Share This Author
Multi-agent Deep Reinforcement Learning for Task Allocation in Dynamic Environment
This work proposes a new task allocation process using deep reinforcement learning that allows cooperating agents to act automatically and learn how to communicate with other neighboring agents to allocate tasks and share resources.
Feasible Automatic Reconfigurations of Real-Time OS Tasks
This research work proposes an agentbased architecture that applies automatic reconfigurations in order to re-obtain the system’s feasibility and to satisfy user requirements and developed the tool RT-Reconfiguration to support these contributions.
Safety Reconfiguration of Embedded Control Systems
The authors define service and reconfiguration processes for tasks and use the semaphore concept to ensure safety mutual exclusions and apply the priority ceiling protocol as a method to ensure the scheduling between periodic tasks with precedence and mutual exclusion constraints.
FUZZY LOGIC MULTI -AGENT SYSTEM
The use of fuzzy logic is proposed to represent the response of the agent in case of interaction with the other in a multi-agent system constituted by several intelligent agents.
Real-Time Reconfigurations of Embedded Control Systems
The authors define the architecture of the Reconfiguration Agent which is modelled by nested state machines to apply local reconfigurations and proposes technical solutions to implement the whole agent-based architecture by defining UML meta-models for both Control Components and also agents.
Model-checking for the functional safety of Control Component-based heterogeneous embedded systems
- M. Khalgui, H. Hanisch, Atef Gharbi
- Computer ScienceIEEE Conference on Emerging Technologies…
- 22 September 2009
The purpose is to check that whenever an error occurs at run-time, the agent behaves as described in user requirements by activating Control Components and deactivating others to guarantee a functional safety of the whole system.
Functional and Operational Solutions for Safety Reconfigurable Embedded Control Systems
The chapter defines a new multi-agent architecture for reconfigurable systems where a Reconfiguration Agent which is modelled by nested state machines is affected to each device of the execution environment to apply local reconfigurations, and uses the semaphore concept to ensure safety mutual exclusions.
A Social Multi-agent Cooperation System based on Planning and Distributed Task Allocation: Real Case Study
This work proposes a solution for distributed task allocation where agents dynamically allocate the tasks while they are building the plans and proves that it is very efficient as it requires little message exchange and computational time.
Feasible Dynamic Reconfigurations of Petri Nets - Application to a Production System
Three formal modules allowing reconfigurations of the system’s Petri nets are defined: changer places to dynamically change places of the model, changer transitions to dynamically reconfigure transitions, and changer marking to modify the initial markings of places.
New Solutions for Feasible and Coherent Reconfigurations of Multi-Agent Embedded Software Architectures