http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Closed Loop Trajectory Optimization Based on Reverse Time Tree
Chyon Hae Kim,Shigeki SUGANO 제어·로봇·시스템학회 2016 International Journal of Control, Automation, and Vol.14 No.6
This paper addresses the general methods for creating the approximately optimal closed loop stabilizationcontrollers that depend on given rigid body systems. The optimal stabilization controllers calculate the optimal force(torque) inputs that depend on the current states of the systems. In this paper, a creation method for approximatelyoptimal controllers named closed loop optimizer based on reverse time tree (CLO-RTT) is proposed. In the openloop optimization phase, this method creates approximately optimal open loop solutions using rapid semi-optimalmotion planning (RASMO). In the closed loop optimization phase, this method selects a solution from the RTTaccording to the measured current state of a system. The proposed method was validated in the time optimalstabilization problem of a double inverted pendulum model. The proposed method successfully stabilized themodel quickly. When the resolution of RASMO was higher, the motion time was shorter.
Murata, Shingo,Yamashita, Yuichi,Arie, Hiroaki,Ogata, Tetsuya,Sugano, Shigeki,Tani, Jun IEEE 2017 IEEE transactions on neural networks and learning Vol.28 No.4
<P>We suggest that different behavior generation schemes, such as sensory reflex behavior and intentional proactive behavior, can be developed by a newly proposed dynamic neural network model, named stochastic multiple timescale recurrent neural network (S-MTRNN). The model learns to predict subsequent sensory inputs, generating both their means and their uncertainty levels in terms of variance (or inverse precision) by utilizing its multiple timescale property. This model was employed in robotics learning experiments in which one robot controlled by the S-MTRNN was required to interact with another robot under the condition of uncertainty about the other's behavior. The experimental results show that self-organized and sensory reflex behavior-based on probabilistic prediction-emerges when learning proceeds without a precise specification of initial conditions. In contrast, intentional proactive behavior with deterministic predictions emerges when precise initial conditions are available. The results also showed that, in situations where unanticipated behavior of the other robot was perceived, the behavioral context was revised adequately by adaptation of the internal neural dynamics to respond to sensory inputs during sensory reflex behavior generation. On the other hand, during intentional proactive behavior generation, an error regression scheme by which the internal neural activity was modified in the direction of minimizing prediction errors was needed for adequately revising the behavioral context. These results indicate that two different ways of treating uncertainty about perceptual events in learning, namely, probabilistic modeling and deterministic modeling, contribute to the development of different dynamic neuronal structures governing the two types of behavior generation schemes.</P>