Autonomous Vehicle Detecting Obstacles is an internship project which general purpose is providing autonomous drive functionalities basing on computer vision and implementation of tigase XMPP server.
The robot has utilities allowing it to find a point of reference by the specified algorithm as edge or color detection. As a result, it provides the capability to drive autonomously without any additional source of feedback as encoders or lidar scanner. The robot also has simple task management system taking responsibility for usage of memory and order of tasks.
The project is basing on piborg mosterborg robot which includes rapsberry PI, camera, motors and motor controller.
Deployed software is written in Java and use open source image processing library openCV and tigase XMPP server.
- Project Manager: Pawel Zaborny
Autonomous Robot v1
Two most important parts of the project are ready.
Object detection deployed on Raspberry Pi
Deployed software to raspbery Pi and checked how it works "in the field". There was no problem with object detection. Even camera is more sensitive to colour differences in sunlight than it is in artificial light.
Investigation on how to deploy openCV javaFX GUI
Trying to solve problems related to deploying program to raspberry. Problems included lack of support in java8 for javaFX on raspberry. Requirement of building native library openCV.so for specified architecture. And problem with capturing webcam.
Colour detection program is now able to find eg. tennis ball in a room and shows it's position and size.