Dynamic Role Assignment Research Articles

Dynamic role discovery and assignment in multi-agent task decomposition

Effective multi-agent teamwork can be facilitated by using personas to decompose goals into lower-level team subtasks through a shared understanding of multi-agent tasks. However, traditional methods for role discovery and assignment are not scalable and fail to adapt to dynamic changes in the environment. To solve this problem, we propose a new framework for learning dynamic role discovery and assignment. We first introduce an action encoder to construct a vector representation for each action based on its characteristics, and define and classify roles from a more comprehensive perspective based on both action differences and action contributions. To rationally assign roles to agents, we propose a representation-based role selection policy based on consideration of role differences and reward horizons, which enables agents to play roles dynamically by dynamically assigning agents with similar abilities to play the same role. Agents playing the same role share their learning of the role, and different roles correspond to different action spaces. We also introduce regularizers to increase the differences between roles and stabilize training by preventing agents from changing roles frequently. Role selection and role policy integrate action representations and role differences in a restricted action space, improving learning efficiency. We conducted experiments in the SMAC benchmark and showed that our method enables effective role discovery and assignment, outperforming the baseline on four of the six scenarios, with an average improvement in win rate of 20%, and is effective in hard and super hard maps. We also conduct ablation experiments to demonstrate the importance of each component in our approach.

ADVANCE ATTACK AND DEFENSE STRATEGY ALGORITHM WITH DYNAMIC ROLE ASSIGNMENT FOR WHEELED SOCCER ROBOT

Game strategy is one of the most critical parts of winning a soccer robot match and cannot be separated from the cooperation among robots in making movements to score goals. In this paper, a wheeled soccer robot game strategy called advance attack and defense has been developed. The strategy is combined with dynamic role assignment, in which robot can change from an attacker to a defender and vice versa. Defender robots are not only based on defensive area but will always block opposing attacker to score goal. The attack strategy performs a rotational trajectory for attacker robot to overpass opponent robot. This strategy has been proven to increase defense and attack effectiveness. Test results using soccer robot gameplay environment simulator developed by Institut Teknologi Sepuluh Nopember Robot with Intelligent System (IRIS) team show that the advance strategies are superior compared with basic strategies. In 30 matches, the advance dynamic strategy won 80%, drew 6.7%, and obtained the highest goal difference, 85 goals. The test was then verified with the implementation in the IRIS robots and showed the same performance. The developed game algorithms were tested in 2019 Indonesian wheeled soccer robot contest (KRSBI-B) and the IRIS team won the title.

LocSpeck: A Collaborative and Distributed Positioning System for Asymmetric Nodes Based on UWB Ad-Hoc Network and Wi-Fi Fingerprinting.

This paper presents LocSpeck, a collaborative and distributed indoor positioning system for dynamic nodes connected using an ad-hoc network, based on inter-node relative range measurements and Wi-Fi fingerprinting. The proposed system operates using peer-to-peer range measurements and does not need ultra-wideband (UWB) fixed anchor, nor it needs a predefined network topology. The nodes could be asymmetric in terms of the available sensors onboard, the computational resources, and the power capacity. This asymmetry adversely affects the positioning performance of the weaker nodes. Collaboration between different nodes is achieved through a distributed estimator without the need of a single centralized computing element. The ranging measurement component of the system is based on the DW1000 UWB transceiver chip from Decawave, which is attached to a set of smartphones equipped with asymmetric sensors. The distributed positioning filter fuses, locally on each node, the relative range measurements, the reading from the internal sensors, and the Wi-Fi received signal strength indicator (RSSI) readings to obtain an estimate of the position of each node. The described system does not depend on fixed UWB anchors and supports online addition and removal of nodes and dynamic node role assignment, either as an anchor or as a rover. The performance of the system is evaluated by real-world test scenarios using a set of four smartphones navigating an indoor environment on foot. The performance is compared to that of a commercial UWB-based system. The results presented in this paper show that weak mobile nodes, in terms of available positioning sensors, can benefit from collaboration with other nearby nodes.

