Open AccessIndoor path planning and obstacle avoidance simulation
Author(s) -
Tom Savu,
Bogdan Alexandru Jugravu
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/682/1/012019
Subject(s) - obstacle avoidance , obstacle , motion planning , dijkstra's algorithm , path (computing) , computer science , collision avoidance , set (abstract data type) , shortest path problem , simulation , real time computing , control theory (sociology) , algorithm , artificial intelligence , mobile robot , robot , geography , control (management) , graph , computer security , archaeology , theoretical computer science , collision , programming language
The paper is describing the work performed for choosing and designing a path planning and obstacle avoidance solution for a car-like vehicle moving in an indoor environment. The proposed algorithm first consists in providing the vehicle with a set of passing points generated by a Dijkstra path planning algorithm. The vehicle is using the points for establishing its path and is avoiding the obstacles using scanned data from a distance sensor. In a simulation environment, initial tests were performed for estimating correct values of the vehicle’s forward and angular velocities and for estimating the effect of the scanning speed on the vehicle’s behaviour. Obstacle avoidance tests were performed for identifying specific situations possible to appear due to high velocities or to low scanning speed. Even not always choosing a smooth avoidance path, the algorithm proved to find a way for avoiding the obstacle in a clear and fast enough manner.