Cooperative Agents Research Articles

Triarylamine-Substituted Benzimidazoliums as Electron Donor-Acceptor Dyad-Type Photocatalysts for Reductive Organic Transformations.

Triarylamine-substituted benzimidazoliums (BI+-PhNAr2), new electron donor-acceptor dyad molecules, were synthesized. Their photocatalytic properties for reductive organic transformations were explored using absorption and fluorescence spectroscopy, redox potential determinations, density functional theory calculations, transient absorption spectroscopy, and reduction reactions of selected substrates. The results show that irradiation of BI+-PhNAr2 promotes photoinduced intramolecular electron transfer to form a long-lived (∼300 μs) charge shifted state (BI•-PhN•+Ar2). In the pathway for photocatalysis of reduction reactions of substrates, BI•-PhN•+Ar2 is subsequently transformed to the neutral benzimidazolyl radical (BI•-PhNAr2) by single-electron transfer from the donor 1,3-dimethyl-2-phenylbenzimidazoline (BIH-Ph) serving as a cooperative agent. Among the benzimidazoliums explored, the bromo-substituted analogue BI+-PhN(C6H4Br-p)2 in conjunction with BIH-Ph demonstrates the most consistent catalytic performance.

Multi-Agent System for Rogue Drone Interception

A multitude of applications based on unmanned aircraft vehicles (UAVs), in conjunction with the UAVs' diminishing costs and increasing capabilities, present a major threat to public safety as well as critical infrastructure security, leading to the need for versatile and robust counter-drone solutions. This work presents a novel multi-agent jamming system (MUAV-JS), where a group of cooperative autonomous agents employ various algorithms (detection, tracking, jamming, and self-localization) to counter unauthorized drone operations. The proposed system employs a joint wireless jamming and cooperative positioning framework to best track and intercept the moving rogue drone, utilizing a relative positioning system based on signals of opportunity in conjunction with inertial and vision measurements. Software-defined radio technology is incorporated on the pursuer agent to achieve rogue drone GPS disruption, while at the same time the autonomous agents cooperate to compute the location estimate of the pursuer agent. In the presence of jamming, to improve the wireless communication performance of the autonomous agents, a cellular communication architecture is also used as an additional channel for control and information exchange. For evaluation purposes, a prototype multi-agent system is designed, implemented, and tested in a real-world environment to demonstrate its enhanced localization and jamming performance, when compared to single-agent approaches.

A player reputation system based on belief formation among Non-Player character societies in Open-World Role-Playing games

The present work is an attempt to design and implement an artificial game environment that provides information dissemination among Non-Player Characters (NPCs) of Open-World Role-Playing Game communities. Based on the perspective that an NPC is a mobile, communicating, cooperative agent that has autonomy and learning ability, and shows socialness in its virtual environment, it was possible to experiment and observe the impacts of human player-generated events on NPCs’ social learning. By means of introducing different tuneable NPC autonomy and socialness parameter values, it is ensured that information and NPC opinions about the player not only spread over the society, but they also help develop player reputation among NPCs.The defined primitives such as NPCs’ self and group-model views; event valuation and reputation models; established learning, memorization, forgetting mechanisms; the introduced information exchange and update protocol; and reputation metric provided for the construction of a tuneable, scalable virtual environment that can be used to investigate the individual and social behavioural aspects of artificial NPC societies. In this virtual environment, it is shown that player’s reputation converges to fixed values. This is noteworthy since it is an indicator of societal learning and belief formation through NPC communications in the game environment.

