The inability to identify the optimal construction of a nerve guidance conduit (NGC) for peripheral nerve regeneration is a challenge in the field of tissue engineering. This is attributed to the vast number of parameters that can be combined in varying quantities. A pre-existing normalization standard is applied in this paper which uses a calculated ratio of gap length divided by the graft's critical axon elongation denoted as L/Lc. This allows for a direct comparison of the nerve regenerative activity, a measure of performance, of any NGC across an array of gap lengths relative to a standard nerve conduit. Data was extracted from a total of 28 scientific publications that compared the nerve regenerative activity of experimental NGCs relative to standard NGCs. Of the extracted data, 40 parameters were identified that impacted the performance of the experimental conduits. We demonstrate how bootstrap aggregated neural networks provides substantial increases in accuracy in predicting the performance of a NGC over a single neural network and previous prediction attempts by the SWarm Intelligence based Reinforcement Learning (SWIRL) system. The improved accuracy will provide for a better understanding and insight for theorizing successful strategies for NGC development.

It is desirable to self-organize mobile sensor networks to form different yet suitable patterns to adapt to environment changes dynamically in uncertain environments. Inspired by biological morphogenesis which is guided by gene regulatory networks (GRNs), in this study, we propose a GRN-based approach to self-organization of mobile sensor networks in dynamic, uncertain environments. Instead of predefining the dynamics of the GRN model like other alternative studies, we aim to evolve the GRN framework to an appropriate structure automatically. Recently biological studies found out that network motifs are simple universal building blocks for most complex networks. Based on this study, the basic idea of the GRN-based approach is as follows: first, some predefined network motifs are employed as the basic building blocks, then an evolutionary algorithm is applied to evolve parameters and the structures of the GRN-based model based on these basic building blocks. Several simulation results have demonstrated that the proposed bio-inspired model is efficient for the self-organization of mobile sensor networks and robust to environmental changes in complex environments.

In order to traverse through a complex environment, swarm robotic systems need to self-organize themselves to form different yet suitable shapes dynamically to adapt to unknown environments. Biological morphogenetic networks, such as gene regulatory networks (GRNs), are modular with independent units and often show the reuse of recurring patterns termed network motifs. Inspired by biological morphogenesis and evolution and structure of network motifs in biology, in this paper, we propose an evolving GRN-based approach for self-organizing robotic swarms to autonomously generate dynamic patterns in unknown environments. The basic idea of this GRN-based model is: first, several network motifs are predefined as the basic building blocks for GRNs, then an evolutionary algorithm is applied to evolve parameters and the structures of the GRNs model. Then a previously proposed bio-inspired pattern formation algorithm is applied to move robots to generated patterns automatically in a distributed manner. Simulation and experimental results demonstrate that the proposed bio-inspired model is effective for complex shape generation and formation and robust to environmental changes in complex unknown environments.

Most available methods in computer vision can only detect one behavior at a time in a video sequence. Multi-object behavior recognition is still a very challenge problem. In this paper, we propose a novel model based on reservoir computing ensembles for multi-pattern recognition. In this new model, multiple interactive sub-reservoirs are connected to construct the reservoir model. The sub-reservoirs are competing with each other through inhibitory connections, and the internal states of all the sub-reservoirs are combined to form the output action potentials. Neurobiological studies have shown that cortical neural networks have a distinctive modular and laminar structure, which can provide powerful computational function. Therefore, cortical neural networks are employed to construct each sub-reservoir, whose parameters can be dynamically tuned by a gene regulatory network (GRN). Extensive experimental results on the MSR action dataset II have demonstrated the feasibility and efficiency of the proposed reservoir computing ensembles model on multi-object behavior recognition in video sequences.

Reservoir computing (RC) is an approach to design, train and analyze recurrent neural networks (RNNs). Traditional RC models use fixed, random topological reservoirs. Very little work has been conducted on adapting the structure of neural reservoirs. In this study, the lamina-specific cortical neural network is employed to construct the reservoir. Numerous experimental data show that cortical neural networks are not silent even without external inputs, but rather maintain a low spontaneous firing activity. This aspect of cortical networks is important for their computational functions, but it is difficult to reproduce this aspect in the models of cortical neural networks due to the inherently unstable property of the low-activity regime. In this paper, we propose a developmental approach to self-organize the structure and synapses of lamina-specific cortical neural networks (CNNs) based reservoir where a gene regulatory network (GRN) is employed. We call this new model as GRN-CNN-RC model. Basically, the weight plasticity, and meta-plasticity of the CNN-based RC will be regulated by the GRN, and the GRN will also be influenced by the activity of the neurons it resides in, in a closed loop. Extensive experimental results on the classical benchmark problems have demonstrated the efficiency and robustness of the proposed model for classification tasks.

