Search

Current robotic studies are focused on the performance of specific tasks. However, such tasks cannot be generalized, and some special tasks, such as compliant and precise manipulation, fast and flexible response, and deep collaboration between humans and robots, cannot be realized. Brain-inspired intelligent robots imitate humans and animals, from inner mechanisms to external structures, through an integration of visual cognition, decision making, motion control, and musculoskeletal systems. This kind of robot is more likely to realize the functions that current robots cannot realize and become human friends. With the focus on the development of brain-inspired intelligent robots, this article reviews cutting-edge research in the areas of brain-inspired visual cognition, decision making, musculoskeletal robots, motion control, and their integration. It aims to provide greater insight into brain-inspired intelligent robots and attracts more attention to this field from the global research community. [ABSTRACT FROM AUTHOR]

This paper presents an event-triggered model predictive control (MPC) strategy with learning terminal cost for robotic manipulators containing model uncertainty and input constraints. In the proposed MPC structure, an adaptive predictive model for the robotic system is established by radial basis function neural networks (RBFNNs) firstly. Then, a terminal cost adjusted by the global learning mechanism is constructed. Both global steady-state optimization and transient fast convergence are achieved by adding the learning terminal cost to the MPC scheme. After that, a triggering condition of the MPC solving is developed based on the predictive model’s weights and the predictive tracking error. Besides, the condition to avoid Zeno behavior is obtained. The recursive feasibility of the proposed MPC strategy is verified, and the ultimately uniformly boundedness (UUB) of all variables is proved according to the Lyapunov theorem. Finally, experiments based on an xMate7 Pro robot are conducted to demonstrate the effectiveness of the presented method. Note to Practitioners—The tracking control of robotic manipulators is a common and important problem in industrial applications, such as grasping, loading, unloading, et al. There exist some limitations in existing control methods. For example, general control strategies such as adaptive control, sliding mode control neglect the balance between control costs and expected performance; existing optimal control approaches rarely consider global steady-state optimization and transient fast convergence under the influence of model uncertainty. This paper is motivated by these limitations of robotic control design and inspired by model predictive control and optimal control theory. It develops a novel strategy for tracking control of robotic manipulators, which includes three following items: (1) adopt an approximation model constructed by neural networks as the predictive model for estimating the robotic system; (2) introduce a critic network into the terminal cost of the objective function of MPC for learning global optimal solution; (3) establish an event-triggered mechanism for solving of the optimization problem. The proposed method is verified by experimental results. In our future work, the proposed control strategy will be applied to more industrial processes. [ABSTRACT FROM AUTHOR]

Adaptation to the operator's intents and the external physical uncertainties is critical to the performances of the human–robot collaboration. In this study, we proposed a control interface that combined the electrical impedance tomography (EIT) based sensing approach with the robotic controllers to produce proper assistance with external uncertainties in the collaborative task. The interface first estimates the continuous forearm muscle contractions (represented by the grasp forces) by the optimized EIT features with an easily worn fabric band. The recognition decisions then serve as the control inputs to adjust the state transitions and the desired interaction forces in real time. We evaluated the interface in the tasks of grasp force estimation and human–robot sawing by recruiting more than 20 subjects in total. For grasp force estimation, the interface produced an average of $R^{2}\geq 0.9$ in both offline and online validations with the feature optimization procedure and a sigmoid regression function. The interface was robust to external disturbances without retraining or manual calibrations. The average $R^{2}=0.86$ with the untrained dynamic postures, and the average $R^{2}$ values ranged from 0.85 to 0.88 in the tests with redonning the front-end in interday and intraday uses. For human–robot sawing, the interface accomplished the tasks with a high success rate in controlling the states ($>$ 96%) and intuitive adjusting of the sawing forces, being combined with the designed hybrid admittance/position controller. It was also adaptive to the sawing frequency changes and the sawing directions according to the operator's intents. The interface's performances are comparable, if not better, to the state of the art on both biological signal based grasp force estimation and human–robot sawing. Future efforts are worth being paid in this new direction to get more promising outcomes. [ABSTRACT FROM AUTHOR]