Security of Mobile Agent Platforms using RBAC based on Dynamic Role Assignment

Mobile agent technology is a new trend in the network computing. It succeeds to capture researchers' and industry's interests long time ago, due to its innovative capabilities and attractive applications. Mobile agents are self-contained data and software modules, able to autonomously move from one host to another across the network, in order to perform their tasks and eventually return to their initiators. Despite their several qualities that make them suitable for various disciplines, where autonomy, dynamism and flexibility are strongly recommended, mobile agents still suffer from some limitations mainly related to the security issues raised by mobility. In this paper, we propose a novel approach to address the security problems evoked by platforms hosting mobile agents, particularly those caused by unauthorized access attacks. Our approach introduces a robust security policy for a Hospital, where a flexible role-based access control model (RBAC) is used and simulated as a set of cooperative agents. We implant a privilege management infrastructure (PMI) charged with issuing attribute certificates based on elliptic curve cryptography, in order to provide this model with a dynamic role assignment. Finally, practical experiments are conducted to evaluate our approach and prove its effectiveness, reliability and security.

Effective Approaches to Adaptive Collaboration via Dynamic Role Assignment

Adaptive collaboration (AC) is essential for group performance optimization in collaborative systems. This paper begins by introducing AC within the context of solving a real-world problem. Next, AC problems are formalized based on the environment-class, agent, role, group, and object (E-CARGO) model. Three algorithms are proposed for solving AC problems. They are based on three different scenarios: 1) the current group state (GS); 2) the GS after a specific period; and 3) the GS throughout the collaboration. More complex AC problems and their solutions are then investigated. Derived from the above-mentioned algorithms, two additional algorithms are presented. They consider reassignment costs. Experiments are developed to analyze the performance of each proposed algorithm. Results indicate that the proposed algorithms perform better than static collaboration where there are no reassignment costs. If reassignment costs exist, we also provide a way of determining whether to adopt an AC approach. This paper provides insights into the AC process and its effectiveness in various scenarios.

Consensus-based formation control with dynamic role assignment and obstacle avoidance

In this paper, dynamic role assignment and collision avoidance based on consensus tracking algorithm for multi-agent systems are investigated. First, based on the traditional consensus protocol, dynamic role assignment is introduced to minimize the total cost of the team of agents by solving an optimal problem using Hungarian algorithm. Secondly, considering the existence of local minimum position of traditional potential field function for collision avoidance, modified potential field function is proposed to guarantee the agent avoiding the obstacle. Finally, modified consensus algorithms containing corresponding gradient terms are presented for multi-agents systems. Simulations and experiments are included to show the effectiveness of the proposed algorithms.

A Dynamic Role Assignment for Wireless Sensor Nodes

A Dynamic Role Assignment for Wireless Sensor Nodes

Adaptive Collaboration Based on the E-CARGO Model

Adaptive Collaboration (AC) is essential for maintaining optimal team performance on collaborative tasks. However, little research has discussed AC in multi-agent systems. This paper introduces AC within the context of solving real-world team performance problems using computer-based algorithms. Based on the authors’ previous work on the Environment-Class, Agent, Role, Group, and Object (E-CARGO) model, a theoretical foundation for AC using a simplified model of role-based collaboration (RBC) is proposed. Several parameters that affect team performance are defined and integrated into a theorem, which showed that dynamic role assignment yields better performance than static role assignment. The benefits of implementing AC are further proven by simulating a “future battlefield” of remotely-controlled robotic vehicles; in this scenario, team performance clearly benefits from shifting vehicles (or roles) using a single controller. Related research is also discussed for future studies.

The Design of FIRA Based on the Dynamic Role Assignment Strategy

Robot Soccer provides a good experimental platform for the automatic control, artificial intelligence, robotics and other researches. A soccer robot system is also a typical multi-agent systems(MAS). Every robot in a soccer team is an agent,so the collaboration between agents, the rational apportionment of the robots' roles and the capacity for actions of the robots is the key to winning game. We present a strategy which is based on dynamic programming algorithm and genetic algorithm. Every robot has fitness to each role through which to carry out the dynamic role assignment, meanwhile, the parameters of the fitness functions could be optimized by genetic algorithm.

