This work is intended to give an overview of technologies, developed from an artificial intelligence standpoint, devised to face the different planning and control problems involved in trajectory generation for mobile robots. The purpose of this analysis is to give a current context to present the Evolutionary Robotics approach to the problem, which is now being considered as a feasible methodology to develop mobile robots for solving real life problems. This chapter also show the authors’ experiences on related case studies, which are briefly described (a fuzzy logic based path planner for a terrestrial mobile robot, and a knowledge-based system for desired trajectory generation in the Geosub underwater autonomous vehicle). The development of different behaviours within a path generator, built with Evolutionary Robotics concepts, is tested in a Khepera© robot and analyzed in detail. Finally, behaviour coordination based on the artificial immune system metaphor is evaluated for the same application.
TopIntroduction
The main goal of this chapter is to describe the authors’ experiences in developing trajectory generation systems for autonomous robots, using artificial intelligence (AI) and computational intelligence (CI) methodologies. During this engineering work, some questions have arisen that motivated the exploration of new techniques like ER and the behaviour coordination with artificial immune systems. This maturing process as well as new questions and hypotheses for the suitability of each technique are presented in the following paragraphs.
In order to provide paths to an autonomous mobile robot, being it terrestrial, aerial or aquatic, there are some basic building blocks that must be necessary present. One essential feature needed consists on on-board sensory systems to have perception of the world and the robot’s presence in the environment. This will be called the navigation system. Another necessary feature is the low-level trajectory generation from the next target position and the robot’s current position, referred as the guidance system. Finally, the lowest level feedback loops allowing the robot to describe a trajectory as close as possible to the proposed path (Fossen, 2002), (Meystel, 1991), named the control system.
A top hierarchy module is responsible of generating the next target positions for the robot, and then, the whole trajectory or path. This module is called the mission planner and varies according to the mobile robot application domain. The mission plan can be given beforehand (static planning) or it can be changed on-line as the robot movement progresses in the real world (dynamic planning or replanning). Mission replanning is the robot’s response to the changing environment (obstacle avoidance, changes in mission objectives priorities, and others).
The navigation, the guidance and the mission planner systems providing trajectories for the mobile robot, may be considered as a supervisory control layer giving appropriate set points to the lower level controllers, in a clear hierarchical structured control (Acosta et. al, 2001). Consequently, every control layer could be approached with many different and heterogeneous techniques. Nevertheless, to better focus within the scope of this book, current technology on mobile robot path generation with AI and CI techniques will be analyzed in more detail in next sections.