Biologically inspired model of adaptive searching behavior

The computer model of searching adaptive behavior is constructed and investigated. The model describes searching behavior of caddis fly larvae which inhabit creek bottoms and build their cases using hard particles of different size. Using large particles, the larva can build cases more quickly and effectively than with small particles, so it prefers large ones. Inertial switching between search tactics takes place. The model is compared with results of biological experiment. The results of simulation are adequate to biological data. The text was submitted by the authors in English.     

Biologically inspired probabilistic coverage for mobile sensor networks

Coupling sensors in a sensor network with mobility mechanism can boost the performance of wireless sensor networks (WSNs). In this paper, we address the problem of self-deploying mobile sensors to reach high coverage. The problem is modeled as a multi-objective optimization that simultaneously minimizes two contradictory parameters; the total sensor moving distance and the total uncovered area. In order to resolve the aforementioned deployment problem, this study investigates the use of biologically inspired mechanisms, including evolutionary algorithms and swarm intelligence, with their state-of-the-art algorithms. Unlike most of the existing works, the coverage parameter is expressed as a probabilistic inference model due to uncertainty in sensor readings. To the best of our knowledge, probabilistic coverage of mobile sensor networks has not been addressed in the context of multi-objective bio-inspired algorithms. Performance evaluations on deployment quality and deployment cost are measured and analyzed through extensive simulations, showing the effectiveness of each algorithm under the developed objective functions. Simulations reveal that only one multi-objective evolutionary algorithm; the so-called multi-objective evolutionary algorithm with decomposition survives to effectively tackle the probabilistic coverage deployment problem. It gathers more than 78 % signals from all of the targets (and in some cases reaches 100 % certainty). On the other hand, non-dominated sorting genetic algorithm II, multi-objective particle swarm optimization, and non-dominated sorting particle swarm optimization show inferior performance down to 16–32 %, necessitating further modifications in their internal mechanisms.     

Biologically inspired control of quadruped walking robot

In this paper, we present a control method for a quadruped walking robot inspired from the locomotion of quadrupeds. A simple and useful framework for controlling a quadruped walking robot is presented, which is obtained by observing the stimulus-reaction mechanism, the gravity load receptor and the manner of generating repetitive motions from quadrupeds. In addition, we propose a new rhythmic pattern generator that can relieve the large computational burden on solving the kinematics. The proposed method is tested via a dynamic simulation and validated by implementation in a quadruped walking robot, called AiDIN-I (Artificial Digitigrade for Natural Environment I). Recommended by Editorial Board member Sangdeok Park under the direction of Editor Jae-Bok Song. This work was supported by the Korea Research Foundation Grant funded by the Korean Government (MOEHRD) (KRF-2005-D00031). Ig Mo Koo received the B.S. degree in Mechanical Engineering from Myongji University, Yongin, Korea, in 2003, the M.S. degree in Mechanical Engineering from the Sungkyunkwan University, Suwon, Korea, in 2005, where he is currently working toward a Ph.D. degree in Mechanical Engineering from Sungkyunkwan University. His research interests include artificial muscle actuators, haptics, tactile display, biomimetics and quadruped walking robots systems. Tae Hun Kang received the B.S., M.S., and Ph.D. degrees in Mechanical Engineering from Sungkyunkwan University, Korea, in 2000, 2002, and 2006, respectively. His current research interests focus on biomimetics and quadruped walking robot. Gia Loc Vo received the B.S degree in Mechanical Engineering form Ha Noi University of Technology in Vietnam 2003, the M.S. degree Mechanical Engineering form Sungkyunkwan University, Suwon, Korea, in 2006, where he is currently working toward a Ph.D. degree in Mechanical Engineering from Sungkyunkwan University. His research interests include legged locomotion, walking and climbing robot. Tran Duc Trong received the B.S degree in Mechatronics from HoChiMinh City University of Technology in Vietnam in 2005, where he is currently working toward a M.S. degree in Mechanical Engineering from Sungkyunkwan University. His research interests include biological inspired control and adaptive control of quadruped walking robot. Young Kuk Song received the B.S. degree in Mechanical Engineering from Sungkyunkwan University, Suwon, Korea, in 2006, where he is currently working toward a M.S. degree in Mechanical Engineering from Sungkyunkwan University. His research interests include biomimetics, hydraulic robotics system and quadruped walking robot. Hyouk Ryeol Choi received the B.S. degree from Seoul National University, Seoul, Korea, in 1984, the M.S. degree from the Korea Advanced Technology of Science and Technology (KAIST), Daejeon, Korea, in 1986, and the Ph.D. degree from the Pohang University of Science and Technology (POSTECH), Pohang, Korea, in 1994. Since 1995, he has been with Sungkyunkwan University, Suwon, Korea, where he is currently a Professor in the School of Mechanical Engineering. He was an Associate Engineer with LG Electronics Central Research Laboratory, Seoul, Korea, from 1986 to 1989. From 1993 to 1995, he was with Kyoto University, Kyoto, Japan, as a grantee of scholarship funds from the Japanese Educational Administry. He visited the Advanced Institute of Industrial Science Technology (AIST), Tsukuba, Japan, as a JSPS Fellow from 1999 to 2000. He is now an Associate Editor in IEEE Transactions on Robotics, Journal of Intelligent Service Robotics, International Journal of Control, Automation and Systems (IJCAS). His interests includes dexterous mechanisms, field application of robots, and artificial muscle actua tors.     