Matrix-scaled resilient consensus of discrete-time and continuous-time networks

This paper studies the matrix-scaled resilient consensus problems over multi-agent networks as occurring in computer science and distributed control. Unlike existing works on consensus problems, where the states of agents converge to a common value or reach some prescribed proportions, we take a more general matrix-scaled approach to accommodate the interdependence of multi-dimensional states. We develop a unified analytical framework to deal with matrix-scaled resilient consensus of discrete-time and continuous-time dynamical agents, where the underlying communication network is modeled as a generic directed time-dependent random graph. We propose new distributed protocols to guarantee the matrix-scaled consensus of cooperative agents in the network in the presence of Byzantine agents, who have full knowledge of the system and pose a severe security threat to the collective consensus objective. The cooperative agents feature multiple input and multiple output, and the number and identities of Byzantine agents are not available to the cooperative ones. Our mathematical approach capitalizes on matrix analysis, control theory, graph theory, and martingale convergence. Some numerical examples are presented to demonstrate the effectiveness of our theoretical results.

EEG channel selection-based binary particle swarm optimization with recurrent convolutional autoencoder for emotion recognition

Electroencephalography (EEG) signals can demonstrate the activities of the human brain and recognize different emotional states. Emotion recognition based on full EEG channels leads to the use of redundant data and increases the hardware complexity. This paper presents a channel selection method based on a new Binary Many-Objective Particle Swarm Optimization with Cooperative Agents (BMaOPSO-CA). More specifically, we perform unsupervised feature learning with recurrent convolutional layers based on autoencoder architecture directly from clean EEG signals. Extensive validation on three public effective benchmarks, i.e. DASPS, DEAP, and SEED which are different in channel number used stimuli, and participant ratings, was carried out with subject independent scheme. As result, the experimental study highlights the optimal electrode locations related to emotions, leading to analyze the relationship between specific brain regions and emotions.

Scaled Event-Triggered Resilient Consensus Control of Continuous-Time Multi-Agent Systems Under Byzantine Agents

This paper investigates the scaled event-triggered consensus control for the continuous-time multi-agent system under Byzantine agents. The Byzantine agents do not follow the desired control strategy, which may influence the consensus performance of the multi-agent systems. To realize the scaled consensus under the Byzantine agents, a novel continuous-time scaled event-triggered mean-subsequence-reduced algorithm is constructed. First, a scaled resilient consensus controller is developed, where every cooperative agent removes the most different event-triggered transmitted values from the in-neighbors and obtains the associated scaled resilient consensus control input. Besides, a novel dynamic event-triggered condition is designed based upon the associated discontinuous and non-differentiable Lyapunov function candidate. In addition, two sets of auxiliary variables are introduced into the event-triggered condition, to prevent the usage of the global topology information and to exclude the Zeno behavior simultaneously. The proposed control algorithm can realize the scaled consensus of the continuous-time multi-agent systems, resist the Byzantine agents, and decrease the communication burden simultaneously. The simulation results verify the effectiveness of the proposed algorithm.

The Impact of Social Preferences on Supply Chain Performance: An Application of the Game Theory Model

Traditional supply chain literature on contracting only considers agents’ economic motivation. Nowadays, with the development of behavioral economics, social preference theory has been widely used in supply chain research. These social preferences are distinct from economic motivation and will influence agents’ behaviors in the supply chain. Agents will make decisions based on not only self-interests but also the interests of others, reciprocity, and fairness. This paper introduces the relationship and status preferences in the utility function. We aim to analyze the impact of social preference on individual competition intensity in the supply chain. A Stackelberg game model (tacit collusion) is used as the theoretical framework of the choice behavior between competition and cooperation. The theoretical results and numerical simulation analysis show that under some conditions, suppliers and retailers who take the social preference factors into account can realize multiple-stage channel coordination through revenue sharing. Moreover, social preference factors will influence the choice behavior of agents in competition and cooperation. Specifically, the relationship preference promotes close cooperation among enterprises and significantly improves the supply chain and individual performance. Status preference causes fierce competition among enterprises and adversely affects supply chain performance and individual performance, making it more unstable. These findings can provide useful insights for supply chain coordination.

