Robust comprehension of natural language instructions by a domestic service robot

We present a method through which domestic service robots can comprehend natural language instructions. For each action type, a variety of natural language expressions can be used, for example, the instruction, ‘Go to the kitchen’ can also be expressed as ‘Move to the kitchen.’ We are of the view that natural language instructions are intuitive and, therefore, constitute one of the most user-friendly robot instruction methods. In this paper, we propose a method that enables robots to comprehend instructions spoken by a human user in his/her natural language. The proposed method combines action-type classification, which is based on a support vector machine, and slot extraction, which is based on conditional random fields, both of which are required in order for a robot to execute an action. Further, by considering the co-occurrence relationship between the action type and the slots along with the speech recognition score, the proposed method can avoid degradation of the robot’s comprehension accuracy in noisy environments, where inaccurate speech recognition can be problematic. We conducted experiments using a Japanese instruction data-set collected using a questionnaire-based survey. Experimental results show that the robot’s comprehension accuracy is higher in a noisy environment using our method than when using a baseline method with only a 1-best speech recognition result.     

Terrain classification and identification of tree stems using ground‐based LiDAR

To operate autonomously in forested terrain, unmanned ground vehicles must be able to identify the load‐bearing surface of the terrain (i.e., the ground) and obstacles in the environment. To travel long distances, they must be able to track their position even when the forest canopy obstructs GPS signals, e.g., by tracking progress relative to tree stems. This paper presents a novel, robust approach for modeling the ground plane and tree stems in forests from a single viewpoint using a lightweight LiDAR scanner. Ground plane identification is implemented using a two‐stage approach. The first stage, a local height‐based filter, discards most nonground points. The second stage, based on a support vector machine classifier, identifies which of the remaining points belong to the ground. Main tree stems are modeled as cylinders or cones to estimate the diameter 130 cm above the ground plane. To fit these models, candidate main stem data are selected by finding points approximately 130 cm above the ground. These points are clustered into separate point clouds for each stem. Cylinders and cones are fit to each point cloud, and heuristic filters identify which fits correspond to tree stems. Experimental results from five forested environments demonstrate the effectiveness of this approach. For ground plane estimation, the overall classification accuracy was 86.28% with a mean error for the ground height of approximately 4.7 cm. For stem estimation, up to 50% of the main stems were accurately modeled using cones, with a root mean square diameter error of 13.2 cm.© 2012 Wiley Periodicals, Inc.     

Traversable Region Estimation for Mobile Robots in an Outdoor Image

This paper describes a novel method to estimate appropriate traversable regions from an outdoor scene image. The traversable regions output by the proposed method reflect the common sense of people. For example, a candidate traversable region is “a paved road somewhat distant from the side ditch.” The input to the traversable region estimation is one color image. First, category is assigned to each pixel in the image. The categorization result is then input to the region estimator. Finally, the traversable region are estimated on the input image. An important aspect of this method is the application of two score functions in region estimation process. One score function places high value on categories selected as traversable paths by subjects. The other function places high value on categories that are not selected as traversable regions but are adjacent to categories with traversable paths. A combination of these two functions produces feasible estimation results. The effectiveness of the combined score functions was evaluated by experiments and a questionnaire.     

Analysis of spatial smoothing effect of short‐term fluctuation of global solar radiation based on data including quantization error

Photovoltaic (PV) systems are attracting attention as one of the promising countermeasures against global warming and the environmental issues. However, the generation output from PV systems is generally unstable and unpredictable. Therefore, large penetration of PV systems may cause some serious impacts on power system operation, such as load frequency control, voltage regulation, etc. Estimation of the influences of PV system installation is becoming important, but it requires simultaneous multipoint solar radiation measurements. The Japan Meteorological Business Support Center has provided 1‐minute meteorological data observed in Japan, but its solar radiation data includes quantization errors. This paper proposes a regeneration method for solar radiation data including quantization errors. It also analyzes the spatial smoothing effect of global solar radiation fluctuations. © 2012 Wiley Periodicals, Inc. Electr Eng Jpn, 180(3): 55–63, 2012; Published online in Wiley Online Library ( wileyonlinelibrary.com ). DOI 10.1002/eej.21274     

Abstract picture generation and zooming user interface for intuitive music browsing

Today many people store music media files in personal computers or portable audio players, thanks to recent evolution of multimedia technologies. The more music media files these devices store, the messier it is to search for tunes that users want to listen to. We propose MusCat, a music browser to interactively search for the tunes according to features, not according to metadata (e.g. title, artist name). The technique firstly calculates features of tunes, and then hierarchically clusters the tunes according to the features. It then automatically generates abstract pictures, so that users can recognize characteristics of tunes more instantly and intuitionally. It finally visualizes the tunes by using abstract pictures. MusCat enables intuitive music selection with the zooming user interface.     

Grain Boundary Segregation Behavior of Boron in Low-Alloy Steel

The boron concentration profiles around prior austenite grain boundaries in Fe-0.05C-0.5Mo-0.001B (mass pct) are examined using aberration-corrected STEM-EELS. In order to obtain the precise distribution of boron around the boundaries, tilt series measurements with thin specimens (<30 nm) are performed and the EEL spectra are analyzed by principal component analysis (PCA) and multivariate curve resolution (MCR). The boron concentration profile changes with the cooling rate from the solid solution temperature. The concentration at grain boundaries is maximized at a medium rate (30 °C/s), where the concentration reaches 8 at. pct, and it decreases at a larger (250 °C/s) or smaller (5 °C/s) rate. On the other hand, the boron distribution becomes wider as the cooling rate becomes smaller. The current results suggest that the boron segregation in the alloy is formed by the “non-equilibrium segregation mechanism.”     

Optimal operation of cogeneration system coordinated by aggregator for providing the demand and supply regulation capacity

Recent growth of renewable energy generations with natural variability, such as photovoltaic generation and wind turbine generation, would make the demand and supply control in a whole power system more difficult, and therefore, alternatives for demand and supply regulation resources would be required. The authors focus on cogeneration system (CGS) as one of regulation resources. In order to procure adequate volume of regulation capability, an aggregator coordinates a number of CGSs efficiently and flexibly considering the wide variety of electricity/thermal demands of CGS owners. This paper proposes a novel optimal operation strategy of CGS coordinated by the aggregator considering the energy balance and operation cost of individual CGS owner. This paper also demonstrates the availability of CGSs for regulation capability by numerical case studies in which the actual consumption profile is employed.     

Estimation of anisotropic properties of nano-structured arrays by modal vibration control at microscale

Nano-structured arrays are engineered to meet the requirements of a variety of applications such as microfilters, sensors, and structural interface due to their unique mechanical characteristics, which cannot be achieved by conventional solid materials. However, it is hard to evaluate the elastic properties of nano-structured arrays owing to the discrete structure, sample size, and availability of suitable techniques. To facilitate this, we develop an advanced three-dimensional microscale vibration testing process. In the test, a specially designed three-dimensional microspecimen with tuned mass is excited by a piezoelectric actuator, and the resonance frequencies are detected by a laser device successfully. The anisotropic elastic moduli of nano-structured array composed of helical nano-springs are identified from a single spectrum. This array shows so strong characteristic anisotropy that the solid one hardly can attain. The microscale testing technique can be extended to other materials and microstructures.