Morphogenesis is the biological process in which a fertilized cell divides, cells migrate and interact with each other, and finally resulting in the mature body plan under the control of gene regulatory networks (GRNs). Recently, biological discovered that 85% of the gene-gene regulation networks are composed of frequently recurring network patterns, which are called network motifs. Inspired by these biological studies, in this paper, we propose a developmental approach, i.e., network motifs based gene regulatory network model (NM-GRN), for self-organization of swarm robots to autonomously generate dynamic patterns to adapt to uncertain environments. First, a general GRN model is proposed with several predefined network motifs as basic building blocks, then an evolutionary algorithm is applied to evolve parameters and the structures of the NM-GRN model based on these basic building blocks. Experimental results demonstrate that the proposed bio-inspired model is effective for complex shape generation and robust to environmental changes in complex environments.

Embryonic development of multicellular organisms, also known as morphogenesis, is regarded as a robust self-organization process for pattern generation. Inspired by the recent findings in biology indicating that morphogen gradients, together with a Gene Regulatory Network (GRN), play a key role in biological patterning, we propose a framework for self-organized multirobot pattern formation and boundary coverage based on an artificial GRN model. The proposed framework does not need a global coordinate system, which makes it more practical to be implemented in a physical robotic system. Moreover, an adaptation mechanism is included in the framework so that the self-organization algorithm is robust to changes in the number of robots. Various case studies of multirobot pattern formation and boundary coverage show the effectiveness of the framework.

Most existing multirobot systems for pattern formation rely on a predefined pattern, which is impractical for dynamic environments where the pattern to be formed should be able to change as the environment changes. In addition, adaptation to environmental changes should be realized based only on local perception of the robots. In this paper, we propose a hierarchical gene regulatory network (H-GRN) for adaptive multirobot pattern generation and formation in changing environments. The proposed model is a two-layer gene regulatory network (GRN), where the first layer is responsible for adaptive pattern generation for the given environment, while the second layer is a decentralized control mechanism that drives the robots onto the pattern generated by the first layer. An evolutionary algorithm is adopted to evolve the parameters of the GRN subnetwork in layer 1 for optimizing the generated pattern. The parameters of the GRN in layer 2 are also optimized to improve the convergence performance. Simulation results demonstrate that the H-GRN is effective in forming the desired pattern in a changing environment. Robustness of the H-GRN to robot failure is also examined. A proof-of-concept experiment using e-puck robots confirms the feasibility and effectiveness of the proposed model.

Inspired by the major principles of gene regulation and cellular interactions in multi-cellular organism's development, we propose a distributed self-organizing algorithm for swarm robot pattern formation. In this approach, swarm robots are able to self-organize themselves into complex shapes driven by the dynamics of a gene regulatory network based model. This is a distributed approach, since only local interaction is needed for each robot to make decisions during shape formation without any global controller. The target shape is represented by the non-uniform rational B-spline (NURBS) and embedded into the gene regulation model, analogous to the morphogen gradients in morphogenesis. Since the self-organization algorithm does not need a global coordinate system, the target shape can be formed anywhere within the environment based on the current distribution of the robots. Simulation and experimental results demonstrate that the proposed algorithm is effective for complex shape construction and robust to environmental changes and system failures.

We aim to develop a new self-reconfigurable modular robot, Cross-Ball, so that we can apply bio-inspired morphogenesis mechanisms to modular robots to adapt to dynamic environments automatically. To this end, the mechanical design of modular robots has to be flexible and robust enough for various complex configurations. The major contributions of the design of this Cross-Ball robots include: 1) it provides several flexible 3D reconfiguration capabilities, such as rotating, parallel, and diagonal movements; (2) a flexible and robust hardware platform for modular robots using more complex self-reconfiguration algorithms; and (3) the mobility of each individual module. Furthermore, a skeleton-based approach is proposed for the motion control of the modules, where the module movements can be conducted in groups to improve the system reconfiguration efficiency. Some simulation results have demonstrated the feasibility of the proposed module design and the corresponding controller by reconfiguring the robots to various complex configurations.