A generalized framework of dynamic role assignment for robot formation control

A dynamic role assignment algorithm is proposed in the paper for formation control of multiple mobile robots. The goal of the algorithm is to reassign a role for each robot automatically during a formation is forming or switching. Many formation control systems have been successfully implemented and validated by supporting experimental results. Nevertheless, this research aims at providing an efficient algorithm of role assignment for a class of formation control systems employing the concept of combinational optimization problems. Specifically, by exploring spatial relationship between robots and information of obstacles surrounding the robots, a character cost function is found to represent the degree of difficulty for a robot been assigned a specified role in a formation. Instead of using complex cost minimization procedure, a solution is provided by calculating the largest value of character set fitness, and a new formation is selected for robots accordingly. The developed algorithm is applied to the formation control of a group omni-directional driven robots. Simulation and experimentation are performed with real platform to verify the proposed algorithm and the results show that the performance of the proposed dynamic role assignment algorithm is efficient for robot formation control.

Dynamic Role-assignment of Transfer Cranes in a Container Terminal

Dynamic Role-assignment of Transfer Cranes in a Container Terminal

2P2-H22 細胞分化メカニズムを用いた複数ロボットの協調制御 : 掃除タスクシミュレーションにおける役割分化(バイオミメティクス・ロボティクス)

2P2-H22 細胞分化メカニズムを用いた複数ロボットの協調制御 : 掃除タスクシミュレーションにおける役割分化(バイオミメティクス・ロボティクス)

Application of reinforcement learning in robot soccer

The robot soccer game has been proposed as a benchmark problem for the artificial intelligence and robotic researches. Decision-making system is the most important part of the robot soccer system. As the environment is dynamic and complex, one of the reinforcement learning (RL) method named FNN-RL is employed in learning the decision-making strategy. The FNN-RL system consists of the fuzzy neural network (FNN) and RL. RL is used for structure identification and parameters tuning of FNN. On the other hand, the curse of dimensionality problem of RL can be solved by the function approximation characteristics of FNN. Furthermore, the residual algorithm is used to calculate the gradient of the FNN-RL method in order to guarantee the convergence and rapidity of learning. The complex decision-making task is divided into multiple learning subtasks that include dynamic role assignment, action selection, and action implementation. They constitute a hierarchical learning system. We apply the proposed FNN-RL method to the soccer agents who attempt to learn each subtask at the various layers. The effectiveness of the proposed method is demonstrated by the simulation and the real experiments.

Dynamic Role Assignment for Multi-Agent System with Parallel Constraints Among Goals

Dynamic Role Assignment for Multi-Agent System with Parallel Constraints Among Goals

Dynamic Role Assignment for Multi-Agent System with Parallel Constraints Among Goals

Dynamic Role Assignment for Multi-Agent System with Parallel Constraints Among Goals

Dynamic data fusion for future sensor networks

DFuse is an architectural framework for dynamic application-specified data fusion in sensor networks. It bridges an important abstraction gap for developing advanced fusion applications that takes into account the dynamic nature of applications and sensor networks. Elements of the DFuse architecture include a fusion API, a distributed role assignment algorithm that dynamically adapts the placement of the application task graph on the network, and an abstraction migration facility that aids such dynamic role assignment. Experimental evaluations show that the API has low overhead, and simulation results show that the role assignment algorithm significantly increases the network lifetime over static placement.