Biologically inspired collective construction with visual landmarks

We describe our research in using environmental visual landmarks as the basis for completing simple robot construction tasks.Inspired by honeybee visual navigation behavior,a visual template mechanism is proposed in which a natural landmark serves as a visual reference or template for distance determination as well as for navigation during collective construction.To validate our proposed mechanism,a wall construction problem is investigated and a minimalist solution is given.Experimental results show that,using the mechanism of a visual template,a collective robotic system can successfully build the desired structure in a decentralized fashion using only local sensing and no direct communication.In addition,a particular variable,which defines tolerance for alignment of the structure,is found to impact the system performance.By decreasing the value of the variable,system performance is improved at the expense of a longer construction time.The visual template mechanism is appealing in that it can use a reference point or salient object in a natural environment that is new or unexplored and it could be adapted to facilitate more complicated building tasks.     

Biologically inspired visual odometer for navigation of a flying robot

Experimental research in biology has uncovered a number of different ways in which flying insects use cues derived from optical flow for navigational purposes, such as safe landing, obstacle avoidance and dead reckoning. In this study, we use a synthetic methodology to gain additional insights into the navigation behavior of bees. Specifically, we focus on the mechanisms of course stabilization behavior and visually mediated odometer by using a biological model of motion detector for the purpose of long-range goal-directed navigation in 3D environment. The performance tests of the proposed navigation method are conducted by using a blimp-type flying robot platform in uncontrolled indoor environments. The result shows that the proposed mechanism can be used for goal-directed navigation. Further analysis is also conducted in order to enhance the navigation performance of autonomous aerial vehicles.     

A 2-D wavelet decomposition-based bag-of-visual-words model for land-use scene classification

Previous works about spatial information incorporation into a traditional bag-of-visual-words (BOVW) model mainly consider the spatial arrangement of an image, ignoring the rich textural information in land-use remote-sensing images. Hence, this article presents a 2-D wavelet decomposition (WD)-based BOVW model for land-use scene classification, since the 2-D wavelet decomposition method does well not only in textural feature extraction, but also in the multi-resolution representation of an image, which is favourable for the use of both spatial arrangement and textural information in land-use images. The proposed method exploits the textural structures of an image with colour information transformed into greyscale. Moreover, it works first by decomposing the greyscale image into different sub-images using 2-D discrete wavelet transform (DWT) and then by extracting local features of the greyscale image and all the decomposed images with dense regions in which a given image is evenly sampled by a regular grid with a specified grid space. After that, the method generates the corresponding visual vocabularies and computes histograms of visual word occurrences of local features found in each former image. Specifically, the soft-assignment or multi-assignment (MA) technique is employed, accounting for the impact of clustering on visual vocabulary creation that two similar image patches may be clustered into different clusters when increasing the size of visual vocabulary. The proposed method is evaluated on a ground truth image dataset of 21 land-use classes manually extracted from high-resolution remote-sensing images. Experimental results demonstrate that the proposed method significantly outperforms previous methods, such as the traditional BOVW model, the spatial pyramid representation-based BOVW method, the multi-resolution representation-based BOVW method, and so on, and even exceeds the best result obtained from the creator of the land-use dataset. Therefore, the proposed approach is very suitable for land-use scene classification tasks.     