Multi-class object recognition is a critical capability for an intelligence robot to perceive its environment. In this paper, a new approach consisting of a number of modular neural networks is proposed to recognize multiple classes of objects for a robotic system. The population of the modular neural networks depends on the class number of the objects to be recognized and each modular network only focuses on learning one object class. For each modular neural network, both the bottom-up (sensory-driven) and top-down (expectation-driven) pathways are fused together, and a supervised learning algorithm is applied to update corresponding weights of both pathways. Furthermore, two different training strategies are evaluated: positive-only training and positive-and-negative training. Experiments on visual image recognition demonstrate the efficiencies of the proposed approach and the corresponding training strategies.

The CIVS (Civilization-Inspired Vying Societies) system is a novel evolutionary learning multi-agent system loosely inspired by the history of human civilization. CIVS uses artificial life (Alife) methods to produce highly-capable artificial intelligence (AI) agents proficient in one or more complex tasks as well as more general adaptability, reasoning, and survivability in dynamic, unpredictable environments. A new cognitive architecture called CHARISMA is proposed as a brain for the social agents within the CIVS system. In this paper, we will develop a self-growing, self-reorganizing semantic network named SHYNE (Semantic HYper NEtwork) as the basic knowledge representation data structure for the CHARISMA cognitive architecture. SHYNE builds on ideas from semantic networks, slipnets, and hypergraphs to create a very powerful and flexible data structure. We believe SHYNE will solve the problem of brittle reliance on predefined rules/relations/concepts with its extensive self-reorganizing capabilities. Experimental results demonstrate that the proposed SHYNE is efficient as the knowledge representation for social agents.

In this paper, we are developing the CIVS (Civilization-Inspired Vying Societies) system, which is a novel evolutionary learning multi-agent system loosely inspired by the history of human civilization. The main objective of the CIVS system is to develop a bottom-up artificial-life approach to produce artificial agents that are inherently social in how they think, learn, adapt, and operate, so as to be more adaptable and generally intelligent in a complex, challenging environment. To this end, the CHARISMA (Context Hierarchy-based Adaptive Reasoning Self-Motivated Agent) cognitive architecture is proposed for the agents within the CIVS system. By using intrinsic motivations and dynamic knowledge representation, the CHARISMA cognitive architecture can provide autonomous mental development capability for the agent to develop its knowledge and skills through its own interactions within a dynamic challenging environment as well as social interactions with other agents.

To improve the efficiency of multi-object recognition in complex scenes, a hybrid system is proposed to learn the concurrencies and spatial relationships among different objects, and to apply such relationships for better recognitions. The hybrid system includes a bottom-up saliency map to generate regions of interest (ROIs), an independent classifiers to recognize these ROIs based on object appearances, and a what-where-memory (WWM) to cast the top-down knowledge of object relationships to help the recognitions provided by independent classifiers. The WWM learns not only the concurrencies but also the spatial layouts of different classes, which can filter out the classes that unlikely appear, and distinguish the correct class from ambiguous classes provided by independent classifiers. Experiments of multi-object recognition on two well-known image datasets demonstrate the efficiency of the proposed system.

Spiking neural networks (SNNs) are considered to be computationally more powerful than conventional NNs. However, the capability of SNNs in solving complex real-world problems remains to be demonstrated. In this paper, we propose a substantial extension of the Bienenstock, Cooper, and Munro (BCM) SNN model, in which the plasticity parameters are regulated by a gene regulatory network (GRN). Meanwhile, the dynamics of the GRN is dependent on the activation levels of the BCM neurons. We term the whole model "GRN-BCM." To demonstrate its computational power, we first compare the GRN-BCM with a standard BCM, a hidden Markov model, and a reservoir computing model on a complex time series classification problem. Simulation results indicate that the GRN-BCM significantly outperforms the compared models. The GRN-BCM is then applied to two widely used datasets for human behavior recognition. Comparative results on the two datasets suggest that the GRN-BCM is very promising for human behavior recognition, although the current experiments are still limited to the scenarios in which only one object is moving in the considered video sequences.

