Mario Calha

Implementing a distributed sensing and actuation system: The CAMBADA robots case study

The use of distributed computing architectures has become commonplace in complex embedded systems with potential advantages, for example, in terms of scalability, dependability and maintainability. One particular area in which that trend can be witnessed is mobile autonomous robotics in which several sensors and actuators are interconnected by means of a control network. In this paper we address one case study concerning the CAMBADA robots that were developed at the University of Aveiro for the Robocup Middle Size League. These robots have a distributed architecture with two layers, a coordination layer responsible for the global behaviors and a distributed sensing and actuating layer that conveys internal state information and executes coordination commands. This paper focuses on the latter layer, which is based on the FTT-CAN protocol, following a network-centric approach that provides an efficient framework for the synchronization of all systems activities. We describe the computing and communication requirements, the robot architecture, the system design and implementation, and finally we provide experimental results that show advantages with respect to a non-synchronized distributed approach

Adapting FTT-CAN for the joint dispatching of tasks and messages

In the context of centralized holistic scheduling of tasks and messages, dispatching can he an issue. This paper presents an architecture with a centralized dispatcher that can be easily integrated in any distributed control system without introducing significant overhead. A central node dispatches both tasks and messages to other nodes that are only required to possess a nano-kernel. Furthermore the interdependences between producer/consumer tasks and messages are studied, resulting in a set of constraints that guarantee system feasibility. It is also shown that this solution is easily implemented using a protocol for message dispatching such as FTT-CAN (flexible time-triggered communication on CAN).

Issues on task dispatching and master replication in FTT-CAN

The FTT-CAN (flexible time-triggered communication on controller area network) protocol supports time-triggered communication in a flexible way as well as the combination of both time and event-triggered traffic with temporal isolation. Previous papers have already discussed its potentialities and presented worst-case temporal analysis for both types of communication. After a brief review of the main characteristics of the protocol, we present new issues concerning its use in distributed embedded systems: the extension for task dispatching and the inclusion of techniques to improve fault tolerance, namely master replication.

SIMHOL - a graphical simulator for the joint scheduling of messages and tasks in distributed embedded systems

Abstract In this paper a simulator to preview the timeliness of the transmission of messages and of the execution of tasks in a distributed system is presented. The simulator, called SIMHOL, builds on previous work by the authors in which a simple mechanism to dispatch tasks and messages was proposed for CAN-based distributed systems. The inputs to the simulator are the so-called data streams, which include the producer tasks, the correspondent messages and the tasks that use the transmitted data. Using the worst-case execution time and transmission time, the simulator is able to verify if deadlines are fulfilled in every node of the system and in the network. Besides discussing the simulator construction and operation, the paper presents some examples of distributed systems requirements and the results obtained by using the tool to analyze the respective timeliness. This is also used to illustrate the outputs of the simulator. One important issue also discussed is the easy way, due to the object oriented approach chosen, to extend the simulation to cover different networks and to use different scheduling techniques either at the task level or at the message level.

Design and development of a proof-of-concept platooning application using the HIDENETS architecture

This paper describes the design and development of a proof-of-concept platooning application, which operates in a mobile and dynamic environment and makes use of architectural and middleware solutions that were proposed in the scope of the HIDENETS project. With this application it is possible to demonstrate the practical feasibility of a hybrid system architecture, with realms of operation with distinct synchrony properties, and the benefits of adopting such architecture. In particular, we show that it is possible to improve the performance and behavior of the platooning application, which operates over an intrinsically uncertain environment (due to mobility and wireless communication), and still secure fundamental safety-critical requirements.

Kernel design for ftt-can systems

In the context of a centralized holistic scheduling of tasks and messages, the complexity of the involved kernels is of utmost importance. Its complexity influences directly the overhead at the computing nodes. In this paper, an architecture of a kernel is presented. This kernel can be integrated in the computing nodes of a distributed control system without introducing a significant overhead. A central node dispatches both tasks and messages to other nodes that are only required to possess a nano-kernel. A case study where these concepts were partially implemented is also presented. This case study demonstrates that this kind of kernel can easily be implemented with low processing power microcontrollers.

Real-Time Procedures In Distributed Systems

: The design of real-time systems can be accomplished using various modelling techniques in which the timing specification has to be included. At such level of abstraction, the functionality might be described using real-time procedures. These procedures specify the actions to be accomplished without any knowledge about the system architecture, in terms of nodes and network. When a procedure maps to various tasks, the determination of the tasks’ and messages’ parameters is not trivial. The technique presented in this paper builds upon previous work by the authors and helps to reduce the time from design to implementation in real-time systems. Copyright

REAL-TIME PROCEDURES IN DISTRIBUTED SYSTEMS

Abstract The design of real-time systems can be accomplished using various modelling techniques in which the timing specification has to be included. At such level of abstraction, the functionality might be described using real-time procedures. These procedures specify the actions to be accomplished without any knowledge about the system architecture, in terms of nodes and network. When a procedure maps to various tasks, the determination of the tasks’ and messages’ parameters is not trivial. The technique presented in this paper builds upon previous work by the authors and helps to reduce the time from design to implementation in real-time systems.