This article proposes a novel decision-making framework that bridges a gap between model-based (MB) and model-free (MF) control processes through only adjusting the planning horizon. Specifically, the output policy is obtained by solving a model predictive control problem with a locally optimal state value as terminal constraints. When the planning horizon decreases to zero, the MB control will transform into the MF control smoothly. Meanwhile, inspired by the neural mechanism of emotion modulation on decision-making, we build a biologically plausible computational model of emotion processing. This model can generate an uncertainty-related emotional response on the basis of the state prediction error and reward prediction error, and then dynamically modulates the planning horizon in the tasks. The simulation results demonstrate that the proposed decision-making framework can produce better policies than traditional methods. Emotion modulation can shift the MB and MF control well to improve the learning efficiency and the speed of decision-making. [ABSTRACT FROM AUTHOR]

Owing to its potential superiorities in terms of flexibility, compliance, and robustness, the musculoskeletal robotic system has become a promising direction for next-generation robots. However, motion learning and generalization of musculoskeletal systems are still challenging problems. In this article, a muscle-synergies-based neuromuscular control is proposed. First, a new computational model of time-varying muscle synergies is constructed, which utilizes both phasic and tonic muscle synergies to characterize the basic features of muscle excitations more sufficiently. Second, a novel neuromuscular control method is proposed for realizing the motion learning and generalization of musculoskeletal systems. Therein, a radial basis function (RBF) neural network is designed to modulate muscle synergies according to different movement targets. Muscle excitations are computed with the combination of modulated muscle synergies. Covariance matrix adaptation evolutionary strategy is applied to realize the synchronous optimization of muscle synergies and the RBF neural network. In the experiment, a sophisticated musculoskeletal system learns to perform center-out reaching tasks through trial-and-error learning on a few targets. With the muscle synergies and neural modulation learned from a few targets, the musculoskeletal system can also reach many unexperienced targets. The proposed method not only improves the speed and accuracy of motion learning but also enhances motion generalization. This article also promotes the development of the musculoskeletal robotic system and the fusion of neuroscience and robotics. [ABSTRACT FROM AUTHOR]

In this article, an adaptive neural network control scheme is presented for an uncertain wheeled mobile robot (WMR) with velocity constraints and nonholonomic constraints. In practice, dynamic parameters of the system, which may change in some conditions, are hard to obtain precisely, and the velocity of the WMR should be constrained for safety. To deal with the uncertainty of the robot, adaptive neural networks are used to approximate unknown robotic dynamics, and the barrier Lyapunov function is used to guarantee the constraint on velocity. The tracking error of the closed-loop system is proven to converge to a small neighborhood of zero. Both simulation studies and practical experiments are provided to illustrate the effectiveness of the proposed control scheme. [ABSTRACT FROM AUTHOR]

This letter proposes a lightweight two-stream convolutional neural network (CNN) for synthetic aperture radar (SAR) target recognition. Specifically, the two-stream CNN first extracts low-level features by three alternating convolution layers and max-pooling layers. Then two streams are followed to extract local and global features. One stream uses global maximum pooling to extract local features with the greatest response; the other uses large-stride convolution kernels to extract global features. Finally, the two streams are combined for target recognition. Therefore, the two-stream CNN can learn rich multilevel features to achieve high recognition accuracy for SAR target recognition. Moreover, compared to other popular CNNs, the two-stream CNN is very lightweight. The experimental results on the moving and stationary target acquisition and recognition (MSTAR) data set demonstrate that the proposed method not only can improve the recognition accuracy but also reduce the number of parameters of the model dramatically. [ABSTRACT FROM AUTHOR]

