1. Introduction

In recent years, the intelligent mobile robots have played an important role in industry, agriculture, aerospace, and space exploration, and it becomes a hotspot issue in many research fields. The robot is divided into two categories from the application environment, named industrial robots and special robots. The industrial robot is industrial oriented multi-joint manipulator or multi-degree of freedom robot, while the special robot is opposite to industrial robots, which is used for non-manufacturing environment or service including service robots, underwater robot, entertainment robot, military robots, agricultural robots, and robotic machines. If we want the robot autonomous mobile in configuration space, the very first thing we will do is the path planning, which can be defined as the process of finding a collision-free path for a robot from its initial position to the goal or target point by avoiding collisions with any static obstacles or other agents present in its environment. In order to solve these problems, many domestic and foreign scholars researched and put forward many theories and methods of the path planning [1–4]. The traditional path planning algorithms, such as ant

© 2016 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and eproduction in any medium, provided the original work is properly cited. © 2018 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

colony algorithm, genetic algorithm, and artificial potential field algorithm, dealing with some motion planning have its unique superiority. In addition, the algorithm based on potential field or heuristic function, such as A\*, D\*, and artificial potential field method, in addressing the problem of planning can meet the requirements of real-time and the optimality. This chapter introduces two kinds of path planning algorithm of the robot, including mobile robots and unmanned ground vehicles (UGV).

2.1. Artificial potential field model

2.1.2. Improved measures

extra potential field Uadd.

2.1.3. Improved potential model

where r X; Xg

proposed as below:

2.1.1. The shortcoming of traditional potential field model

line repeatedly, but it cannot reach to the target point.

applied to replace traditional vector force control.

There are some problems when this method is applied to robot path planning:

attractive force, leading to the problem of goal unreachable (GNRON).

1. Because the traditional artificial potential field method applies virtual force to control the movement of the robot, it is possible for a robot that it cannot go through a narrow passage when two obstacles are near to each other. Moreover, if robot, obstacles and target point are on the same straight line, the robot controlled by force can only move on the straight

2. If obstacles are near to target point, it will be possible that repulsive force is greater than

3. The robot has not yet arrived at target point nearly, however, the summation of suffered forces is zero, consequently, it will fall in local minimum point and stop moving.

Aimed at the defects of traditional artificial potential field model, improved measures are

1. Turning the attractive force of target to the robot and the repulsive force of obstacles to the robot into a kind of potential field intensity, a method of calculating potential field is

2. Adding a coefficient entry ∥X � Xμ∥<sup>2</sup> in the gravitational potential of obstacles, when the robot is close to the target point, gravitational potential is reducing as well as repulsion potential. Finally, they are zero until the robot arrives at the target point, so the problem of

3. For a "deadlock" issue caused by local minimum point, the "added potential field" is introduced to guide the robot to walk out the local minimum point, that is, adding an

According to above improved measures, the improved artificial potential field model is pro-

Uattð Þ¼ <sup>X</sup> <sup>0</sup>:5kr<sup>2</sup> <sup>X</sup>; Xg

vehicle's body and target point; k is a proportional gain coefficient; X is the position ½ � x; y

� � is the distance between the current location of the central point of mobile

� � (1)

h i<sup>T</sup>

Motion Planning for Mobile Robots http://dx.doi.org/10.5772/intechopen.76895 147

.

<sup>T</sup> of

posed. The attractive force model of the target to a full range of vehicle's body is:

robot's central point in movement space; and Xg is the target point position xg; yg

obstacles and target point being too close causing goal unreachable.