Developmental robotics is also known as epigenetic robotics. We propose in this paper that there is one substantial difference between developmental robotics and epigenetic robotics, since epigenetic robotics concentrates primarily on modeling the development of cognitive elements of living systems in robotic systems, such as language, emotion, and social skills, while developmental robotics should also cover the modeling of neural and morphological development in single- and multirobot systems. With the recent rapid advances in evolutionary developmental biology and systems biology, increasing genetic and cellular principles underlying biological morphogenesis have been revealed. These principles are helpful not only in understanding biological development, but also in designing self-organizing, self-reconfigurable, and self-repairable engineered systems. In this paper, we propose morphogenetic robotics, an emerging new field in developmental robotics, is an important part of developmental robotics in addition to epigenetic robotics. By morphogenetic robotics, we mean a class of methodologies in robotics for designing self-organizing, self-reconfigurable, and self-repairable single- or multirobot systems, using genetic and cellular mechanisms governing biological morphogenesis. We categorize these methodologies into three areas, namely, morphogenetic swarm robotic systems, morphogenetic modular robots, and morphogenetic body and brain design for robots. Examples are provided for each of the three areas to illustrate the main ideas underlying the morphogenetic approaches to robotics.

Morphogenesis is the biological process that governs self-organized spatial pattern formation of cells during the embryonic development of multi-cellular organisms. Inspired by this process, we have proposed a morphogenetic framework for pattern formation and boundary coverage in a distributed swarm robotic system. The framework is based only on local communications among robots and will set up a local coordinate system. This paper focuses on the theoretical and empirical analysis of the framework regarding two aspects, namely, local communication load among the robots, and system performance such as system convergence time and average travel distance of robots for several pattern formation tasks. Results show that the proposed framework is efficient and scalable for self-organizing distributed swarm robotic systems with reasonable local communication load among robots.

Detecting human activities automatically in a video stream in various scenes is a challenging task. The major difficulty of this task lies in how to extract the spatial and temporal features of video sequences so that the human activities can be recognized. To tackle this problem, we propose a new classifier model using a BCM-based spiking neural network, where the auto-regulated plasticity and meta-plasticity of the BCM network will help to extract the temporal features for the classifier. In the proposed model, the weight, weight plasticity, and meta-plasticity of the BCM network are regulated by a gene regulatory network (GRN), which plays a key role in neural development and neuromodulation. Meanwhile, the GRN will also be influenced by the activity of the neurons it resides in, resulting in a closed loop between the neural network and GRN. By using this new classifier model, only the spatial features need to be extracted from image frames in the preprocessing. Extensive experimental results have demonstrated the efficiency of the proposed model for online human activity detection.

In this paper, an artificial neural network model is built up with two pathways: bottom-up sensory-driven pathway and top-down expectation-driven pathway, which are fused to train the neural network for visual object recognition. During the supervised learning process, the bottom-up pathway generates hypotheses as network outputs. Then target label will be applied to update the bottom-up connections. On the other hand, the hypotheses generated by the bottom-up pathway will produce expectations on the sensory input through the top-down pathway. The expectations will be constrained by the real data from the sensory input which can be used to update the top-down connections accordingly. This two-pathway based neural network can also be applied to semi-supervised learning with both labeled and unlabeled data, where the network is able to generate hypotheses and corresponding expectations. Experiments on visual object recognition suggest that the proposed neural network model is promising to recover the object for the cases with missing data in sensory inputs.

In security defense tasks, multiple robots need work cooperatively to detect offensive intrusion to protect some sensitive areas. In this paper, we propose a distributed algorithm for a multi-robot system with some static sensors. The system concept is that static sensors sense intrusions and act as a cueing sensor to an ensemble of robots. These robots in turn engage the potential intruder, performing surveillance and/or neutralization of the intrusion. To minimize the intruder missing rate and average response time, a STAGS (Shame-level Task Allocation and Gap-based Self-deployment) method is proposed, which is a decentralized method without a central control unit. To further improve the system adaptability under dynamic environments, a multi-objective optimization (MOO) method is proposed to adjust the system parameters of STAGS. Extensive simulation results demonstrate the effectiveness and robustness of the proposed algorithm in a dynamic intruder detection task.