Feature correspondence lays the foundation for many computer vision and image processing tasks, which can be well formulated and solved by graph matching. Because of the high complexity, approximate methods are necessary for graph matching, and the continuous relaxation provides an efficient approximate scheme. But there are still many problems to be settled, such as the highly nonconvex objective function, the ignorance of the combinatorial nature of graph matching in the optimization process, and few attention to the outlier problem. Focusing on these problems, this paper introduces a continuation method directly targeting at the combinatorial optimization problem associated with graph matching. Specifically, first a regularization function incorporating the original objective function and the discrete constraints is proposed. Then a continuation method based on Gaussian smoothing is applied to it, in which the closed forms of relevant functions with respect to the outlier distribution are deduced. Experiments on both synthetic data and real world images validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Grasping and assembly are essential tasks in high-precision robotic manipulation for industrial manufacturing as well as for home service applications. Many efforts have been devoted to this area in an attempt to meet the increasing precision requirement of the task. However, it remains a problematic objective to fulfill high precision, high reliability, high speed, and high flexibility all at once during one robotic manipulation task. To find answers to the above-mentioned problem, this article tries to categorize, review, and compare the recent works focusing on robotic grasping and assembly tasks to reveal some potential trends in this research area. The approaches will be divided into five groups based on the difference in the utilization of sensing or constraints. For each part, robotic grasping and assembly will be treated as practical cases to illustrate the concrete work in that area. This article could give the readers some knowledge on the current developments in robotic manipulation, and provide new thoughts on future direction in this area—inspiring new designs, structures, and systems to meet new requirements in applications in industrial manufacturing and home service. [ABSTRACT FROM AUTHOR]

Locomotion mode recognition across multiple sessions and days is an indispensable step towards the practical use of the robotic transtibial prosthesis. In this study, we proposed an adaptive recognition strategy to against the time-varying features of on-prosthesis mechanical signals in inter-session and inter-day recognition tasks. The strategy was designed with an automatic training algorithm which could update the classifiers with the data of the most recent completed gait cycles to seize the changes of the features brought by external disturbances. After implementation, we measured multiple experimental sessions on six transtibial amputees with intervals from a few hours (inter-session experiment) to several months (108 days at most in inter-day experiment). In each session, they performed five locomotion modes and eight locomotion transitions using the robotic prosthesis. Between each two experimental sessions, the subjects were required to doff the robotic prosthesis (including the socket). The proposed adaptive recognition algorithm significantly improved recognition accuracies in both experiments. In inter-session experiment, the proposed method increased the recognition accuracy from 89.3% to 92.8% than previous non-adaptive recognition method. In inter-day experiments, it increased the recognition accuracy from 60% to 88.8%. If taking three modes (level walking, stair ascending/descending) and four locomotion transitions into calculation, the recognizer produced an accuracy up to 96.6% (swing phase) for static mode and an accuracy of 96.9% for locomotion transitions on inter-day tasks without manual intervenes. Compared with state-of-the-art, our study extends the ability of the robotic transtibial prosthesis in locomotion mode recognition across multiple sessions and days. Future efforts are worth being paid in this direction to get more promising results. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) data are sequentially acquired and usually large scale. Fast and accurate classification is particularly important for their applications. By introducing online learning, the PolSAR system can learn a classification model incrementally from a stream of instances, which is of high efficiency for newly arrived samples processing, strong adaptability for a dynamically changing environment, and excellent scalability for rapidly increasing data. In this paper, we propose an Online Multi-view Passive-Aggressive learning algorithm, named OMPA, for PolSAR data real-time classification. The polarimetric, color, and texture features are extracted to characterize PolSAR data, and each type of features corresponds to one view. In order to exploit the consistency and complementary property of these views, we give a new optimization model that ensembles the classifiers of multiple distinct views and enforces the agreement between each predictor and the combined predictor. The corresponding algorithms for both binary and multiclass classification tasks are derived, and the update steps have analytical solutions. In addition, we rigorously derive a bound on the number of prediction mistakes of the method. The proposed OMPA algorithm is evaluated on two real PolSAR datasets for built-up areas extraction and land cover classification, respectively. Experimental results demonstrate that OMPA consistently maintains a smaller mistake rate with low time cost and achieves about 1% and 2% accuracy improvements on the datasets, respectively, compared with the best results of the previously known online single-view and multiview learning methods. [ABSTRACT FROM AUTHOR]

Policy search in reinforcement learning (RL) is a practical approach to interact directly with environments in parameter spaces, that often deal with dilemmas of local optima and real-time sample collection. A promising algorithm, known as guided policy search (GPS), is capable of handling the challenge of training samples using trajectory-centric methods. It can also provide asymptotic local convergence guarantees. However, in its current form, the GPS algorithm cannot operate in sequential multitask learning scenarios. This is due to its batch-style training requirement, where all training samples are collectively provided at the start of the learning process. The algorithm’s adaptation is thus hindered for real-time applications, where training samples or tasks can arrive randomly. In this paper, the GPS approach is reformulated, by adapting a recently proposed, lifelong-learning method, and elastic weight consolidation. Specifically, Fisher information is incorporated to impart knowledge from previously learned tasks. The proposed algorithm, termed sequential multitask learning-GPS, is able to operate in sequential multitask learning settings and ensuring continuous policy learning, without catastrophic forgetting. Pendulum and robotic manipulation experiments demonstrate the new algorithms efficacy to learn control policies for handling sequentially arriving training samples, delivering comparable performance to the traditional, and batch-based GPS algorithm. In conclusion, the proposed algorithm is posited as a new benchmark for the real-time RL and robotics research community. [ABSTRACT FROM AUTHOR]