A review: On bio-inspired optimization methods for path planning of mobile robot

In recent years, researchers have paid attention to algorithms inspired by nature where these algorithms have proven their efficiency in solving many optimization problems, especially in complex situations, due to their high precision, speed of optimization, simplicity of the techniques, and efficiency in agent cooperation. The primary issue in the field of autonomous mobile robots is navigation. An autonomous robot's navigation ability is one of its most crucial and distinctive features. There are four components of the autonomous robot navigation issue: vision, localization, cognition, and path planning. Many academics have used bio-inspired methods to solve navigation difficulties in mobile robots in recent years, including path planning where they considered the path planning problem as an optimization problem. Many novel path-planning methods have been created, and those using bio-inspired algorithms have received much attention. These algorithms have been shown to be useful in solving complex problems where the solution space isn't always adequately characterized and the problem necessitates solving complex mathematical models of live processes. More intricate optimization methods that transcend the constraints of classical procedures must be applied as the complexities of the optimization problem increase. This work contributes to presenting a group of algorithms inspired by nature that has been used to solve the problem of planning the path of mobile robots, and then making a comparison between these algorithms based on three factors (cost, time, and path length). Choosing an appropriate path-planning method contributes to ensuring safe and efficacious navigation from one point to another.

A Pragmatic Analysis of Flouting Maxims in Classroom Verbal Interaction as Seen in Freedom Writers Movie

Successful classroom verbal interactions will occur when both the teacher and the students intend to be cooperative conversational agents contributing to the conversation's aims. In Pragmatics, this underlying principle is called Grice’s conversational maxims. However, in the classroom, both sides often intentionally flout these conversational maxims. Thus, this research aimed to conduct a pragmatic analysis to investigate the types of Grice’s conversational maxims violated by the main character of Freedom Writers movie along with the categories of teacher’s verbal interactions found in that movie under Flanders Interaction Analysis Categories System (FIACS). Using the document analysis method, the researcher used the movie transcript as the primary document to be analyzed. The findings showed that the four maxims were violated intentionally for several reasons, including warning the students of the consequences of their actions, encouraging them, avoiding certain topics of discussion, and emphasizing important messages without blatantly stating them to the whole class, and avoiding hurting the students’ feelings. Meanwhile, under Flanders Interaction Analysis Categories (FIAC), direct and indirect talks could be found in the movie. The result of this study can provide educators and pre-service teachers a glimpse of the importance of promoting appropriate classroom verbal interactions by analyzing the quality of classroom verbal interaction in terms of Grice’s Conversational Maxims and Flanders’ Interaction Analysis.

Persimmon tannin can enhance the emulsifying properties of persimmon pectin via promoting the network and forming a honeycomb-structure

In the present study, multi-scale methods, including emulsifying capability evaluation and emulsion stability determination, were used to explore the effect of persimmon tannin (PT) on the emulsification performance of persimmon pectin (PP). A series of PP-PT solutions containing 10 mg/mL of PP and 0.05–2 mg/mL of PT were prepared and used to fabricate oil-in-water emulsions. Further, the potential influencing mechanism of PT on the emulsifying characteristics of PP was exploited by the Cryo-SEM morphology, interfacial tension, and interfacial dilatational rheology measurements. The results indicated that the emulsifying and emulsion-stability potential of PP was enhanced with the addition of high-level PT (1 and 2 mg/mL), reflected by the improvement in emulsifying capacity, droplet sizes (D 32 , D 43 , and particle size), TSI value, creaming thickness, and the strengthened tolerance to salt ions (100–1000 mmol/L NaCl and 100–500 mmol/L CaCl 2 ), heating treatment (50–90 °C for 60 min), and accelerated destruction process (thermal cycling and accelerated centrifugation). However, PT in low concentrations (0.05, 0.1, and 0.2 mg/mL) displayed emulsion-damaging effects. In addition, high concentrations of PT (1 and 2 mg/mL) promoted the 3D-network structure, formed the honeycomb structure of emulsions and enhanced the viscoelasticity of the interfacial film to resist unfavorable factors. In contrast, the network structure and interfacial viscoelasticity deteriorated when low levels of PT (0.05, 0.1, and 0.2 mg/mL) were added. Overall, high levels of PT can be a cooperative agent for enhancing the emulsification properties of PP. Our data might provide a scientific basis for broadening the application of PP and PT as functional ingredients in the food industry. • PT significantly affected the emulsification properties of PP. • High concentrations of PT (1 and 2 mg/mL) enhanced PP's (10 mg/mL) emulsifying performance; by contrast, the low levels (0.05, 0.1, and 0.2 mg/mL) damaged it. • High concentrations of PT (1 and 2 mg/mL) promoted the 3D-network structure, formed the honeycomb structure of emulsions and enhanced the viscoelasticity of the interfacial film to resist unfavorable factors.

