Machine learning is a rapidly developing research field that gives computer systems the ability to learn with data and to act without being explicitly programmed. Modern applications of machine learning techniques can be found in self-driving cars, image and speech recognition, virtual personal assistance, and human genome decoding. Machine learning is so pervasive today that people use it dozens of times a day without knowing it, e.g. traffic jams predictions, social media services, email spam and malware filtering, online customer support, search engine results refining, and product recommendations. We are working on many machine learning problems including environment perception for autonomous driving, robotics, systems biology, and GPR data analysis etc.
Environment perception plays a very important role in enabling autonomous driving systems by providing the vehicle with crucial information on the environment like detecting lane information and free space on road, detecting static and dynamic objects, predicting the behavior of these dynamic objects, etc. This task can be accomplished with the help of a variety of sensors like cameras, lidar, radar, ultrasonic sensors. The perceived information is needed to perform crucial tasks like decision making and path planning.
Ground Penetrating Radar (GPR) is one of the most effective sensors used in geological surveys. It provides us with a non-destructive way of extracting crucial information about concrete and structures present under the road surface. This information can be used in many applications, including maintenance and monitoring of roads, and in autonomous driving. We are using GPR sensor in the scope of RADSPOT project for mainly two purposes, sub-surface damage detection and localization.