| Abstract [eng] |
The paper clearly explains about the necessity of path planning and methodology used to create a path planning for Unmanned Ground Vehicles especially in obstacle avoidance algorithm. For autonomous vehicles path planning is as important where the vehicle uses its capability to drive on its own by avoiding obstacles and reaching the goal, in order to achieve that the vehicles undergo numerous detection process and analysing procedures and methodology to find the easiest and correct path to reach the goal. There are many methodologies that can be used to investigate an unmanned ground vehicle obstacle avoidance model. One common methodology is to use a simulation tool such as Gazebo. This allows for the creation of a virtual environment in which the unmanned ground vehicle can be tested. Another methodology is to use an actual physical robot to test the model. Similar to these model this paper deals with MATLAB/SIMULINK algorithmic model for graphical outputs to determine the weightage of the models success rate. This has the advantage of being able to test the model in a real-world environment. However, it is often more expensive and time-consuming than using a simulation tool. There are also many different algorithms that can be used for obstacle avoidance. A common algorithm is the potential field algorithm. This algorithm calculates a repulsive force between the robots and obstacles in its environment. Which one is best depends on the specific needs of the researcher. Investigators have long been interested in the development of unmanned ground vehicles (UGVs) for a variety of applications. One significant challenge in this area is obstacle avoidance; that is, the ability of a UGV to autonomously navigate around obstacles in its environment. Many different methodologies and algorithms have been proposed for tackling this problem, each with its own advantages and disadvantages. In this paper, we investigate a number of these approaches and compare their performance in terms of speed, accuracy, and robustness. Our results suggest that the artificial potential field method is the most appropriate for general UGV obstacle avoidance applications. |
