This paper proposes a hand interface through a novel deep learning that provides easy and realistic interactions with hands in immersive virtual reality. The proposed interface is designed to provide a real-to-virtual direct hand interface using a controller to map a real hand gesture to a virtual hand in an easy and simple structure. In addition, a gesture-to-action interface that expresses the process of gesture to action in real-time without the necessity of a graphical user interface (GUI) used in existing interactive applications is proposed. This interface uses the method of applying image classification training process of capturing a 3D virtual hand gesture model as a 2D image using a deep learning model, convolutional neural network (CNN). The key objective of this process is to provide users with intuitive and realistic interactions that feature convenient operation in immersive virtual reality. To achieve this, an application that can compare and analyze the proposed interface and the existing GUI was developed. Next, a survey experiment was conducted to statistically analyze and evaluate the positive effects on the sense of presence through user satisfaction with the interface experience.

Path tracking system plays a key technology in autonomous driving. The system should be driven accurately along the lane and be careful not to cause any inconvenience to passengers. To address such tasks, this research proposes hybrid tracker based optimal path tracking system. By applying a deep learning based lane detection algorithm and a designated fast lane fitting algorithm, this research developed a lane processing algorithm that shows a match rate with actual lanes with minimal computational cost. In addition, three modified path tracking algorithms were designed using the GPS based path or the vision based path. In the driving system, a match rate for the correct ideal path does not necessarily represent driving stability. This research proposes hybrid tracker based optimal path tracking system by applying the concept of an observer that selects the optimal tracker appropriately in complex road environments. The driving stability has been studied in complex road environments such as straight road with multiple 3way junctions, roundabouts, intersections, and tunnels. Consequently, the proposed system experimentally showed the high performance with consistent driving comfort by maintaining the vehicle within the lanes accurately even in the presence of high complexity of road conditions. Code will be available in https://github.com/DGIST-ARTIV.

No abstract

Path tracking system plays a key technology in autonomous driving. The system should be driven accurately along the lane and be careful not to cause any inconvenience to passengers. To address such tasks, this paper proposes hybrid tracker based optimal path tracking system. By applying a deep learning based lane detection algorithm and a designated fast lane fitting algorithm, this paper developed a lane processing algorithm that shows a match rate with actual lanes with minimal computational cost. In addition, three modified path tracking algorithms were designed using the GPS based path or the vision based path. In the driving system, a match rate for the correct ideal path does not necessarily represent driving stability. This paper proposes hybrid tracker based optimal path tracking system by applying the concept of an observer that selects the optimal tracker appropriately in complex road environments. The driving stability has been studied in complex road environments such as straight road with multiple 3way junctions, roundabouts, intersections, and tunnels. Consequently, the proposed system experimentally showed the high performance with consistent driving comfort by maintaining the vehicle within the lanes accurately even in the presence of high complexity of road conditions. Code will be available in https://github.com/DGIST-ARTIV.

No abstract