This article proposes a new reinforcement learning method using the swarm intelligence-trained neural network (SWINN) to generate solutions to various real-world problems efficiently. The swarm intelligence algorithm, particle swarm optimisation (PSO), is combined with a training resource allocator (TRA) in SWINN for specific problems. TRA, as a heuristic global search method, controls the allocation of training resources to different candidate topologies of artificial neural networks (ANNs) to expedite the system convergence, while PSO is applied as a local search algorithm to adjust the ANNs connection weights. To evaluate the performance of the SWINN algorithm, two reinforcement learning case studies: the double pole balance (a.k.a. double inverted pendulum) problem and a mobile robot localisation problem are conducted. Extensive simulation results successfully demonstrate that SWINN offers performance that is competitive with modern neuroevolutionary techniques, and is viable for real-world problems.

Identification of the most successful strategy for applications in tissue engineering is often confusing, with a wide variety of options and variables available, that can fit into an ideal graft or scaffold. The complexity of the problem is multifold in application of grafts for regeneration of peripheral nerve injuries, with many variables that affect the regeneration process and thereby the success of regeneration. Here, we develop a Swarm Intelligence based artificial neural network (SWIRL) to predict the outcome of success of a nerve graft, thus providing critical information on the ability of a nerve graft to succeed under certain circumstances. Over 30 independent variables were identified and used as features for training the network and estimation of outcomes. Specific parameters such as the critical regeneration length and the ratio of the actual length to critical length were used in the evaluation and estimation of the success of the nerve grafts. Using the SWIRL, we estimate the success of regeneration of any nerve grafts to approximately 92.59 % accuracy. This system could allow for the estimation of the best possible outcome with a fixed set of variables or identification of best possible combinations with the multitude of options available, aiding researchers to perform experiments and test hypothesis efficiently and ethically.

Simulation software is vital to ALife research. It is known that stoichiometry is important for modeling real world ecosystems. However, most currently available ALife simulators ignore stoichiometry mechanics. Of course, not all ALife research is trying to model life as it is found on earth. In this paper, we demonstrate the value of including simple stoichiometry in ALife simulation software. Through extensive simulation results, we show that it is worthwhile even in simulators far removed from modeling real organisms on earth. Including simple stoichiometry allows agents to fill niches in a complex food web instead of all directly competing for the same resources. This increases the adaptability, survivability, robustness, and diversity of the simulated agents. Consequently the simulator is more powerful and will ultimately yield more intelligent agents.

Biological organisms have evolved to perform and survive in a world characterized by rapid changes, high uncertainty, infinite richness, and limited availability of information. Gene regulatory networks (GRNs) are models of genes and gene interactions at the expression level. In this paper, inspired by the biological organisms and GRNs models, a distributed multi-robot self-construction method is proposed. By using this method, a multi-robot system can self-construct to different predefined shapes, and self-reorganize to adapt to dynamic environments. Various case studies have been conducted in the simulation, and the simulation results demonstrate the efficiency and convergence of the proposed method.

This paper investigates empirically the influence of regulation logic on the dynamics of two computational models of genetic regulatory network motifs. The gene regulatory network motifs considered in this work consist of three genes with both positive and negative feedback loops. Two forms of fuzzy logic, namely, the Zadeh operators and the probabilistic operators, as well as the summation logic have been investigated. We show that the easiness of evolving sustained oscillation, and the stability of the evolved oscillation depend both on the regulation logic and on the consistency of the regulation on the target gene.

Some common issues exist in the bio-inspired algorithms for a multi-robot system include considerable randomness of the robot movement during coordination and unevenly distributed robots in a multi-task environment. To address these issues, a self-adaptive distributed mufti-task allocation method in a multi-robot system is proposed in this paper. In this method, each robot only communicates with its neighbors through a virtual stigmergy mechanism and makes its local movement decision based on a balance between the exploration and exploitation inspired from particle swarm optimization (PSO) method. To further reduce the random movement, a new task utility function is developed, where not only the current available task weight and the travel cost are considered, but also the potential number of robot redundancy around the task, as well as the task/robot distribution ratio. The proposed algorithm has been implemented on the embodied robot simulator, Player/Stage, in a searching task. The simulation results demonstrate the efficiency and robustness in a power-efficient manner with the real-world constraints.