This letter proposes a novel multiview feature extraction method for supervised polarimetric synthetic aperture radar (PolSAR) image classification. PolSAR images can be characterized by multiview feature sets, such as polarimetric features and textural features. Canonical correlation analysis (CCA) is a well-known dimensionality reduction (DR) method to extract valuable information from multiview feature sets. However, it cannot exploit the discriminative information, which influences its performance of classification. Local discriminant embedding (LDE) is a supervised DR method, which can preserve the discriminative information and the local structure of the data well. However, it is a single-view learning method, which does not consider the relation between multiple view feature sets. Therefore, we propose local discriminant CCA by incorporating the idea of LDE into CCA. Specific to PolSAR images, a symmetric version of revised Wishart distance is used to construct the between-class and within-class neighboring graphs. Then, by maximizing the correlation of neighboring samples from the same class and minimizing the correlation of neighboring samples from different classes, we find two projection matrices to achieve feature extraction. Experimental results on the real PolSAR data sets demonstrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

Automatic assembly with high precision is an essential step in robotic manipulation. It is still a difficult problem due to various complicated requirements, such as less contact force, irregular shapes of the parts, sensing information understanding in complex environment, etc. In the previous work, the concept of attractive region in environment (ARIE) was proposed, which helps to achieve high-precision manipulation with low-precision systems by using the constraints formed by the environment. In this paper, the general relation between the physical space and the configuration space for the robotic assembly system will be analyzed, the strategies of using ARIE to achieve high-precision peg-hole assembly will be provided, and furthermore, practical examples for industrial applications will be given, which further illustrates the usefulness of the concept. [ABSTRACT FROM PUBLISHER]

In various industries, there is a need for low-cost, flexible robotic grasping systems that handle and classify different items, which usually involve low-cost grippers and reliable manipulations. One-degree-offreedom (1-DoF) two-pin or three-pin grippers are widely used in the automation of manufacturing processes because of their low cost and high reliability. However, some uncertainties introduced by the object and the gripper may affect the robustness of the grasp. The principle of caging enables us to deal with these uncertainties, and it is therefore important to study caging as a practical solution to improve the grasps of 1-DoF industrial grippers. [ABSTRACT FROM AUTHOR]

Recently, many biologically inspired visual computational models have been proposed. The design of these models follows the related biological mechanisms and structures, and these models provide new solutions for visual recognition tasks. In this paper, based on the recent biological evidence, we propose a framework to mimic the active and dynamic learning and recognition process of the primate visual cortex. From principle point of view, the main contributions are that the framework can achieve unsupervised learning of episodic features (including key components and their spatial relations) and semantic features (semantic descriptions of the key components), which support higher level cognition of an object. From performance point of view, the advantages of the framework are as follows: 1) learning episodic features without supervision—for a class of objects without a prior knowledge, the key components, their spatial relations and cover regions can be learned automatically through a deep neural network (DNN); 2) learning semantic features based on episodic features—within the cover regions of the key components, the semantic geometrical values of these components can be computed based on contour detection; 3) forming the general knowledge of a class of objects—the general knowledge of a class of objects can be formed, mainly including the key components, their spatial relations and average semantic values, which is a concise description of the class; and 4) achieving higher level cognition and dynamic updating—for a test image, the model can achieve classification and subclass semantic descriptions. And the test samples with high confidence are selected to dynamically update the whole model. Experiments are conducted on face images, and a good performance is achieved in each layer of the DNN and the semantic description learning process. Furthermore, the model can be generalized to recognition tasks of other objects with learning ability. [ABSTRACT FROM PUBLISHER]

