Collision Avoidance Algorithm for Multi-sensor Mobile Robot
Marwah Almasri[1] [Abrar Alajlan[2], Khaled Elleithy[3]]
Collision Avoidance (CA) systems have been widely used in various robotics applications. Collision avoidance is an essential factor in mobile robot systems. The goal of obstacle avoidance is to make the robot travels in a collision-free path until it reaches the target. In general, obstacles can be static or dynamic. Static obstacles are those with predefined locations where dynamic obstacles are moving objects. Therefore, detecting dynamic obstacle is more challenging because it requires a prediction of its position.
The collision position can be detected by some measurements that are obtained from different modules such as cameras, GPS, ultrasonic sensors, and infrared sensors. Based on fusion of these reading, the robot can make a decision and avoid collisions until it reaches its targeted location.
In this poster, a collision avoidance algorithm for mobile robot is developed that relies on the use of low-cost ultrasonic with infrared sensors, and involving some other modules such as camera, and GPS.
The collision avoidance algorithm was tested on FEZ Cerbot robot from GHI Electronics company. This robot has been equipped with different types of sensors as follow. Two infrared sensors at the front (left and right), ultrasonic sensor (Distance US3 module), camera module, and GPS module. The algorithm was implemented on a Windows platform using .NET. The main goal of this work is to detect objects within the range of detection. Different types of sensors have been used in order to improve the reliability and the robustness of the robot. Sensor data fusion is applied to obtain the most reliable measurement. After data fusion is done, the robot will detect the obstacles and avoid collisions. The flowchart of the algorithm is shown below.
[1] Computer Science and Engineering Department, University of Bridgeport, Bridgeport, CT 06604, USA,
[2] Computer Science and Engineering Department, University of Bridgeport, Bridgeport, CT 06604, USA,
[3] Computer Science and Engineering Department, University of Bridgeport, Bridgeport, CT 06604, USA,