This paper deals with the problem of mission allocation for robot agents cooperating with human agents, in industrial application. RFID (Radio frequency identification) sensor platform is exploited to describe the environment state. Relevant information is available in RFID tags which are placed on objects and machines, and agents (robots or humans) types. The mission allocator receives the information from the RFID platform, and calculates the adequate sub-mission (set of sequential tasks) assigned to each agent. The robot agents execute the assigned tasks, organized through task planning strategy. The human agents perform the assigned sub-mission plans introduced via Human Machine Interfaces (HMIs). After the execution of each task by the agents, the environment state is updated. A general framework allowing mission distribution for robot and human agents is proposed in this article. The effectiveness of the proposed solution is tested in simulation with mobile manipulator agents in cooperation with a group of human agents.

Manipulator robots are widely used in many fields to replace humans in complex and risky environments. However, in some particular environments the robot is prone to failure, resulting in decreased performance. In such environments, it is extremely difficult to repair the robot which interrupts the execution process. Therefore, fault tolerance plays an important role in industrial manipulators applications. In this paper, the key problems related to fault-tolerance and path planning of manipulator robots under joints failures are handled within an on-line fault-tolerant fuzzy-logic based path planning approach for high degree-of-freedom robots. This approach provides an alternative to using mathematical models to control such robots, and improves tolerance to certain faults and mechanical failures. The controller consists of two fuzzy units (i) the first unit, Fuzzy_Path_Planner, is responsible of path planning; (ii) the second unit, Fuzzy_Obstacle_Avoidance, is conceived for obstacles avoidance. Moreover, the proposed approach is capable of repelling the manipulator away from both local minima and limit cycle problems. Finally, to validate the proposed approach and show its performances and effectiveness, different tests are carried out on two six degree-of-freedom manipulator robots (ULM and PUMA560 robots), accomplishing point-to-point tasks, with and without considering some joints failures.

This paper deals with one of the most challenging decisional problems in multi-robot based production systems. It is related to tasks (products) scheduling, which requires the allocation of operations and their sequencing on the robots, while satisfying tasks and robots constraints under makespan minimization.

The paper presents a new approach for robots tasks allocation and scheduling in order to minimize the total execution time (makespan) of a mission while satisfying all the tasks constraints. This approach is implemented in a multi-agent architecture for remote control of heterogeneous multi-robot systems. The agents controlling the robots coordinate their actions and cooperate to achieve the assigned mission. The proposed approach is carried out in two phases. During the first phase, a negotiation process (based on the Contract-net protocol) is carried out between the agents of the system to allocate the tasks to the robot proposing the minimal execution time (cost). In the second phase, a local scheduling process based on priority rules is carried out by the corresponding agent for each allocated task in order to minimize its inoccupation (idle) time.

This paper presents our ongoing efforts toward the development of a distributed multi-agent framework for autonomous control of mobile manipulators. The proposed scheme assigns a reactive agent (Joint agent) to control each articulation of the manipulator, a hybrid agent (Mobile base agent) for the control of the mobile base, and a Supervisory agent to coordinate and synchronize the work of all the precedent agents. Each Control agent implements a Simulation-verification technique, in order to optimize, locally and independently from the other agents, the value of a predefined Objective function (f Obj ). The paper illustrates, also, the methodology we have followed to determine the best combination among possible footsteps for the Control agents of the system. This combination will be the input, among others, of the procedure seeking the optimal solution bringing the position of the end-effector of the mobile manipulator as close as possible to the imposed Target position. For this aim, different simulation scenarios are described and carried out, with and without considering breakdowns of some articulations of the manipulator or the mobile base. For the evaluation of the obtained solutions and the selection of the best footsteps combination, we have considered two criteria (i) f Obj values and (ii) the number of iterations.

This work presents a flexible cell controller based on the multi-agent approach. The main goal of the approach resides in the total distribution of the scheduling and control functions and support of temporal and precedence constraints between tasks during scheduling process. Contract Net protocol was the protocol adopted for scheduling and rescheduling process. An implementation of the proposed architecture is discussed.

In this paper, we address a one-machine real-time scheduling problem with a continuous input of new jobs subject to time limit constraints. Our aim was to build up an approach that optimizes the execution number of input tasks but which maintains the actual tasks available at the beginning of the processing within their characteristic temporal intervals. We have proposed to solve this problem by constructing a new schedule that accounts for the new circumstances relative to the occurrence of a task arrival. The proposed approach aims at characterizing an insertion position (if any) so as to satisfy the temporal constraints and optimize the criterion. Two algorithms solving such real-time scheduling problem have been elaborated for specific features of the input tasks. Application examples are discussed.

This paper describes an intelligent distributed monitoring architecture for flexible manufacturing systems (FMS) based on the multi-agent paradigm. The proposed approach models the FMS by a society of cognitive agents, which monitor a set of heterogeneous resources. These agents have sufficient knowledge for the decision-making and they co-operate together in order to achieve the FMS monitoring functions. The originality of this approach resides in the total distribution of the monitoring functions over the agents and the co-operation of these agents by the contract net protocol for the real-time supervision. These characteristics improve flexibility, extensibility, real-time running, autonomy, fast reaction to faults, and development cost. Experimental results developed in simulation show the feasibility and the potentialities of the proposed multi-agent architecture for distributed monitoring where concepts such us flexibility, co-ordination, reactivity and integration are involved.

We investigate a new neural network decomposed dynamic adaptive controller for the robot manipulator. The robot controller is divided into two components. The dynamic action is based on the decomposition of dynamical model into fixed and variable torque. The fixed torque represents the nominal torque and the variable torque, based on the parameter estimation obtained with an ANN, tracks the change in the dynamical system. To estimate the variable parameters we used an ANN parameter estimator. Two schemes were derived from this approach and applied successfully to a SCARA robot.

A robotics workcell is by nature a hierarchically distributed system, composed of elements such as robots, machining tools and vision systems, whose actions must be carefully coordinated. The first problem to solve is their integration into a single workcell programming and control environment. Such an environment should provide a flexible way of coordinating the actions of these elements in terms of generic (device-independent) commands which are eventually mapped to the native command languages (if any) of the physical devices. In this paper we describe the programming and control environment WORKPROV with emphasis placed on the distributed and hierarchical run time control of the workcell.

Describes an intelligent real time cell control architecture for flexible manufacturing systems. This architecture is based on the multi-agent concept of the distributed artificial intelligence. We propose an actor architecture. This multi-agent prototype system involves the following functions: scheduling, dispatching, monitoring and error handling. A new contract protocol for dynamic scheduling is presented. The purpose of this protocol is to dynamically assign operations to the resources of the manufacturing system in order to accomplish the proposed tasks. This protocol is able to deal with exceptions.