A precise robotic assembly for large-scale objects is an important application in manufacture. In this paper, we design a new assembly system for large-scale objects based on automatic guidance and alignment with two cameras and three laser distance sensors. The corresponding strategy consists of three stages. First, the object is guided from a remote position to a close one based on our proposed link-line model-based polygon detection and Computer Aided Design (CAD) - View method. Second, the object is aligned to the installation framework based on the proposed visual and laser alignment method. Finally, the object is automatically inserted into the installation framework. An accurate easily applying and close-loop hand-eye calibration method is also proposed. The proposed assembly system has high assembly precision and efficiency. In our test for a 710 \text mm \times 625 mm optical module, the maximum 6-DOF localization error of guidance and alignment is 0.53 mm in translation and 0.10° in orientation. The mechanical constraint-based controlling accuracy, i.e., the final assembly accuracy, is up to 0.2 mm in translation. [ABSTRACT FROM PUBLISHER]

This letter proposes a method that can preserve the global and local discriminative information based on the tensor representation to achieve feature extraction for synthetic aperture radar (SAR) target configuration recognition. We model SAR images of targets with different configurations as different manifolds, and each manifold is represented as a collection of maximal linear patches (MLPs), each depicted by a subspace. The manifold-to-manifold distance and subspace-to-subspace distance are used to maintain the global discriminative structure of data. Meanwhile, point-to-point distance (PPD) in an MLP is exploited to keep the local discriminative information of data. These two terms are then integrated to maintain the structure of data. Experimental results on the moving and stationary target automatic recognition (MSTAR) database demonstrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

Recently, many computational models have been proposed to simulate visual cognition process. For example, the hierarchical Max-Pooling (HMAX) model was proposed according to the hierarchical and bottom-up structure of V1 to V4 in the ventral pathway of primate visual cortex, which could achieve position- and scale-tolerant recognition. In our previous work, we have introduced memory and association into the HMAX model to simulate visual cognition process. In this paper, we improve our theoretical framework by mimicking a more elaborate structure and function of the primate visual cortex. We will mainly focus on the new formation of memory and association in visual processing under different circumstances as well as preliminary cognition and active adjustment in the inferior temporal cortex, which are absent in the HMAX model. The main contributions of this paper are: 1) in the memory and association part, we apply deep convolutional neural networks to extract various episodic features of the objects since people use different features for object recognition. Moreover, to achieve a fast and robust recognition in the retrieval and association process, different types of features are stored in separated clusters and the feature binding of the same object is stimulated in a loop discharge manner and 2) in the preliminary cognition and active adjustment part, we introduce preliminary cognition to classify different types of objects since distinct neural circuits in a human brain are used for identification of various types of objects. Furthermore, active cognition adjustment of occlusion and orientation is implemented to the model to mimic the top-down effect in human cognition process. Finally, our model is evaluated on two face databases CAS-PEAL-R1 and AR. The results demonstrate that our model exhibits its efficiency on visual recognition process with much lower memory storage requirement and a better performance compared with the traditional purely computational methods. [ABSTRACT FROM PUBLISHER]

High-precision manipulation is very important for a variety of tasks in manufacturing. In general, high-precision manipulation is usually achieved by the guidance of high-precision sensors; however, sensorless methods, for some special cases, are more reliable and effective. There are many important works in this aspect [1]–[3]. The concept of “attractive region in environment” (ARIE), which was proposed in our previous works [4]–[6], provides a prospective approach for low-precision systems to achieve high-precision manipulation. It has been used in various industrial applications, such as robotic assembly [7], grasping [8], and localization [9]. ARIE is a region from any point of which the uncertainty of the system can be eliminated by a state-independent input. The utilization of attractive region can be easily understood by the case of a bean in a bowl. For a bean in a bowl, no matter where the initial position of the bean is, it will move to and finally stay at the bottom of the bowl under gravity. Thus, the uncertainty of the bean is eliminated by gravity without any sensor feedback. Inspired by the above case, the general concept of ARIE is proposed and is applied to industry. In this paper, we review the application of ARIE and give its formal definition. Furthermore, we establish conditions for the existence of ARIE in the generalized configuration space, which is complex and nonideal. The relationship between the high-dimensional attractive region and the low-dimensional one is also discussed, which is helpful to make feasible and reliable manipulation strategies in the low-dimensional configuration space. The main contribution of this paper is the generalization of the concept of ARIE, which provides a theoretical foundation for applications including the high-precision manipulation with low-precision system. The experimental simulations on different kinds of complex manipulations show the effectiveness of the proposed method for industrial applications. [ABSTRACT FROM PUBLISHER]