Biologically inspired model of path integration based on head direction cells and grid cells

Some neurons in the brain of freely moving rodents show special firing pattern. The firing of head direction cells (HDCs) and grid cells (GCs) is related to the moving direction and distance, respectively. Thus, it is considered that these cells play an important role in the rodents’ path integration. To provide a bionic approach for the vehicle to achieve path integration, we present a biologically inspired model of path integration based on the firing characteristics of HDCs and GCs. The detailed implementation process of this model is discussed. Besides, the proposed model is realized by simulation, and the path integration performance is analyzed under different conditions. Simulations validate that the proposed model is effective and stable.     

Biologically inspired decision-making in the robot platform MAMoRo

An important step in coming near to building machines with artificial intelligence is by studying and understanding how the human brain works, then applying this knowledge to build machines that “think” using the same concept. MAMoRo (modular autonomous mobile robot) is a general-purpose robot platform targeted at teaching and research in the academia. It consists of three modules: power and motion module, control module, and intelligence module. The decision unit of MAMoRo is distributed into two modules: the control module, which is equipped with a low-cost microcontroller, and handles low-level hardware functions, and the intelligence module, which is equipped with a field-programmable gate array (FPGA) and handles high-level functions. This model of distribution was inspired by the anatomy of the human brain and brings with it many advantages. To prove the concept, MAMoRo was tested with a practical application. This work was presented in part at the First European Workshop on Artificial Life and Robotics, Vienna, Austria, July 12–13, 2007     

Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence

In this paper a novel stereo correspondence algorithm is presented. It incorporates many biologically and psychologically inspired features to an adaptive weighted sum of absolute differences (SAD) framework in order to determine the correct depth of a scene. In addition to ideas already exploited, such as the color information utilization, gestalt laws of proximity and similarity, new ones have been adopted. The presented algorithm introduces the use of circular support regions, the gestalt law of continuity as well as the psychophysically-based logarithmic response law. All the aforementioned perceptual tools act complementarily inside a straightforward computational algorithm applicable to robotic applications. The results of the algorithm have been evaluated and compared to those of similar algorithms.     

Multisensor integration for underwater scene classification

We describe a new approach for the classification of a seafloor that is imaged with high frequency sonar and optical sensors. Information from these sensors is combined to evaluate the material properties of the seafloor. Estimation of material properties is based on the phenomenological relationship between the acoustical image intensity, surface roughness, and intrinsic object properties in the underwater scene. The sonar image yields backscatter estimates, while the optical stereo imagery yields surface roughness parameters. These two pieces of information are combined by a composite roughness model of high-frequency bottom backscattering phenomenon. The model is based on the conservation of acoustic energy travelling across a fluid-fluid interface. The model provides estimates of material density ratio and sound velocity ratio for the seafloor. These parameters serve as physically meaningful features for classification of the seafloor. Experimental results using real data illustrate the usefulness of this approach for autonomous and/or remotely operated undersea activity.Supported by the National Science Foundation Research Initiation Award IRI-91109584.     

Biologically inspired design of a parallel actuated humanoid robot

This paper presents the comparison for the role of bi-articular and mono-articular actuators in human and bipedal robot legs, in particular the hip and knee joint, for driving the design of a humanoid robot with inspirations from the biological system. The various constraints driving the design of both systems are also compared. Additional factors particular to robotic system are identified and incorporated in the design process. To do this, a dynamic simulation is used to determine loading conditions and the forces and power produced by each actuator under various arrangements. It is shown that while the design principles of humans and humanoids are similar, other constraints ensure that robots are still merely inspired by humans, and not direct copies. A simple design methodology that captures the complexity and constraints of such a system in this paper is proposed. Finally, a full-size humanoid robot that demonstrates the newfound principle is highlighted.     

Joint scene classification and segmentation based on hidden Markov model

Scene classification and segmentation are fundamental steps for efficient accessing, retrieving and browsing large amount of video data. We have developed a scene classification scheme using a Hidden Markov Model (HMM)-based classifier. By utilizing the temporal behaviors of different scene classes, HMM classifier can effectively classify presegmented clips into one of the predefined scene classes. In this paper, we describe three approaches for joint classification and segmentation based on HMM, which search for the most likely class transition path by using the dynamic programming technique. All these approaches utilize audio and visual information simultaneously. The first two approaches search optimal scene class transition based on the likelihood values computed for short video segment belonging to a particular class but with different search constrains. The third approach searches the optimal path in a super HMM by concatenating HMM's for different scene classes.     

