Behavioral Path Planning

Behavioral Path Planning

Copyright: © 2013 |Pages: 28
DOI: 10.4018/978-1-4666-2074-2.ch006
OnDemand PDF Download:
No Current Special Offers


A large part of our everyday motion is governed by behaviors. We necessarily do not look at the entire map and formulate the best way out, but rather take instinctive actions regarding our motion. We naturally reach the desired locations fairly easily and near optimally. With the same inspirations in mind, in this chapter, the authors explore the behavioral systems for the task of motion of the mobile robot. In this chapter, they study two different algorithms, fuzzy inference systems and artificial neural networks. The fuzzy systems are governed by a set of rules, which determine the behavior of the system, for any applied input. The major task involves the use of fuzzy sets for the output computations. As per the theory of these sets, every input belongs to every set by a varying degree called as the membership degree. The authors use this concept of fuzzy-based inference to design a system for the motion of the mobile robot. They further introduce the neural networks paradigm, which is an inspiration from the human brain for problem solving. Neural networks process applied input layer wise by unit processing centers known as artificial neurons. These systems may be trained by a training database that is particular to a problem. The authors use both these algorithms to design systems for behavioral path planning of mobile robots.
Chapter Preview


The manners in which we react to situations, take everyday common decisions, and carry our daily jobs constitute our behavior. Behavior is developed over the time and may or may not have reasoning associated with it. It may usually be very difficult to justify every big and small action we just made, or are making. However, it would be fairly right to say that the taken actions were governed by whatever we have learnt in life, experienced, whatever believes and values we possess, and whatever thinking capability we have. By this virtue of behavior, we can take our own decisions in life for every big and small problem. In fact, to some extent behaviors characterize our personalities and abilities in a world full of individuals. It is, hence, very necessary to develop behaviors so as to succeed in accomplishing any task.

Another important characteristic associated with behaviors is that they are instinctive. We do not necessarily think out a lot or attempt to foresee long consequences when making a decision. In most scenarios, we let our instincts make decisions, which depend upon the individual behaviors we possess. It would be interesting to realize the kind of information processing that governs our actions based on these behaviors or instincts. We naturally do not carry intensive computations or attempt to analyze each and every aspect of the problem in our decision-making. Rather, we are more likely to see a part of it and use the summarized form of our experiences to quickly come up with the action plan. This form of decision-making is quick, and based on our behaviors may be effective.

Based on the natural behaviors, there is a sure urge to make behaviors for the artificial systems that govern their actions to the problems that they are given. The aim is to replicate the same problem solving methodology in these systems, as the humans showcase in their daily problem solving. By this mechanism, we are likely to give the systems the ability to quickly decide and act upon problems, rather than making a full-analysis and deciding on the same basis. A complete analysis on many of the problems may not be possible owing to uncertainties in inputs, non-understanding of the problem domain, lack of availability of information, etc. Many other times there may be serious computational constraints, considering the fact that complexity drastically increases with small additions in the modeling scenario, which has a very adverse effect on the computational requirements. Hence, it is advisable, and in many problems the only solution, to design behavioral systems for decision-making.

The problem of path planning is a similar problem. Consider your everyday motion where you move from one spot to another in the entire room or city at large. In regular motion, we hardly consider the obstacles that lie or are likely to lie too far off. Similarly, we are likely not to consider the complexities of the route. Rather, we normally walk, avoiding possible collisions with any of the obstacles we may find on our way. Everyday walking is a proof of us being able to navigate long distances with ease and without any collision with any of the obstacles.

Based on the same principles, there is a motivation to construct a planning algorithm for the navigation of the mobile robot. This system, in place of looking at the entire map and computing all complexities, may only concentrate on its surroundings and try to steer itself through obstacles, moving towards the goal position. This is somewhat like the manner in which we walk. A clear advantage of this system comes in cases of dynamically changing environment. While walking, if we encounter any obstacle that may be moving or may have suddenly appeared, we do not get struck. In turn, we keep walking, ensuring that we do not collide with the newly observed obstacle. This is a very important characteristic in planning knowing operations are in a place where uncertainties are high and anything may suddenly appear, or where map is fairly unknown.

Complete Chapter List

Search this Book: