Search

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.robot.2006.05.012 Byline: Takamitsu Matsubara (a)(c), Jun Morimoto (b)(c), Jun Nakanishi (b)(c), Masa-aki Sato (c), Kenji Doya (a)(c)(d) Abstract: In this paper, we propose a learning framework for CPG-based biped locomotion with a policy gradient method. We demonstrate that appropriate sensory feedback to adjust the rhythm of the CPG (Central Pattern Generator) can be learned using the proposed method within a few hundred trials in simulations. We investigate linear stability of a periodic orbit of the acquired walking pattern considering its approximated return map. Furthermore, we apply the controllers acquired in numerical simulations to our physical 5-link biped robot in order to empirically evaluate the robustness of walking in the real environment. Experimental results demonstrate that the robot was able to successfully walk using the acquired controllers even in the cases of an environmental change by placing a seesaw-like metal sheet on the ground and a parametric change of the robot dynamics with an additional weight on a shank, which was not modeled in the numerical simulations. Author Affiliation: (a) Nara Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara 630-0101, Japan (b) ICORP, JST, 2-2-2, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan (c) ATR, CNS, 2-2-2, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan (d) Neural Computation Unit, Initial Research Project, Okinawa Institute of Science and Technology, 12-22, Suzaki, Gushikawa, Okinawa 904-2234, Japan Article History: Received 15 October 2005; Revised 12 May 2006; Accepted 24 May 2006

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.robot.2006.03.004 Byline: Takashi Bando (a), Tomohiro Shibata (a)(b), Kenji Doya (c)(b)(a), Shin Ishii (a) Abstract: In this article, we propose a new particle filtering scheme, called a switching particle filter, which allows robust and accurate visual tracking under typical circumstances of real-time visual tracking. This scheme switches two complementary sampling algorithms, Condensation and Auxiliary Particle Filter, in an on-line fashion based on the confidence of the filtered state of the visual target. The accuracy and robustness of the switching scheme were evaluated using real visual tracking experiments as well as computer simulations. Furthermore, we demonstrate through visual tracking experiments that our scheme not only outperforms existing particle filters but also assists on-line learning of target dynamics. Author Affiliation: (a) Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, 6300192, Nara, Japan (b) Computational Neuroscience Laboratories, ATR International, 2-2-2 Hikaridai, Keihanna Science City, 6190288, Kyoto, Japan (c) Initial Research Project, Okinawa Institute of Science and Technology, 12-22 Suzaki, Uruma, 9042234, Okinawa, Japan Article History: Received 4 January 2005; Revised 27 September 2005; Accepted 23 March 2006

A multi-population genetic algorithm (MPGA) was employed to improve the performance of evolutionary algorithm, while application of an extended MPGA (EMPGA) was proposed to improve the convergence of evolution. The results indicate that EMPGA gave the best performance and evolved faster by distributing efficiently the genetic resources as different strategies became successful during the course of evolution.

The aim of the Cyber Rodent project is to understand the origins of our reward and affective systems by building artificial agents that share the same intrinsic constraints as natural […]

Temporal and sequential information is essential to any agent continually interacting with its environment. In this paper, we test whether it is possible to evolve a recurrent neural network controller […]

Recent studies have shown that multiple brain areas contribute to different stages and aspects of procedural learning. On the basis of a series of studies using a sequence-learning task with trial-and-error, we propose a hypothetical scheme in which a sequential procedure is acquired independently by two cortical systems, one using spatial coordinates and the other using motor coordinates. They are active preferentially in the early and late stages of learning, respectively. Both of the two systems are supported by loop circuits formed with the basal ganglia and the cerebellum, the former for reward-based evaluation and the latter for processing of timing. The proposed neural architecture would operate in a flexible manner to acquire and execute multiple sequential procedures.