In this letter, we propose a novel saliency model for saliency detection, named sparse-distinctive (SD) saliency model. Different from the existing models that only consider sparsity or distinctness of image, the proposed model computes saliency based on sparsity and distinctness. The basic idea is that sparsity and distinctness contribute to saliency simultaneously and play different roles under different scenes. This sparse-distinctive saliency model is based on some key ideas introduced in this letter and supported by psychological evidence. Experimental results on public benchmark eye-tracking datasets show that considering the sparsity and distinctness for saliency can improve the accuracy of predicting human fixations, and the proposed model outperforms the mainstream models on predicting human fixations. [ABSTRACT FROM AUTHOR]

Reports on RASS Society activity in China. [ABSTRACT FROM PUBLISHER]

Development of a flexible low-cost robotic system to grasp various 3D workpieces is of practical important. Traditional approaches on 3D grasping usually need to compute the effective contact positions based on sufficient conditions, such as “force-closure” or “form-closure,” to prevent all the motions of the grasped objects. Compared with the previous work motivated by high-precision applications, caging provides a way to manipulate an object without needing to immobilize it. However, most caging conditions consider only 2D motions of the object in grasping. In some cases, other motions in 3D space, e.g., the pitch and roll rotations of the objects, would also possibly change a caging configuration to an uncaging configuration. This paper aims to discuss caging with frictionless contact, by taking into consideration of all the motions of the object. We first discuss the relationship between the gripper configuration and the state of the grasped object in grasping, where all the motions of the object are taken into account. We then establish the sufficient conditions to find a set of 3D caging configurations in terms of the width of the object's projection and the gap of the gripper, such that we can utilize the projection to find the feasible placements of the pins to determine the caging configuration. Furthermore, we discuss how to find the caging configuration that is capable of leading to a form-closure based on attractive region formed in the configuration space. [ABSTRACT FROM PUBLISHER]

Graph regularized Sparse Coding (GSC) considers data relationships during Sparse Coding (SC) and thus has better performance in certain image analysis tasks. However, it is very time consuming. This letter aims at speeding up GSC. The alternating optimization framework for GSC involves repeatedly solving a variant of \ell _1 minimization referred to as GSRsub in this letter. Traditional ways to deal with GSRsub are to generalize optimization strategies for \ell _1 minimization to solve its primal problem that is strongly convex but non-differentiable, thus converging slowly. We propose that GSC can be accelerated by solving a new dual problem of GSRsub called D-GSRsub. Compared with the primal form and the existing dual form of GSRsub, D-GSRsub has a strongly convex and smooth objective function with less variables. Based on these properties, four dual gradient ascent strategies with lower computational complexities are developed. Experimental results on real-world datasets demonstrate that these strategies can dramatically and stably speed up GSC without affecting its performance in the corresponding image analysis tasks. [ABSTRACT FROM AUTHOR]

Control gains play an important role in the control of a natural or a technical system since they reflect how much resource is required to optimize a certain control objective. This paper is concerned with the controllability of neuronal networks with constraints on the average value of the control gains injected in driver nodes, which are in accordance with engineering and biological backgrounds. In order to deal with the constraints on control gains, the controllability problem is transformed into a constrained optimization problem (COP). The introduction of the constraints on the control gains unavoidably leads to substantial difficulty in finding feasible as well as refining solutions. As such, a modified dynamic hybrid framework (MDyHF) is developed to solve this COP, based on an adaptive differential evolution and the concept of Pareto dominance. By comparing with statistical methods and several recently reported constrained optimization evolutionary algorithms (COEAs), we show that our proposed MDyHF is competitive and promising in studying the controllability of neuronal networks. Based on the MDyHF, we proceed to show the controlling regions under different levels of constraints. It is revealed that we should allocate the control gains economically when strong constraints are considered. In addition, it is found that as the constraints become more restrictive, the driver nodes are more likely to be selected from the nodes with a large degree. The results and methods presented in this paper will provide useful insights into developing new techniques to control a realistic complex network efficiently. [ABSTRACT FROM PUBLISHER]

