Separation of Concerns Within Robotic Systems Through Proactive Computing

Abstract

In this short paper, we first introduce a possible new model for designing and implementing software in robotic systems. This model is based on proactive scenarios, coded through dynamic sets of condition-action rules. Each scenario embeds the required rules and can be assembled dynamically with others, allowing the proactive system to achieve a unique objective or behavior and instruct the robot accordingly. Furthermore, a scenario is not aware of the existence of the other scenarios. In fact, it only contains information about a predefined central scenario, which oversees global decision making. In addition, each scenario knows where to enter its suggestions, thus allowing for a high degree in terms of separating concerns and modularity of code. Consequently, allowing easier development, testing and optimization of each scenario independently, possible reuse in different robots, and finally, a faster achievement of robust and scalable robotics software. We then show how to apply this programming model and its functionalities during runtime, by a proof of concept consisting of a virtual robot deployed in the Webots™ simulator. This simulator is controlled with four proactive scenarios (plus the central one), in charge of three different objectives.

Software Model for Robot Programming and Example of Implementation for Navigation System

“…In our implementation, as shown in figure (1) we have a connection between ROS and PE through a MySQL database. As you see in the design of our implementation in the ROS part, we have subscriber and publisher nodes.…”

“…They are running in parallel, and each scenario is not aware of the existence of other scenarios. Therefore, our implementation has better separation of concerns [1].…”

“…The researchers in this project managed to move the functionalities from the robot side toward the proactive engine such that they could implement them in separate scenarios. Therefore, they reach the objectives of having separate concerns [1]. We would like to implement the same concept in a ROS framework, which is a great simulation tool because the real robot's and the simulation's outcome are pretty much the same in this framework, and the code used for the simulation can be transferred to a real robot.…”

“…The PE has several scenarios; a scenario is a set of condition action rules. They are running in parallel, and each scenario is not aware of the existence of the other scenarios [1]. In our proposed model, we are going to have a connection between ROS and PE through a database.…”

“…In our proposed model, we are going to have a connection between ROS and PE through a database. As you see our design in figure (1), data from ROS will be sent to the database, and the PE will use the requested data based on its needs, in figure (2), you will see the detailed design of PE. Our PE design consists of several kinds of scenarios: Strategy, Planners, Controllers, Recoveries, and Decision Making (DM).…”