Observational studies of human infants tell us that they can successfully acquire lexicon and that the relationship between the meaning and the uttered word can be understood from only one teaching session by a caregiver, even though there are many other possible mappings. This paper proposes a lexical acquisition model that makes use of curiosity to associate visual features of observed objects with the labels that are uttered by a caregiver. A robot changes its attention and learning rate based on the curiosity. In experiments with a humanoid robot, the visual features are represented using self-organizing maps that adaptively represent the shape of the observed objects independent of viewpoint.
Manipulators resemble human beings in shape of an arm. They also have flexibilities in performance capacity and have been utilized for various kinds of work in place of human beings. Many researches seeking for the design and control of manipulators have been developed and valuable results for energy-efficient manipulators have been reported. However, the driving mechanism of manipulators is, in many cases, different from that of a human arm. Human arms provide not only uniarticular muscles but also biarticular muscles, while manipulators are only equipped with one motor for each joint. With regard to the biarticular muscles, it is reported that they play an important role in performing advanced dynamic functions of human arm movements. This study investigates the relationship between driving mechanisms and energy consumption, and the driving mechanism equipped with a driving motor acting on the shoulder and the elbow joints is proposed.
We propose a robot communication module for enhancing teleoperation stability. The communication module has two major advanced functions. One is multi-homing by HIP (Host Identity Protocol) . The other is multimedia QoS (Quality of Service) control for a teleoperated robot. HIP has distinguished features such as multi-homing, mobility supporting and IPsec communication that must be essential in robot teleoperation. Our QoS control for teleoperated robots adapts to dynamic network conditions under heterogeneous environment and environment of the robot using robot's sensor information. We implemented HIP component as a HIP kernel module and QoS component as APIs similar to socket APIs. Thus these components can be installed easily. In this paper, we conducted a verification of the performance of the robot communication module and summarize our future works.
One drawback of the traditional feature-based visual servoing is that undesired set back motion occurs if the rotation around the optical axis is required to move to the goal position and orientation. Another drawback is that some feature points may go off the screen in the case that goal positions for the feature points are near the edges of the screen, unless the gain coefficients are adjusted appropriately. To overcome these drawbacks, this paper introduces a fuzzy control to the feature based visual servoing that uses a middle image made from a current image and the goal image. Input variables to the fuzzy system are: distance to the current and goal position of the feature points from the center of the screen, the distance between the current and goal position of the feature points, rotational angle required to reach the goal position of the feature points, and the distance of the mean position of the current feature points from the center of the screen. An output from the fuzzy system is a heading or setting back motion that prevent the feature points from going off the screen and make the feature points approach the goal position efficiently. Effectiveness of the proposed method is demonstrated experimentally, compared to the other two traditional methods.
In this paper, we conducted theoretical investigation and experimental verification of robustness on a power assist system that utilizes stiffness optimization of a mechanical elastic element. This power assist system amplifies torque of its operator and optimizes the stiffness automatically to minimize torque of an actuator in the case of sinusoidal motions. The theoretical investigation clarified physical meanings of all terms of the controller, which realizes the torque amplification and the automatic stiffness optimization. Some experimental results demonstrated the effectiveness of the proposed power assist system even when some physical parameters of the controlled object are not known precisely.