Influence of reward and location on dogs’ behaviour toward an interactive artificial agent

Animal–robot interaction studies provide outstanding opportunities to understand the principles of social interactions. Here we investigated whether dogs’ behaviour toward a cooperative artificial agent (Unidentified Moving Object (UMO)) is influenced by receiving a reward directly from the agent, and by variability in the UMO’s location. In a problem-solving task, the UMO either helped dogs to obtain food (Direct Reward Group, DRG) or to fetch an object followed by an indirect reward from the owner/experimenter (Indirect Reward Group, IRG). During the Familiarization, the UMO either started from the same location or changed its starting location in all trials. In the Test phase, dogs faced the same task, but additionally a second, unfamiliar UMO was present. We found that both reward groups gazed at the UMO with decreasing latency during the Familiarization, with the IRG showing more gaze alternations between UMO and hiding location. Dogs showed no preference for either UMO in the Test phase but looked at the familiar UMO sooner if it had changed its location during the Familiarization. Thus, direct reward is not necessary to elicit elements of socially competent behavior in dogs, but variability in its motion may be important to improve the UMO’s animacy and promote flexible learning.

Friction-enhanced lifetime of bundled quantum vortices

Experiments in the early 1980s have shown that a compact bundle of quantum vortex rings in superfluid helium remains coherent and travels a significant distance compared to its size. This is surprising because a single vortex ring, under the effect of friction with the background of thermal excitations (the so-called normal fluid), would quickly lose energy and decay. The observation of these long-lived vortex structures has remained an unsettled question since their experimental detection. In this work, by taking into account the fully coupled dynamics of superfluid vortices and the normal fluid, we show that the motion of the superfluid bundle generates a large-scale wake in the normal fluid which reduces the overall friction experienced by the bundle, enhancing its lifetime. This collective effect is similar to the drag reduction observed in systems of active, hydrodynamically cooperative agents such as bacteria in aqueous suspensions, fungal spores in the atmosphere and cyclists in pelotons.

Russian Clinical Research Market: Problems and Prospects

The global market for clinical trials is directed at harmonizing international cooperation to address issues of universal provision of high quality and availability of medicines. Considering the ubiquitous nature of digitalization, at the present stage there are a number of barriers that impede the close international cooperation of social agents in the clinical research industry: the fragmentation of the rules and requirements of ethical and legal regulation, as well as significant disadvantages in the popularization of such research in the public mind. The Russian clinical trials sector is lagging behind in the development of digital volunteer/patient search services, that reduces the ability to conduct large valid clinical trials with human participation. The article presents data from a comparative analysis of popular digital volunteer/patient search services currently available on the global Internet for their compliance with the requirements of a consumer request, and also suggests options for their improvement. The result of the study was the identification of problem areas of the modern market for international clinical trials, as well as factors lagging behind the Russian sector due to the imbalance of the legislative framework and the low quality of domestic digital platforms for promoting and attracting volunteers

A Cooperative Relative Localization System for Distributed Multi-Agent Networks

While absolute position information is inaccessible for multi-agent networks due to the lack of global reference in GNSS-challenged or infrastructure-free scenarios, relative pose information among the agents can be obtained via agent cooperation. In this paper, we develop a cooperative relative localization system for distributed multi-agent networks. In particular, we propose a node activation strategy to select the backbone agents that minimize the information loss caused by malformed topology, and then the listener agents localize themselves based on the backbone topology. The scheme also incorporates a back calibration step that utilizes the position estimates of the listener agents to further improve the localization accuracy of the backbone topology. Moreover, a multi-sensory information fusion scheme is developed for dynamic scenes, where a coordinate transformation method is proposed to reduce the accumulated error caused by the coordinate misalignment. Finally, the system is implemented on a low-cost hardware platform with the ultra-wideband radios, and extensive simulations and experiments demonstrate that the proposed system can achieve decimeter-level relative localization accuracy.

