Imitation of human motion on a humanoid robot using non-linear optimization

Do, Martin; Azad, Pedram; Asfour, Tamim; Dillmann, Rüdiger

doi:10.1109/ichr.2008.4756029

Cited by 63 publications

(31 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This hypothesis was proved both by extensive experiments on synthetic data and real-world experiments in relevant realistic scenarios. Furthermore, the developed systems proved their online applicability for manipulation using visual servoing (see [Vahrenkamp et al, 2008]), and imitation (see [Do et al, 2008]) in numerous demonstrations with the humanoid robot ARMAR-III. The scientific contributions of the three developed systems are:…”

Section: Contributionmentioning

confidence: 99%

“…For stable recognition or reproduction of such configurations with a humanoid robot system, trajectories must be postprocessed in order to ensure continuity and uniqueness of the joint angle values in the target kinematics model. This post-processing can be performed online at runtime, as it was applied for the reproduction of movements on the humanoid robot ARMAR-III (see [Do et al, 2008]). Finally, in Fig.…”

Section: Real-world Experiments and Accuracymentioning

confidence: 99%

“…Therefore, a significant relation is understood to the extent that it is unlikely to have arisen by accident [Lowe, 1987]. As features, straight line segments are used, which are extracted by using a method based on the iterative endpoint fit algorithm [Duda and Hart, 1973] on the edge filtered image. Fig.…”

Section: • Collinearitymentioning

confidence: 99%

See 2 more Smart Citations

Visual Perception for Manipulation and Imitation in Humanoid Robots

Azad

2009

Cognitive Systems Monographs

Self Cite

View full text Add to dashboard Cite

Section: Contributionmentioning

confidence: 99%

Section: Real-world Experiments and Accuracymentioning

confidence: 99%

See 1 more Smart Citation

Visual Perception for Manipulation and Imitation in Humanoid Robots

Azad

2009

Cognitive Systems Monographs

Self Cite

View full text Add to dashboard Cite

“…그리고 물체를 파지 후 적절한 경로로 이동하는 경로계획 [8,9] 과 사람과 비슷 한 동작으로 일을 처리하기 위해 모션을 학습 시키거나 사람의 동작을 따라 하는 연구 [10][11][12] 도 진행되고 있다.…”

unclassified

Evaluation of Performance Index of Dual-arm manipulator for Multiple Shape Object Handling

Son¹,

Chen²,

Lee³

2012

The Journal of Korea Robotics Society

View full text Add to dashboard Cite

This paper proposes a performance index for the multiple shape object handling of dual arm manipulator to determine whether a robot is good or not. When the dual-arm manipulator grasps a fixed object and is posed, the dual-arm manipulator should procure a space to freely control the manipulator. As a performance evaluation parameter, each joint torque from current sensor signal is utilized. From the current information, torque and energy for each joint are estimated. In this paper an performance index for an unstructured object is defined by an energy-cost function, and stability analysis for each motion is derived by the maximum force to the object. The maximum force to the object is computed by the inertia of object and acceleration information of end-effector. The acceleration data are derived by the double derivation of each encoder signal. Manipulability measure which implies how efficiently the dual -arm manipulator can move with the grasped object, can be represented by the intersection of the two manipulability ellipsoids for the left and right arms. Effectiveness of the proposed algorithm has been verified through the practical simulations and real experiments.

show abstract

“…Once a human observes a task being carried out for the first time, they are usually capable of immediately performing the same action. In robotics, this process is more complex and can be interpreted in different ways, such as: the imitation learning process and the motion imitation process [1]. The imitation learning process is aimed at understanding the characteristics of human motions, based on data collected from multiple observations of the demonstrated action.…”

Section: Introductionmentioning

confidence: 99%

Human to humanoid motion conversion for dual-arm manipulation tasks

Tomić¹,

Chevallereau²,

Jovanović³

et al. 2018

Robotica

View full text Add to dashboard Cite

SUMMARYA conversion process for the imitation of human dual-arm motion by a humanoid robot is presented. The conversion process consists of an imitation algorithm and an algorithm for generating human-like motion of the humanoid. The desired motions in Cartesian and joint spaces, obtained from the imitation algorithm, are used to generate the human-like motion of the humanoid. The proposed conversion process improves existing techniques and is developed with the aim to enable imitating of human motion with a humanoid robot, to perform a task with and/or without contact between hands and equipment. A comparative analysis shows that our algorithm, which takes into account the situation of marker frames and the position of joint frames, ensures more precise imitation than previously proposed methods. The results of our conversion algorithm are tested on the robot ROMEO through a complex "open/close drawer" task.

show abstract

Imitation of human motion on a humanoid robot using non-linear optimization

Cited by 63 publications

References 14 publications

Visual Perception for Manipulation and Imitation in Humanoid Robots

Visual Perception for Manipulation and Imitation in Humanoid Robots

Evaluation of Performance Index of Dual-arm manipulator for Multiple Shape Object Handling

Human to humanoid motion conversion for dual-arm manipulation tasks

Contact Info

Product

Resources

About