Conference Paper

Hierarchical motor learning and synthesis with passivity-based controller and phase oscillator

JST, ICORP, Kawaguchi
DOI: 10.1109/ROBOT.2008.4543620 Conference: Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on
Source: IEEE Xplore

ABSTRACT In this paper, we propose a simple framework for learning and synthesis of fast and complex motor tasks. Where a passivity-based task-space controller acts not only as a full-body force control module, but also as an important module to generate phasic joint patterns. The generated joint patterns are encoded into the parameters of phase oscillators and form the synergy of the task. Then, similar and/or faster motions are synthesized by superposing the task space controller output and the oscillator output with the modified oscillator amplitudes and/or frequencies. We present some examples of whole-body motion synthesis on a human-sized biped humanoid robot including squatting, dancing and stepping while bipedal balancing. The simulation and experimental videos are supplemented.

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper it is presented a CPG approach based on phase oscillators to bipedal locomotion where the designer with little a priori knowledge is able to incrementally add basic motion primitives, reaching bipedal walking and other locomotor behaviors as final result. The proposed CPG aims to be a model free solution for the generation of bipedal walking, not requiring the use of inverse kinematical models and previously defined joint trajectories. The proposed incremental construction of bipedal walking allows an easier parametrization and performance evaluation throughout the design process. Furthermore, the approach provides for a developmental mechanism, which enables progressively building a motor repertoire. It would easily benefit from evolutionary robotics and machine learning to explore this aspect. The proposed CPG system also offers a good substrate for the inclusion of feedback mechanisms for modulation and adaptation. It is explored a phase regulation mechanisms using load sensory information, observable in vertebrate legged animals. Results from simulations, on HOAP and DARwIn-OP in Webots software show the adequacy of the locomotor system to generate bipedal walk on different robots. Experiments on a DARwIn-OP demonstrates how it can accomplish locomotion and how the proposed work can generalize, achieving several distinct locomotor behaviors.
    Robotics and Autonomous Systems 09/2014; 62(12). DOI:10.1016/j.robot.2014.08.010 · 1.11 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a full-body compliant motor control strategy with a virtual musculoskeletal system for anthropomorphic robots. This integrates a task-space control module and a joint stiffness control module on joint torque control implementation. The passivity-based task-space controller manages the Cartesian forces and provides the robot with full-body compliance and balancing ability, and the joint stiffness controller locally stabilizes the desired posture trajectories. We discuss the advantage of the proposed strategy from two practical computational points of view: computational cost in the postural maintenance and redundancy resolution to suppress the internal motions. The implementation issues of the torque controller with hydraulic actuators are also discussed. The effectiveness of the proposed method is empirically validated by four kinds of full-body motion control experiments on our hydraulic biped anthropomorphic robot.
    IEEE/ASME Transactions on Mechatronics 01/2010; DOI:10.1109/TMECH.2009.2033117 · 3.65 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new supervised learning and syn- thesis framework for fast and complex motor tasks. Wherein, a statics-based task-space controller acts not only as a full- body motion control module, but also as a module to generate synergetic joint patterns. The generated joint patterns are encoded into the parameters of phase trajectories of attractors and form the synergy of the task. Similar, but faster motions are synthesized by superposing the task-space controller output and the trajectory attractor output with the modified parameters, while learning dynamics and stiffness according to the task error. We demonstrate the proposed framework by simulating a balanced fast squat on a humanoid robot model.

Gordon Cheng