This paper presents a new object tracking algorithm by using the particle swarm optimization (PSO), which is a bio-inspired population-based searching algorithm. Firstly the potential solutions of the problem are projected into a state space called solution space where every point in the space presents a potential solution. Then a group of particles are initialized and start searching in this solution space. The swarm particles search for the best solution within this solution space using the Particle Swarm Optimization (PSO) algorithm. An accumulative histogram of the object appearance is applied to build up the fitness function for the interested object pattern. Eventually the swarming particles driven by the fitness function converge to the optimal solution. Experimental results demonstrate that the proposed PSO method is efficient and robust in visual object tracking under dynamic environments

Multi-robot reinforcement learning is a very challenging area due to several issues, such as large state spaces, difficulty in reward assignment, nondeterministic action selections, and difficulty in merging learned experiences from other robots. In this paper, we propose a dynamic correlation matrix based multi-Q learning (DCM-MultiQ) method for a distributed multi-robot system. A novel dynamic correlation matrix is proposed, which not only handles each agentpsilas Q value, but also deals with the correlation among agents. Furthermore, a theoretical proof of the convergence of the proposed DCM-MultiQ algorithm is also provided using a feedback matrix control theory. To evaluate the efficiency of the proposed DCM-MultiQ method, several case studies of a multi-robot system in forage tasks have been conducted. The simulation results show the efficiency and convergence of the proposed method.

Miniature robots have many advantages over their larger counterparts, such as low cost, low power, and easy to build a large scale team for complex tasks. Heterogeneous multi miniature robots could provide powerful situation awareness capability due to different locomotion capabilities and sensor information. However, it would be expensive and time consuming to develop specific embedded system for different type of robots. In this paper, we propose a generic modular embedded system architecture called SMARbot (Stevens modular autonomous robot), which consists of a set of hardware and software modules that can be configured to construct various types of robot systems. These modules include a high performance microprocessor, a reconfigurable hardware component, wireless communication, and diverse sensor and actuator interfaces. The design of all the modules in electrical subsystem, the selection criteria for module components, and the real-time operating system are described. Some preliminary experimental results are also presented.

This paper presents a new object tracking algorithm that embeds swarming particles into generic particle filter framework to achieve more robustness and flexibility. Firstly a group of particles associated with potential solutions are initialized in a high-dimensional space. Then particle swarm optimization (PSO) is used to drive particles flying. The object is tracked when the particles reach convergence. This PSO-based algorithm contains resample, similarity measure, and integration together such that the degeneracy problem of particle filter can be avoided. Furthermore, a multiple feature model is proposed for object description to enhance the tracking accuracy and efficiency. The proposed algorithm is independent with specific objects and can be used for any free-selected object tracking. Some experimental results demonstrate efficiency and robustness of the algorithm.

In this paper, we propose a swarm intelligence based reinforcement learning (SWIRL) method to train artificial neural networks (ANN). Basically, two swarm intelligence based algorithms are combined together to train the ANN models. Ant Colony Optimization (ACO) is applied to select ANN topology, while Particle Swarm Optimization (PSO) is applied to adjust ANN connection weights. To evaluate the performance of the SWIRL model, it is applied to double pole problem and robot localization through reinforcement learning. Extensive simulation results successfully demonstrate that SWIRL offers performance that is competitive with modern neuroevolutionary techniques, as well as its viability for real-world problems.

A collective construction task require a multi-robot system to search for randomly distributed building blocks and push those blocks to some predefined locations. To address this problem, a bio-inspired swarm intelligence based algorithm is proposed for a distributed multi-robot system to combine explorative searching and dynamic task allocation together for collective construction. Basically, a virtual pheromone trail based method is proposed as the message passing mechanism among the robots, where robots make distributed movement decisions through local interactions. Since blocks may need multiple robots to work together, dynamic task allocation among robots is necessary. A modified Particle Swarm Optimization (PSO) method is proposed to balance the exploration and exploitation, which helps to allocate reasonable robots to different target blocks. The simulation results in multi-robot construction task demonstrate the efficiency and robustness of the proposed method.