A famous biologically inspired hierarchical model (HMAX model), which was proposed recently and corresponds to V1 to V4 of the ventral pathway in primate visual cortex, has been successfully applied to multiple visual recognition tasks. The model is able to achieve a set of position- and scale-tolerant recognition, which is a central problem in pattern recognition. In this paper, based on some other biological experimental evidence, we introduce the memory and association mechanism into the HMAX model. The main contributions of the work are: 1) mimicking the active memory and association mechanism and adding the top down adjustment to the HMAX model, which is the first try to add the active adjustment to this famous model and 2) from the perspective of information, algorithms based on the new model can reduce the computation storage and have a good recognition performance. The new model is also applied to object recognition processes. The primary experimental results show that our method is efficient with a much lower memory requirement. [ABSTRACT FROM PUBLISHER]

In this paper we propose the graduated nonconvexity and concavity procedure (GNCCP) as a general optimization framework to approximately solve the combinatorial optimization problems defined on the set of partial permutation matrices. GNCCP comprises two sub-procedures, graduated nonconvexity which realizes a convex relaxation and graduated concavity which realizes a concave relaxation. It is proved that GNCCP realizes exactly a type of convex-concave relaxation procedure (CCRP), but with a much simpler formulation without needing convex or concave relaxation in an explicit way. Actually, GNCCP involves only the gradient of the objective function and is therefore very easy to use in practical applications. Two typical related NP-hard problems, partial graph matching and quadratic assignment problem (QAP), are employed to demonstrate its simplicity and state-of-the-art performance. [ABSTRACT FROM PUBLISHER]

In this letter, we propose a semi-supervised dimensionality reduction method named Discriminative Sparsity Preserving Projection (DSPP). In order to get the feature mapping f which projects the high-dimensional data into a low-dimensional intrinsic space, DSPP attempts to maintain the prior low-dimensional representation constructed by the data points and the known class labels and, meanwhile, considers the complexity of f in the ambient space and the smoothness of f in preserving the sparse representation of data. On one hand, the DSPP method obtains an explicit nonlinear feature mapping for the out-of-sample extrapolation. On the other hand, the DSPP method has a high discriminative ability which is inherited from the sparse representation of data. Experiment results show the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

Manifold learning has been a popular method in many areas such as classification and recognition. In this paper, we propose a novel algorithm for pedestrian tracking based on our previous work on manifold learning. A new kind of manifold subspace is introduced, in which the intrinsic features of the target's motion can be best preserved, and the dimensionality of feature is very low. In the proposed subspace, variations of continuous pedestrian postures can be represented well by these intrinsic features. This also validates our conjecture that the movement of pedestrians can be described by some intrinsic and low-dimensional features, which are significant for tracking. Although intrinsic features are useful for tracking, algorithms that directly apply intrinsic features could not guarantee stable performance due to the influence from a complicated background. To address this issue, a foreground extraction method is introduced to enhance tracking stability by selecting the most discriminative color features to automatically distinguish the foreground from the candidate image. This preprocessing stage is proven to promote the accuracy of low-dimensional feature representation in pedestrian tracking. The whole tracking procedure, particularly dimensionality reduction, is linear and fast without complicated calculations. The experimental results validate the effectiveness of our algorithm under challenging conditions, such as a complex background, various pedestrian postures, and even occlusion. [ABSTRACT FROM PUBLISHER]

In general, localization is a very important step in the manufacturing process, which can be considered as a prior process of assembly, machining, transportation, etc. Localization can be achieved with or without sensors. Compared with localization with sensors, localization without sensors can be more reliable, cheaper, and can have lower requirements on the environment. For example, localization without sensors can be achieved in a dark environment. However, it is more restrictive to the condition of the system. Localization of 2-D objects without sensors has been deeply investigated. Some theoretical results on 3-D-object localization without sensors have been given. On the other hand, some work has been carried out that tries to find methods to reduce uncertainties in the 3-D orientation of a polyhedron (i.e., the orientation of the polyhedron in a 3-D space). However, to the best of our knowledge, no practical and effective methods have been proposed, so far, to localize a polyhedron from any initial 3-D orientation to a unique 3-D orientation without sensors. This paper aims to find conditions and strategies for 3-D objects to be rotated from an unknown initial stable state to a unique stable state without sensors. The main contributions of this paper are given as follows: 1) It is discovered and proved that there are two classes of 3-D objects that can be rotated into a unique state from an arbitrary initial state without sensory feedback. 2) For these two classes of objects, the practical strategies are presented, and one example for each class is given to show the validity of the strategy. 3) Based on the above results, the robotic system and localization operations are illustrated, and some experimental results are given. [ABSTRACT FROM PUBLISHER]

