scispace - formally typeset
Search or ask a question
Topic

Humanoid robot

About: Humanoid robot is a research topic. Over the lifetime, 14387 publications have been published within this topic receiving 243674 citations. The topic is also known as: 🤖.


Papers
More filters
Proceedings ArticleDOI
06 May 2013
TL;DR: GSL is introduced, an iterative optimization framework for speeding up robot learning using an imperfect simulator, and is fully implemented and validated on the task of learning to walk using an Aldebaran Nao humanoid robot.
Abstract: Simulation is often used in research and industry as a low cost, high efficiency alternative to real model testing. Simulation has also been used to develop and test powerful learning algorithms. However, parameters learned in simulation often do not translate directly to the application, especially because heavy optimization in simulation has been observed to exploit the inevitable simulator simplifications, thus creating a gap between simulation and application that reduces the utility of learning in simulation.This paper introduces Grounded Simulation Learning (GSL), an iterative optimization framework for speeding up robot learning using an imperfect simulator. In GSL, a behavior is developed on a robot and then repeatedly: 1) the behavior is optimized in simulation; 2) the resulting behavior is tested on the real robot and compared to the expected results from simulation, and 3) the simulator is modified, using a machine-learning approach to come closer in line with reality. This approach is fully implemented and validated on the task of learning to walk using an Aldebaran Nao humanoid robot. Starting from a set of stable, hand-coded walk parameters, four iterations of this three-step optimization loop led to more than a 25% increase in the robot's walking speed.

86 citations

Proceedings ArticleDOI
31 Oct 2000
TL;DR: With the proposed method, safety and energy-effective control of biped walking robot can be realized and multi-pattern walking with respect to energy level is proposed.
Abstract: It has been shown that a simplest walker with suitable parameter choice can walk down a gentle slope without any control forces and generate its steady walking pattern utilizing gravity effect automatically. On the floor, however, the robot cannot exhibit passive walk, so any application methods of passive walk to active walker on the horizontal floor has not been studied yet. In this paper we introduce "virtual passive dynamic walking" with virtual gravity field which acts as a driving force for the biped robot. The robot can walk on the floor without any control torque except virtual gravity effect. Since the modified gravity field seems to be very close to real condition, the generated walking pattern seems to be natural. Further, multi-pattern walking with respect to energy level is proposed. With the proposed method, safety and energy-effective control of biped walking robot can be realized.

86 citations

Journal ArticleDOI
25 Aug 2014-PLOS ONE
TL;DR: The findings suggest that the observer may transiently match his/her own motor repertoire to that of the observed agent, which might mediate the activation of motor resonance, and modulate the spontaneity and the pleasantness of the interaction, whatever the nature of the communication partner.
Abstract: Motor resonance mechanisms are known to affect humans' ability to interact with others, yielding the kind of “mutual understanding” that is the basis of social interaction. However, it remains unclear how the partner's action features combine or compete to promote or prevent motor resonance during interaction. To clarify this point, the present study tested whether and how the nature of the visual stimulus and the properties of the observed actions influence observer's motor response, being motor contagion one of the behavioral manifestations of motor resonance. Participants observed a humanoid robot and a human agent move their hands into a pre-specified final position or put an object into a container at various velocities. Their movements, both in the object- and non-object- directed conditions, were characterized by either a smooth/curvilinear or a jerky/segmented trajectory. These trajectories were covered with biological or non-biological kinematics (the latter only by the humanoid robot). After action observation, participants were requested to either reach the indicated final position or to transport a similar object into another container. Results showed that motor contagion appeared for both the interactive partner except when the humanoid robot violated the biological laws of motion. These findings suggest that the observer may transiently match his/her own motor repertoire to that of the observed agent. This matching might mediate the activation of motor resonance, and modulate the spontaneity and the pleasantness of the interaction, whatever the nature of the communication partner.

86 citations

Proceedings ArticleDOI
16 May 1998
TL;DR: The authors introduce a life-size biped walking robot having antagonistic driven joints using a nonlinear spring mechanism and a dynamic biped Walking control method using these joints, and proposed a walking control method for dynamic biping walking that uses antagonistic drive joints to vary joint stiffness.
Abstract: The authors introduce a life-size biped walking robot having antagonistic driven joints using a nonlinear spring mechanism and a dynamic biped walking control method using these joints. In the current research concerning a biped walking robot, there is no developed example of a life-size biped walking robot with antagonistically driven joints by which the human musculo-skeletal system is imitated in lower limbs. Humans are considered to walk efficiently using the inertial energy and the potential energy of the lower limbs effectively, walk smoothly with less impact force when a foot lands and cope flexibly with the outside environment. The human joint is driven by two or more muscle groups. Humans can vary the joint stiffness, using nonlinear spring characteristics possessed by the muscles themselves. These functions are indispensable for a humanoid. However, the biped walking robots developed previously have been unable to walk in this way. Therefore, the authors developed a biped walking robot having antagonistic driven joints, and proposed a walking control method for dynamic biped walking that uses antagonistic driven joints to vary joint stiffness. The authors performed walking experiments using the biped walking robot and the control method. As a result, dynamic biped walking varying the joint stiffness using antagonistic driven joints was realized.

85 citations

Proceedings ArticleDOI
01 Nov 2011
TL;DR: An exploration of current trends in control methods of biped walks, behavior interface tools for motion control for NAO and imminent findings in both research areas are discussed.
Abstract: Humanoids; a most intriguing subject to behold by both the engineers and the world at large. With the introduction of humanoid robot NAO by Aldebaran-Robotics in 2008, a performant biped robot is now available and affordable for research laboratories and the mass market. In this paper, an exploration of current trends in control methods of biped walks, behavior interface tools for motion control for NAO and imminent findings in both research areas are discussed. Future directions are for researchers to devise a unique controller with low power consumption without compromising the robot's speed and robustness.

85 citations


Network Information
Related Topics (5)
Mobile robot
66.7K papers, 1.1M citations
96% related
Robot
103.8K papers, 1.3M citations
95% related
Adaptive control
60.1K papers, 1.2M citations
84% related
Control theory
299.6K papers, 3.1M citations
83% related
Object detection
46.1K papers, 1.3M citations
81% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023253
2022759
2021573
2020647
2019801
2018921