This paper presents a robust tracking algorithm using an adaptive tracking window associated with five parameters, where the parameters of the tracking window are optimized by a particle swarm optimization (PSO) algorithm. Basically, the optimization of a tracking window is transformed into a searching algorithm in a five-dimension feature space, which constrains the possibilities of the window. Particles associated with different parameters fly around the searching space independently, while they are sharing information from the society and adjust their behaviors to achieve the global optimization, which means the most optimized parameters for the tracking window. Appearance histogram is employed to calculate the fitness function for particles, where the distance between histograms is measured by histogram intersection. Estimated people motion is utilized to expedite the convergence of particles. Experimental results of people tracking demonstrate that the algorithm is efficient, robust, and adaptive to various rigid and non-rigid people motions

Distributed coordination is critical for a multi-robot system in hazardous waste cleanup under a dynamic environment. To achieve higher efficiency as well as robustness, a bio-inspired local interaction via virtual stigmergy (LIVS) coordination approach is proposed in this paper. This new meta-heuristic integrates two mechanisms - stigmergy-based autocatalytic mechanism and particle swarm optimization cognitive capabilities through local interaction - into one efficient approach. The proposed LIVS algorithm has been implemented on both self-developed simulator and embodied robot simulator Player/Stage in a searching task. The simulation results demonstrate the feasibility, robustness, and scalability of the methods with real-world constraints.

In this paper, we present a hybrid ant colony optimization/particle swarm optimization (ACO/PSO) control algorithm for distributed swarm robots, where each robot can only communicate with its neighbors within its communication range. A virtual pheromone mechanism is proposed as the message passing coordination scheme among the robots. This hybrid ACO/PSO architecture adopts the feedback mechanism from environment of ACO and the adaptive interplay among agents of PSO to create a dynamic optimization system, and it is well-suited for a large scale distributed multi-agent system under dynamic environments. Furthermore, a pheromone-edge pair propagation funneling method is developed to reduce the communication overhead among robots. The simulation results concretely demonstrate the robustness, scalability, and individual simplicity of the proposed control architecture in a swarm robot system with real-world constraints

To make a mobile robot with real-time vision system adapt to the highly dynamic environments and emergencies under the real-time constraints, a significant account of processing power is needed. Instead of pushing the limit of software development and computational resources, and to reduce the system computation time and improve system fault-tolerance, this paper presents an embedded platform which can dynamically reconfigure a mobile robot system on the fly by integrating field programmable gate arrays (FPGA) and embedded processors in a system-on-chip (SOC) environment. The BDI agent model is adopted as the unified agent structure, which significantly simplify the HW/SW partitioning and communication. A self-reconfigurable platform is also proposed to improve the hardware flexibility. This proposed embedded framework has been applied to a real-world mobile robot, and the experimental results demonstrate its feasibility and efficiency

Performing face detection and tracking on a mobile robot in a dynamic environment is a challenging task with the real-time constraints. To realize a natural reactive behavior of the mobile robot, some efficient algorithms are applied for face detection and tracking due to the limited onboard computation power. Instead of pushing the limit of software development and the computational resources by implementing these algorithms on a software platform, a reconfigurable System-on-Chip (SoC) platform is adopted to achieve the higher real-time performance. A BDI intelligent agent model is proposed as a unified structure for both hardware and software. The real-world experimental results on a mobile vision system for face detection and tracking demonstrate the feasibility and efficiency of the reconfigurable intelligent agent model.

The limited power, low radio range, and an ever changing environment make the ability to explicitly communicate between multi-robots decreases in a searching task. When this happens, maintaining the weakened connection will cause robots to cluster during searching, which may be suboptimal with respect to the searching time. In this paper, several integration strategies are proposed to coordinate a team of robots which have limited explicit communication. To speed up the reconnection procedure for the proposed aggregate strategies, implicit communication through vision sensors is proposed in this paper to establish a movement plan to recover the explicit communication. Simulation results are presented and discussed; The real-world experiments with 3 Pioneer robots have been conducted. The proposed strategies can be extended to a large-scale searching environment as well as a combination of humans and robots

A color image coding scheme, that takes advantage of the chrominance-on-luminance masking effect, is proposed in this paper. This coding scheme exploits the remarkable crossed masking effect, such that more distortion in luminance will be hidden in the places where the chrominance components are strong. First, the asymmetrical crossed masking effects are introduced. Next, proper evaluation of the luminance just-noticeable-difference (JND) threshold lifting due to the chrominance masking is investigated. Based upon that, the crossed masking effect is utilized to achieve extra gain on color image compression under the dyadic wavelet transform (DWT) centric image coding framework without compromise of viewing quality. Meanwhile, no overhead of side information is invoked in the proposed scheme.