Insop Song

Soft-Computing-Based Embedded Design of an Intelligent Wall/Lane-Following Vehicle

Soft computing techniques are generally well suited for vehicular control systems that are usually modeled by highly nonlinear differential equations and working in unstructured environments. To demonstrate their applicability in real-world applications, two intelligent controllers based on fuzzy logic and artificial neural network are designed for performing a wall-following task. Based on performance and flexibility considerations, the two controllers are implemented onto a reconfigurable hardware platform, namely a field-programmable gate array. As comparative studies of these two embedded hardware controllers designed for the same vehicular application are limited in literature, this research also presents an evaluation of the two controllers, comparing them in terms of hardware resource requirements, operational speeds, and trajectory tracking errors in following different predefined trajectories.

A Framework for Coordinated Control of Multiagent Systems and Its Applications

In this paper, a framework is proposed for the distributed control and coordination of multiagent systems (MASs). In the proposed framework, the control of MASs is regarded as achieving decentralized control and coordination of agents. Each agent is modeled as a coordinated hybrid agent, which is composed of an intelligent coordination layer and a hybrid control layer. The intelligent coordination layer takes the coordination input, plant input, and workspace input. In the proposed framework, we describe the coordination mechanism in a domain-independent way, i.e., as simple abstract primitives in a coordination rule base for certain dependence relationships between the activities of different agents. The intelligent coordination layer deals with the planning, coordination, decision making, and computation of the agent. The hybrid control layer of the proposed framework takes the output of the intelligent coordination layer and generates discrete and continuous control signals to control the overall process. To verify the feasibility of the proposed framework, experiments for both heterogeneous and homogeneous MASs are implemented. The proposed framework is applied to a multicrane system, a multiple robot system, and a MAS consisting of an overhead crane, a mobile robot, and a robot manipulator. It is demonstrated that the proposed framework can model the three MASs. The agents in these systems are able to cooperate and coordinate to achieve a global goal. In addition, the stability of systems modeled using the proposed framework is also analyzed.

A Real-Time Scheduler Design for a Class of Embedded Systems

We consider here the design aspect of a real-time scheduler for a class of embedded systems. For this purpose, we design a feedback controller for a reservation-based CPU scheduler for soft real-time systems. The execution time of soft real-time systems, such as multimedia systems, portable MP3 players, personal digital assistants, cellular phones, and embedded Web servers is highly variable. Hence, it is crucial to assign an adequate amount of CPU resources for the running tasks to guarantee the quality of service. On the other hand, it is also important not to allocate the large amount of resources to avoid waste. The purpose of this paper is to attain the aforementioned crucial objectives for a class of embedded systems under real-time computing constraints. Specifically, we provide an analytical model for a real-time scheduler in terms of a switched system with time-varying uncertainty. Moreover, by using Lyapunov stability in a linear matrix inequalities (LMIs) framework, we design a state feedback controller that stabilizes the switched system. This, in fact, achieves the regulation of scheduling errors caused by time-varying uncertainty to a desired level. We extend an LMI-framework-based control scheme to a relatively new control application domain, i.e., a soft realtime scheduling domain. We provide performance analysis under scheduler simulation environments and implement a feedback bandwidth server scheduler under a real-time kernel simulator. In the simulation studies, the advantages of the controller design scheme are clearly highlighted in comparison with some conventional existing open-loop systems.

FPGA implementation of fuzzy wall-following control

The objective of this study concerns the design and implementation of a complete intelligent mechatronic system. The basic idea uses the concept of car maneuvers; control (fuzzy logic controller) and sensor-based behaviors together merged to implement the wall-following control algorithm. The fuzzy logic control algorithm (FLC) was considered as the heart of the controller due to the advantage of its easy implementation on an FPGA (field programmable gate array). The FLC is implemented on a compact custom FPGA board, which provides a powerful reconfigurable hardware platform and software design, at the same time. Complementing the system, a CPU synthesized on the FPGA takes care of interfacing with the external world. The FPGA board and the hardware network are demonstrated in the form of a controller embedded on the prototype car for a task of wall-following and obstacle avoidance. Experimental results on a car-like robot show that the algorithm proposed can successfully navigate the robot to follow the wall in an unknown and changing environment.