One-Layer Real-Time Optimization Using Reinforcement Learning: A Review with Guidelines

This paper reviews real-time optimization from a reinforcement learning point of view. The typical control and optimization system hierarchy depend on the layers of real-time optimization, supervisory control, and regulatory control. The literature about each mentioned layer is reviewed, supporting the proposal of a benchmark study of reinforcement learning using a one-layer approach. The multi-agent deep deterministic policy gradient algorithm was applied for economic optimization and control of the isothermal Van de Vusse reactor. The cooperative control agents allowed obtaining sufficiently robust control policies for the case study against the hybrid real-time optimization approach.

Training Management For Field Cooperative Extension Official At Service Of Cooperations And Small Medium Enterprises In West Nusa Tenggara

This   research   is   based   on   the   main   problem   regarding   Field Cooperative Extension Officers (FCEO) need to be equipped with adequate and competent cooperative knowledge as a guide and coach for cooperative members and the community in cooperative activities, cooperative members and the community in the field to fully understand, realize the importance of FCEO as a cooperative extension agent, this is one of the supporting factors in realizing an increase in people's income. The purpose of this research is to find out and describe more deeply about how training management for PPKL can then be obtained which steps are more effective and efficient so that the cooperative apparatus develops, is sustainable and improves quality and keeps up with the times, so that it is expected to be a solution to problems that occur in the community field. The research method used is descriptive qualitative research method, the data obtained through observation, in-depth interviews with informants or resource persons from representatives of the apparatus in the Cooperative and SME agencies and researchers conducted an in-depth analysis through case studies on FCEO in the Cooperatives and SMEs Office in Nusa Southeast West. The results showed that the training strategy for PPKL obtained training methods through 1) Online / Zoom meetings, 2) Blended Learning 3) Classical  or  Face-to-face  and  four  new  types  of  training  were  obtained, namely 1) Cooperative Management, 2) Sariah Economics, 3) Cooperative Digitalization.  , 4) Modern  Cooperatives and  training strategies based on theory   adopting   references   to   management/training   cycles,   namely   1) Analysis, 2) Design, 3). Development (Development), 4) Implementation and 5) Evaluation and the results of further research found a very important and basic substance, namely members of cooperatives and the community so that their existence can be maintained (existence) can be sustainable, empowerment through coaching towards members of cooperatives and the general public in the field related to improving the lives and welfare of cooperative members and the general public, the guidance is through 1). Asset Development, 2). Fostering and Managing Productive Areas and 3). Build Relationships

Cooperation: A Systematic Review of how to Enable Agent to Circumvent the Prisoner’s Dilemma

It is widely accepted that rational individuals are unable to create cooperation in a prisoner’s dilemma. However, in everyday life, cooperation, for example, during a fishing moratorium, can be observed frequently. Additionally, the appearance of cooperation in the prisoner’s dilemma can be seen in numerous simulation studies. This paper reviews 31 simulation studies published between January 2017 and January 2023 in which agents can be observed in the results to improve cooperation in a prisoner’s dilemma. The proposed methodologies were sorted into seven categories, including Bounded Rationality, Memory, Adaptive Strategy, Mood Model, Intrinsic Reward, Network Dynamics, and Altruistic Attribute. Based on their impacts, the effectiveness of these seven approaches was classified into three categories: generating cooperation, maintaining cooperation, and spreading cooperation. This review is expected to be helpful for scholars conducting future research on multi-agent cooperation and irrational agent modeling.