Cooperation Issues and Distributed Sensing for Multirobot Systems

This paper considers the properties a multirobot system should exhibit to perform an assigned task cooperatively. Our experiments regard specifically the domain of RoboCup middle-size league (MSL) competitions. But the illustrated techniques can be usefully applied also to other service robotics fields like, for example, videosurveillance. Two issues are addressed in the paper. The former refers to the problem of dynamic role assignment in a team of robots. The latter concerns the problem of sharing the sensory information to cooperatively track moving objects. Both these problems have been extensively investigated over the past years by the MSL robot teams. In our paper, each individual robot has been designed to become reactively aware of the environment configuration. In addition, a dynamic role assignment policy among teammates is activated, based on the knowledge about the best behavior that the team is able to acquire through the shared sensorial information. We present the successful performance of the Artisti Veneti robot team at the MSL Challenge competitions of RoboCup-2003 to show the effectiveness of our proposed hybrid architecture, as well as some tests run in laboratory to validate the omnidirectional distributed vision system which allows us to share the information gathered by the omnidirectional cameras of our robots

Blue-Park: Energy-efficient operation of Bluetooth networks using park mode

Bluetooth provides wireless networking among proximate nodes. The Bluetooth nodes are usually battery-powered, which puts a strong demand on the design of energy-efficient network structures. In the conventional piconets and scatternets, the roles of master, slave, and bridge are assigned to the nodes in a semi-static manner. This produces unfairness, since the master and bridge roles have higher activity and thus higher energy consumption. The logical piconet/scatternet structure decreases the energy efficiency by requiring packet forwarding even when a direct wireless link is possible. In this paper, we propose Blue-Park, a flexible networking structure that achieves energy efficiency and fairness, without requiring change to the Bluetooth Specification. Blue-Park utilizes the Bluetooth park mode and can be described as a self-referencing structure, where each node parks all the other nodes as a master. The packets are exchanged between nodes with dynamic park/unpark procedures, which results in dynamic role assignment. We evaluate the Blue-Park in two scenarios – comparison with a piconet and comparison with a scatternet among nodes that are physically within a single hop. The simulation results show that, when the incoming traffic at each device is bursty, in both scenarios Blue-Park can achieve higher energy efficiency and lifetime. Furthermore, the delay is not increased significantly due to the dynamic link establishment.

OPTIMAL TASK ALLOCATION AND DYNAMIC TRAJECTORY PLANNING FOR MULTI-VEHICLE SYSTEMS USING NONLINEAR HYBRID OPTIMAL CONTROL

Based on a nonlinear hybrid dynamical systems model a new planning method for optimal coordination and control of multiple unmanned vehicles is investigated. The time dependent hybrid state of the overall system consists of discrete (roles, actions) and continuous (e.g. position, orientation, velocity) state variables of the vehicles involved. The evolution in time of the system's hybrid state is described by a hybrid state automaton. The presented approach enables a tight and formal coupling of discrete and continuous state dynamics, i.e. of dynamic role and action assignment and sequencing as well as of the physical motion dynamics of a single vehicle modeled by nonlinear differential equations. The planning problem of determining optimal hybrid state trajectories that minimize a cost function as time or energy for optimal multi-vehicle cooperation subject to constraints including the vehicle's motion dynamics is transformed to a mixed-binary dynamic optimization problem being solved numerically. The numerical method consists of an inner iteration where multiphase optimal control problems are solved using a direct collocation method and an outer iteration based on a branch-and-bound search of the discrete solution space. The approach presented in this paper is applied to the scenarios of optimal simultaneous waypoint or target sequencing and dynamic trajectory planning for a team of unmanned aerial vehicles in a plane and to optimal role assignment and physics-based trajectories in robot soccer.

Distributed Coordination in Heterogeneous Multi-Robot Systems

Coordination in multi-robot systems is a very active research field in Artificial Intelligence and Robotics, since through coordination one can achieve a more effective execution of the robots' tasks. In this paper we present an approach to distributed coordination of a multi-robot system that is based on dynamic role assignment. The approach relies on the broadcast communication of utility functions that define the capability for every robot to perform a task and on the execution of a coordination protocol for dynamic role assignment. The presented method is robust to communication failures and suitable for application in dynamic environments. In addition to experimental results showing the effectiveness of our approach, the method has been successfully implemented within the team of heterogeneous robots Azzurra Robot Team in a very dynamic hostile environment provided by the RoboCup robotic soccer competitions.