptive control [19]- [21]. In particular, much of the mentioned work refers to exciting a robot's dynamics -using information theoretic measures [10], [12], [13], reward functions [9], [10], [15], [17] in reinforcement learning, and other methods [22], [23]-in order to obtain the "best" set of measurements that resolve a parameter or the "best-case" mapping (either of the state-control map or of the dynamics).…”

Section: A History and Related Workmentioning

confidence: 99%

“…where learn is the information maximizing objective (learning task) and task (z, u) is the task objective for which the policy μ(z) is a solution to (14) when learn = 0. Given 14, we want to synthesize a controller that is bounded to the policy μ(z), but also allows for improvement of an information measure for active learning.…”

Section: A Control Formulationmentioning

confidence: 99%

Active Learning of Dynamics for Data-Driven Control Using Koopman Operators

2019

View full text Add to dashboard Cite

This paper presents an active learning strategy for robotic systems that takes into account task information, enables fast learning, and allows control to be readily synthesized by taking advantage of the Koopman operator representation. We first motivate the use of representing nonlinear systems as linear Koopman operator systems by illustrating the improved model-based control performance with an actuated Van der Pol system. Informationtheoretic methods are then applied to the Koopman operator formulation of dynamical systems where we derive a controller for active learning of robot dynamics. The active learning controller is shown to increase the rate of information about the Koopman operator. In addition, our active learning controller can readily incorporate policies built on the Koopman dynamics, enabling the benefits of fast active learning and improved control. Results using a quadcopter illustrate single-execution active learning and stabilization capabilities during free fall. The results for active learning are extended for automating Koopman observables and we implement our method on real robotic systems.

show abstract

“…Off-line methods have been proposed as well to reconstruct the human motion within the physical constraints imposed by the retargeted subject kinematics and dynamics. Ayusawa and Yoshida [22] proposed a simultaneous morphing parameter identification and motion optimization. In [23] Borno et al used instead a LQR-tree formulation to transfer the motion between 3D realistic human models and adapting it to the different body shapes.…”

Section: Related Workmentioning

confidence: 99%

Robust Real-Time Whole-Body Motion Retargeting from Human to Humanoid

Peneo

Clément

Moduano

et al. 2018

2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

Transferring the motion from a human operator to a humanoid robot is a crucial step to enable robots to learn from and replicate human movements. The ability to retarget in realtime whole-body motions that are challenging for the humanoid balance is critical to enable human to humanoid teleoperation. In this work, we design a retargeting framework that allows the robot to replicate the motion of the human operator, acquired by a wearable motion capture suit, while maintaining the whole-body balance. We introduce some dynamic filter in the retargeting to forbid dangerous motions that can make the robot fall. We validate our approach through several experiments on the iCub robot, which has a significantly different body structure and size from the one of the human operator.

show abstract

Motion Retargeting for Humanoid Robots Based on Simultaneous Morphing Parameter Identification and Motion Optimization

Cited by 55 publications

References 30 publications

Robot Expressive Motions

Robot Expressive Motions

Active Learning of Dynamics for Data-Driven Control Using Koopman Operators

Robust Real-Time Whole-Body Motion Retargeting from Human to Humanoid

Contact Info

Product

Resources

About