Distributed Clustering for Cooperative Multi-Task Learning Networks

Distributed learning enables collaborative training of machine learning models across multiple agents by exchanging model parameters without sharing local data. Each agent generates data from distinct but related distributions, and multi-task learning can be effectively used to model related tasks. This paper focuses on clustered multi-task learning, where agents are partitioned into clusters with distinct objectives, and agents in the same cluster share the same objective. The structure of such clusters is unknown apriori. Cooperation with the agents in the same cluster is beneficial and improves the overall learning performance. However, indiscriminate cooperation of agents with different objectives leads to undesired outcomes. Accurately capturing the clustering structure benefits the cooperation and offers many practical benefits; for instance, it helps advertising companies better target their ads. This paper proposes an adaptive clustering method that allows distributed agents to learn the most appropriate neighbors to collaborate with and form clusters. We prove the convergence of every agent towards its objective and analyze the network learning performance using the proposed clustering method. Further, we present revision2 a method of computing combination weights that approximately optimizes the network's learning performance to determine how one should aggregate the neighbors' model parameters after the clustering step. The theoretical analysis is well-validated by the evaluation results using target localization and digits classification, showing that the proposed clustering method outperforms existing distributed clustering methods as well as the case where agents do not cooperate.

Toward cooperative multi-agent video streaming perception

Video streaming perception ability is critical for AI applications on resource-constrained devices (agents), which prefers to offload video streams from devices to edge servers for real-time inference by deep neural networks (DNNs). Meanwhile, the multi-agent system (MAS) community is attempting to run DNNs on multiple cooperative agents to enable improved swarm intelligence-based tasks (e.g., drone swarm intelligence, self-driving fleet collaboration, and multi-agent robot cooperation). However, transferring video streaming perception capability from single-agent systems to MASs is extremely difficult due to spontaneous competition-induced trade-offs between the desired goals of accuracy, consistency, and capacity, which are three critical but conflicting measuring indexes. In this paper, we present the design and implementation of MASSIVE, an edge-assisted cooperative multi-agent video streaming perception system that simultaneously achieves all three desired goals. In our design, we consider the performance characteristics of video streaming perception and the insight of its periodic offloading pattern. On this basis, we develop a Pareto improvement scheduler to eliminate spontaneous competition among agents, allowing multi-objective optimization to achieve an ideal Pareto optimal state. Finally, we propose a virtual traffic shaper based on the mainstream 802.11 MAC protocol to ensure deterministic periodic video stream offloading in an uncertain wireless network. Our experiments demonstrate that MASSIVE achieves 122.7% accuracy and 1.8x capacity compared to the closest baseline on multiple actual cooperative vision tasks with even better consistency, and achieves an ideal Pareto optimal state in a wireless environment.

Coordinating Multiple Cooperative Vehicle Trajectories on Shared Road Networks

This paper addresses the problem of planning trajectories for multiple cooperative agents along specified paths through a static road network. Vehicle trajectories are coupled through interactions at shared areas, including intersections and road segments. A motion model is presented that includes the combined trajectories of all vehicles. The trajectories are optimized for travel time by solving a Mixed Integer Linear Program (MILP) that incorporates constraints to ensure collision avoidance. To improve the computation time of solving the MILP, two model modifications are introduced related to interactions: 1) The use of binary variables is reduced by grouping them at targeted travel times. 2) The relative travel order of interacting vehicles is constrained, guided by a heuristic solver. To further reduce computation time, an iterative method solves a sequence of smaller MILPs by targeting essential vehicle interactions with an algorithm that predicts interactions. Experiments are run on a simulated road network based on a real surface mine and haul truck trips. The proposed MILP methods are shown to significantly reduce solution costs compared to a reactive approach based on common driving practices. The MILP modifications significantly reduce computation time, trading off marginal solution quality. The reduction is extended by the iterative MILP scheme without degradation of solution quality.