Humanoids skill learning based on real-time human motion imitation using Kinect

Elbasiony, Reda; Gomaa, Walid

doi:10.1007/s11370-018-0247-z

Cited by 23 publications

(12 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, most papers addressed to the teleoperation of biped or humanoid robots are based on using motion capture devices in order to map the movements of a human operator to the robot, as in reference [5], or employing two traditional joysticks [6]. Te main disadvantage of both articles is that the user does not receive any kind of tactile feedback.…”

Section: Introductionmentioning

confidence: 99%

Stable Bilateral Teleoperation Control Method for Biped Robots with Time-Varying Delays

Moya

Slawiñski

Mut

et al. 2023

Journal of Robotics

View full text Add to dashboard Cite

This document proposes a control scheme applied to delayed bilateral teleoperation of the forward and turn speed of a biped robot against asymmetric and time-varying delays. This biped robot is modeled as a hybrid dynamic system because it behaves as a continuous system when the leg moves forward and discrete when the foot touches the ground generating an impulsive response. It is proposed to vary online the damping according to the time delay present in the communication channel, and the walking cycle time using an optimization criterion, to decrease the teleoperation system errors. To accomplish this, a three-phase cascade calibration process is used, and their benefits are evidenced in a comparative simulation study. The first phase is an offline calibration of the inverse dynamic compensation and also the parameters of the bilateral controller. The second phase guarantees the bilateral coordination of the delayed teleoperation system, using the Lyapunov–Krasovskii stability theory, by changing the leader damping and the equivalent follower damping together. The third phase assures a stable walk of the hybrid dynamics by controlling the walking cycle time and the real damping to move the eigenvalues of the Poincaré map, numerically computed, to stable limit cycles and link this result with an equivalent continuous system to join both phases. Additionally, a fictitious force was implemented to detect and avoid possible collisions with obstacles. Finally, an intercontinental teleoperation experiment of an NAO robot via the Internet including force and visual feedback is shown.

show abstract

Section: Introductionmentioning

confidence: 99%

Stable Bilateral Teleoperation Control Method for Biped Robots with Time-Varying Delays

Moya

Slawiñski

Mut

et al. 2023

Journal of Robotics

View full text Add to dashboard Cite

show abstract

“…advantage of need not map the human motions to the robot space while has a limitation on robot configuration. Not all kinds of robot can be moved by a human demonstrator [7]. The third one is using the sensor mounted on the robot, for example, its camera.…”

Section: Introductionmentioning

confidence: 99%

“…The robot extracting necessary information by using its vision is the most nature method because less effort must be invested by the human tutor. The skeleton tracking method [8] provided by the Microsoft Kinect Software Development Kit (SDK) which allows the robot to detect the skeleton of a human is widely used in many related studies [7], [9]- [20]. The detected joint angles of a human skeleton are then mapped to those of a robot by either inverse kinematics or computational geometry method.…”

Section: Introductionmentioning

confidence: 99%

“…A complex motion can be generated by combining several MPs and a path trajectory. The popular MP representations include dynamic movement primitives (DMPs) [22] and GMMs [4], [5], [19], [7]. In [22], a complex motion sequence involves MPs and a moving path.…”

Section: Introductionmentioning

confidence: 99%

“…Elbasiony and Gomaa integrated a Kinect sensor and two force sensors to capture human motions and project the motion on a latent space by using the Gaussian process latent variable model (GPLVM) to extract the relevant features. Finally, the robot learned the different motions and learned object grasping [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Motion Imitation and Augmentation System for a Six Degrees of Freedom Dual-Arm Robot

Liu

Liang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

A motion imitation and augmentation system comprising an imitation system, a self-collision avoidance system, and a motion augmented system was proposed in this study. The imitation system captures the human skeleton by using an RGB-D camera and a method involving forward kinematics and the space vector method was developed and integrated to map the human joint angles to the motor angles of the robot's arm. To improve safety of the system, a self-collision avoidance system was incorporated so that the various parts of the robot do not collide with each other while imitating human motions. The imitated motion was recorded and stored in a motion dataset as a reference motion. To address different situations and objects, the reference motion was adjusted using the motion augmented system in which both the adjusted trajectory and its corresponding motor angles were generated using the integrated adaptive constricted particle swarm optimization algorithm. So that, the adjusted motion can adapt to the real situation while maintaining similarity with the reference motion. Experiments conducted in practical situations demonstrated the efficiency of the motion imitation and augmentation system. The robot can mimic a reference motion by using its vision and can generate a suitable motion based on the imitated motion for coping with different objects and situations.

show abstract

Modular Real-Time System for Upper-Body Motion Imitation on Humanoid Robot Talos

Savevska

Simonič

Ude

2021

Advances in Service and Industrial Robotics

View full text Add to dashboard Cite

Humanoids skill learning based on real-time human motion imitation using Kinect

Cited by 23 publications

References 32 publications

Stable Bilateral Teleoperation Control Method for Biped Robots with Time-Varying Delays

Stable Bilateral Teleoperation Control Method for Biped Robots with Time-Varying Delays

Motion Imitation and Augmentation System for a Six Degrees of Freedom Dual-Arm Robot

Modular Real-Time System for Upper-Body Motion Imitation on Humanoid Robot Talos

Contact Info

Product

Resources

About