The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The problem of optimal degree of autonomy and minimal complexity is considered for mission capable systems in spacecrafts and unmanned aeronautical systems. Levels of autonomy and system requirements are discussed. Simple and goal oriented system architectures are summarized and the prospect of plug-and-play systems is outlined. The engineering compromise to be made between degree of autonomy and...
The problem of distinguishing between relevant and irrelevant variation is shared by natural and artificial data analysis systems. The problem is especially hard when the dimensionality of the data is high and yet inferences need to be made based on only few samples, and when the models are flexible machine learning models. I will discuss three learning strategies for coping with the problem, and...
Despite of much evidence suggesting how and where sensory information converge in the human brain, the neural mechanisms of interaction among modalities at the level of neuronal cells and ensembles are still not well understood. The chapter explores emulation of multimodal information processing in a brain-like manner through evolving spiking neural network (ESNN) architectures that use several multimodal...
We aim to develop a robust and flexible navigation system having adaptability against changes in circumstances like a human being. A practical local navigation system inspired by the structure of the entorhino-hippocampal loop circuitry is described. The local navigation system consists of a landmark extraction unit, a learning-type matching unit and a local route memory unit. In the local route memory...
We propose to introduce the desire for existence, specific curiosity, diversive curiosity, and novelty into reinforcement learning as intrinsic rewards for developing truly autonomous mobile robots capable of behaving without being told what to do. A pursuit-evasion game composed of predators and their prey is selected as a testbed. Simulation experiments and experiments using real mobile robots,...
We propose to introduce the desire for existence into reinforcement learning as intrinsic motivation for developing robots with emerging behaviors. A pursuit-evasion game composed of predators and their prey is selected as a testbed. To demonstrate the effectiveness of using the desire for existence, simulation experiments and experiments using mobile robots, WITH, on the robotic field are carried...
We propose to use novelty as one of intrinsic motivations for learning in developmental robotics. Our approach classifies omni-view images taken from a mobile robot, finds outliers, and detects novelty. We use linear discriminant analysis for classification due to its optimality within linear computation. Experimental results demonstrate that although there are many misclassifications, there’s a possibility...
In this paper, the use of two internal reward models, curiosity and boredom, is proposed. Experiments on a maze navigation task demonstrated that appropriate values of parameters simultaneously improved the performance of the predictor of the environment and increase the external rewards compared with the conventional reinforcement learning. In conclusions, the relation between the proposed method...
Reinforcement learning (RL) is suitable for navigation of a mobile robot. We overcame some difficulties of RL which are large computational cost and determination of parameter values for RL with the help of a genetic algorithm (GA) and method of parameter prediction based on results of GA and complexity measure. As a result of these proposals, we succeeded in navigating the real robot practically...
This paper presents an Evolutionary Particle Swarm Optimization (EPSO) for PSO model selection. It provides a new paradigm of meta-optimization that systematically estimates appropriate values of parameters in PSO model for efficiently solving various optimization problems. In order to further investigate the characteristics, i.e., exploitation and exploration in search, of the PSO model optimized...
The trajectory planning is generally an important and difficult problem to solve when robots are required to do some actions. Robots should move in an efficient way satisfying several constraints imposed on them. The constraints include dynamics of the robots, the limitations of values of state and control variables, e.g. imitations of angles and torques of joints, obstacle avoidance and achievement...
In rodents, many forms of behavior (avoidance, food choice, exploring, etc.) have been shown to be transmitted through social interaction. Previous psychological studies have shown that acquisition of avoidance behavior is under the influence of social interaction but detail analyses have not been done. In the present study, we studied how learned avoidance behavior is influenced by interacting with...
We investigated the effect of environmental chemicals on exploratory behavior and emotional behavior in Wistar rats, using behavioral task such as open-field test, elevated plus maze test and forced swimming test. We used green odor and jasmine tea odor as natural environmental chemicals and 1-bromopropane (1-BP) and bisphenol-A (BPA) as artificial environmental chemicals. Green odor did not affect...
The orbitofrontal cortex (OBF) is known to play important roles in evaluation of reward value based on integration of multimodal sensory inputs. In this study, we investigated the complex cognitive functions in the OBF neurons from rhesus monkeys (Macaca mulatta). Glass-coated Elgiloy electrodes and tungsten fiber multi-barreled glass microelectrodes have been used for extracellular recording during...
Autonomous underwater vehicles (AUVs) have great advantages for activities in deep oceans [1], and are expected as the attractive tool for underwater development or investigation near future. However, AUVs have various problems which should be solved such as motion control, acquisition of sensors’ information, behavioral decision, navigation without collision, self-localization and so on. Therefore,...
Recently, various mechanisms have been developed combining linkage mechanisms and wheels. Especially passive linkage mechanisms and small wheel type robots are proposed, because a wheel type mobile mechanism has difficulty on the rough terrain movement. In our research, a 6-wheeled mobile robot employing the linkage mechanism has been developed to enhance maneuverability, and achieved climbing over...
In this paper, in order to realize an effective inspection system, an embedded computer based autonomous pipe inspection robot is presented. This robot is designed as a fully autonomous, un-tethered robot, which fits to the pipes within a diameter range of 200- 300 millimeters. The practical field tests show that the robot performs well and can do pipe inspection properly and the robot moves gracefully...
In our previous study, we showed that the frog, Rana catesbeiana, produces collision avoidance behavior when the retinal size of an approaching object reaches about 20o. In this study, we examined whether the threshold value is unchangeable under any conditions. The avoidance behavior of the frog to looming stimulus moving toward the animal on a collision course was examined...
The medial and lateral perforant pathways (MPP and LPP) conveying spatial and non-spatial information terminate within the middle and the outer 1/3 of the dentate molecular layer, respectively. MPP projection neurons generate subthreshold oscillations, whereas LPP projection neurons do not, implying that the MPP signal is regular and the LPP signal is rather random. In this paper, we investigated...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.