Learning multi-label scene classification

In classic pattern recognition problems, classes are mutually exclusive by definition. Classification errors occur when the classes overlap in the feature space. We examine a different situation, occurring when the classes are, by definition, not mutually exclusive. Such problems arise in semantic scene and document classification and in medical diagnosis. We present a framework to handle such problems and apply it to the problem of semantic scene classification, where a natural scene may contain multiple objects such that the scene can be described by multiple class labels (e.g., a field scene with a mountain in the background). Such a problem poses challenges to the classic pattern recognition paradigm and demands a different treatment. We discuss approaches for training and testing in this scenario and introduce new metrics for evaluating individual examples, class recall and precision, and overall accuracy. Experiments show that our methods are suitable for scene classification; furthermore, our work appears to generalize to other classification problems of the same nature.     

A comprehensive system for image scene classification

In recent years, image scene classification based on low/high-level features has been considered as one of the most important and challenging problems faced in image processing research. The high-level features based on semantic concepts present a more accurate and closer model to the human perception of the image scene content. This paper presents a new multi-stage approach for image scene classification based on high-level semantic features extracted from image content. In the first stage, the object boundaries and their labels that represent the content are extracted. For this purpose, a combined method of a fully convolutional deep network and a combined network of a two-class SVM-fuzzy and SVR are used. Topic modeling is used to represent the latent relationships between the objects. Hence in the second stage, a new combination of methods consisting of the bag of visual words, and supervised document neural autoregressive distribution estimator is used to extract the latent topics (topic modeling) in the image. Finally, classification based on Bayesian method is performed according to the extracted features of the deep network, objects labels and the latent topics in the image. The proposed method has been evaluated on three datasets: Scene15, UIUC Sports, and MIT-67 Indoor. The experimental results show that the proposed approach achieves average performance improvement of 12%, 11% and 14% in the accuracy of object detection, and 0.5%, 0.6% and 1.8% in the mean average precision criteria of the image scene classification, compared to the previous state-of-the-art methods on these three datasets.

     

Self-learning classification of radar features for scene understanding

Autonomous driving is a challenging problem in mobile robotics, particularly when the domain is unstructured, as in an outdoor setting. In addition, field scenarios are often characterized by low visibility as well, due to changes in lighting conditions, weather phenomena including fog, rain, snow and hail, or the presence of dust clouds and smoke. Thus, advanced perception systems are primarily required for an off-road robot to sense and understand its environment recognizing artificial and natural structures, topology, vegetation and paths, while ensuring, at the same time, robustness under compromised visibility. In this paper the use of millimeter-wave radar is proposed as a possible solution for all-weather off-road perception. A self-learning approach is developed to train a classifier for radar image interpretation and autonomous navigation. The proposed classifier features two main stages: an adaptive training stage and a classification stage. During the training stage, the system automatically learns to associate the appearance of radar data with class labels. Then, it makes predictions based on past observations. The training set is continuously updated online using the latest radar readings, thus making it feasible to use the system for long range and long duration navigation, over changing environments. Experimental results, obtained with an unmanned ground vehicle operating in a rural environment, are presented to validate this approach. A quantitative comparison with laser data is also included showing good range accuracy and mapping ability as well. Finally, conclusions are drawn on the utility of millimeter-wave radar as a robotic sensor for persistent and accurate perception in natural scenarios.     

Learning extremely shared middle-level image representation for scene classification

Learning middle-level image representations is very important for the computer vision community, especially for scene classification tasks. Middle-level image representations currently available are not sparse enough to make training and testing times compatible with the increasing number of classes that users want to recognize. In this work, we propose a middle-level image representation based on the pattern that extremely shared among different classes to reduce both training and test time. The proposed learning algorithm first finds some class-specified patterns and then utilizes the lasso regularization to select the most discriminative patterns shared among different classes. The experimental results on some widely used scene classification benchmarks (15 Scenes, MIT-indoor 67, SUN 397) show that the fewest patterns are necessary to achieve very remarkable performance with reduced computation time.     

Improving multi-label classification using scene cues

Multimedia Tools and Applications - Multi-label classification is one of the most challenging tasks in the computer vision community, owing to different composition and interaction (e.g. partial...