Several adaptive visual tracking algorithms have been recently proposed to capture the varying appearance of target. However, adaptability may also result in the problem of gradual drift, especially when the target appearance changes drastically. This paper gives some theoretical principles for online learning of target model, and then presents a novel adaptive tracking algorithm which is able to effectively cope with drastic variations in target appearance and resist gradual drift. Once target is localized in each frame, the patches sampled from target observation are first classified into foreground and background using an effective classifier. Then the adaptive, pure and time-continuous target model is extracted online through two processes: absorption process and rejection process, through which only the reliable features with high separability are absorbed in the new target model, while the “dangerous” features which may cause interfusion of background patterns are rejected. To minimize the influence of background and keep the temporal continuity of target model, two collaborative models dominant model and continuous model are designed. The proposed learning and generation mechanisms of target model are finally embedded in an adaptive tracking system. Experimental results demonstrate the robust performance of the proposed algorithm under challenging conditions. [ABSTRACT FROM AUTHOR]

Classification-based pedestrian detection systems (PDSs) are currently a hot research topic in the field of intelligent transportation. A PDS detects pedestrians in real time on moving vehicles. A practical PDS demands not only high detection accuracy but also high detection speed. However, most of the existing classification-based approaches mainly seek for high detection accuracy, while the detection speed is not purposely optimized for practical application. At the same time, the performance, particularly the speed, is primarily tuned based on experiments without theoretical foundations, leading to a long training procedure. This paper starts with measuring and optimizing detection speed, and then a practical classification-based pedestrian detection solution with high detection speed and training speed is described. First, an extended classification/detection speed metric, named feature-per-object (fpo), is proposed to measure the detection speed independently from execution. Then, an fpo minimization model with accuracy constraints is formulated based on a tree classifier ensemble, where the minimum fpo can guarantee the highest detection speed. Finally, the minimization problem is solved efficiently by using nonlinear fitting based on radial basis function neural networks. In addition, the optimal solution is directly used to instruct classifier training; thus, the training speed could be accelerated greatly. Therefore, a rapid and accurate classification-based detection technique is proposed for the PDS. Experimental results on urban traffic videos show that the proposed method has a high detection speed with an acceptable detection rate and a false-alarm rate for onboard detection; moreover, the training procedure is also very fast. [ABSTRACT FROM AUTHOR]

In this paper, a novel methodology called a reference model approach to stability analysis of neural networks is proposed. The core of the new approach is to study a neural network model with reference to other related models, so that different modeling approaches can be combinatively used and powerfully cross-fertilized. Focused on two representative neural network modeling approaches (the neuron state modeling approach and the local field modeling approach), we establish a rigorous theoretical basis on the feasibility and efficiency of the reference model approach. The new approach has been used to develop a series of new, generic stability theories for various neural network models. These results have been applied to several typical neural network systems including the Hopfield-type neural networks, the recurrent back-propagation neural networks, the BSB-type neural networks, the bound-constraints optimization neural networks, and the cellular neural networks. The results obtained unify, sharpen or generalize most of the existing stability assertions, and illustrate the feasibility and power of the new method. [ABSTRACT FROM AUTHOR]

The path following algorithm was proposed recently to approximately solve the matching problems on undirected graph models and exhibited a state-of-the-art performance on matching accuracy. In this paper, we extend the path following algorithm to the matching problems on directed graph models by proposing a concave relaxation for the problem. Based on the concave and convex relaxations, a series of objective functions are constructed, and the Frank-Wolfe algorithm is then utilized to minimize them. Several experiments on synthetic and real data witness the validity of the extended path following algorithm. [ABSTRACT FROM PUBLISHER]