Intelligent Parking System Design Using FPGA

In this research, we introduce FPGA based fuzzy logic controller (FLC). The benefit of using FPGA based FLC compare to software FLC is that the computation time reduction. Using this FLC, we design automated car back parallel parking system also with complete FPGA based controller. We build a small-scaled robot car and test on a real environment with VHDL code for wall following and parking. This paper describes the background of fuzzy logic system, the design of fuzzy logic system with FPGA and the experimental results.

CONCORD: A Control Framework for Distributed Real-Time Systems

Novel network technology combined with advances in hardware development have permitted the enabling of distributed real-time systems and have shortened the time-to-market period. Distributed frameworks, also known as middleware, are often used to integrate enterprise systems, shorten the development time, and reduce complexity. However, to deploy standard middleware in robotics and control applications, we have to deal with the challenge of producing predictable outputs. Most real-time applications in these areas are developed in ad hoc manner, and as such, it is hard to migrate them to new platforms. To overcome this issue while minimizing development effort and increasing reusability for distributed real-time systems, we propose a control framework for distributed real-time systems based on standard middleware specifications. The control framework is composed of asynchronously running task modules, which can be located on either the local or the remote machines. The task modules are connected by an event channel, which uses the publish/subscribe communication method. We also have developed an adaptive event channel in order to meet real-time system requirements and to produce predictable outputs. Detailed development of the control framework along with the adaptive event channel are assessed through a set of experimental results.

Hardware/software approache for the FPGA implementation of a fuzzy logic controller

This paper presents different approaches to design and implement a fuzzy logic controller (FLC) for an intelligent parking system (IPS). In recent years fuzzy logic has been adopted for scientific and engineering applications. FLC is particularly successful in the area of system control when human expert knowledge is available. It provides an alternative much simpler than the use of an analytical model. FLC can be implemented on an FPGA (field-programmable gate array) using software or hardware approach. With the software approach, FLC is performed on a flexible FPGA soft core processor. The FLC is developed and tested on a reconfigurable FPGA board

A distributed real-time system framework design for multi-robot cooperative systems using real-time CORBA

Distributed system frameworks (also known as middlewares) are developed to wrap distributed components regardless of their program languages, operating systems, and hardware platforms. Middleware hides networking details from application developers, and it increases reusability and reconfigurability of developed systems. CORBA (Common Object Request Broker Architecture) is a standard middleware. We adapt CORBA for our multi-robot research since it hides all network program details from programmers. Thus, CORBA increases development efficiency and component reusability. Recently Real-time CORBA (RT-CORBA) has been defined by Object Management Group (OMG), and it supports many real-time properties. Using RT-CORBA, we can define and implement real-time applications with stringent end-to-end quality of service (QoS) requirements. In this research, we tested one of the RT-CORBA properties. We show our testing result of a propagated priority model to guarantee that a high priority client invocation can be processed before that of a low priority client.

Multi-agent CORBA-based robotics vision architecture for cue integration

The robustness of a given vision system in the field of robotics is a very challenging problem and represents a major bottleneck in any industrial setting. Nevertheless, there is a hypothesis that the fusion of multiple natural features facilitates a robust detection and object tracking in scenes of real world complexity. Several fusion methods have been tested for cue integration with good results, but the computational effort grows as the number of features increases. This research work represents a variant of the fusion method based both on distributed systems and on an agent concept. In this work, multiple agents interact with each other to perform different roles. The structure has a cooperative approach so that the agents work as a team. The communication among the agents is based on the Event Service of CORBA technology. By using this architecture, we are exploiting the parallelism and concurrency of distributed systems, and by using the concept of agents we are exploiting the encapsulation concept to built modular systems.

An optimization algorithm for the coordinated hybrid agent framework

The coordinated hybrid agent (CHA) framework for the control of multi-agent systems (MASs) has been used to model both the homogeneous and the heterogeneous multi-agent systems. In this framework, the control of the MASs is regarded as a decentralized control and coordination of agents. The CHA framework is able to implement coordination tasks for multi-agent systems. In this study, the optimization of MASs modelled by the CHA framework is studied. The time-driven dynamics and the event-driven dynamics for the optimization of a CHA system are given. The optimization problem of the MASs is analyzed. An example is also given to illustrate how to define the optimization problem for a CHA. The forward algorithm is also introduced for solving the optimization problem for a CHA system.