We present a novel approach to automatically identify driver behaviors from vehicle trajectories and use them for safe navigation of autonomous vehicles. We propose a novel set of features that can be easily extracted from car trajectories. We derive a data-driven mapping between these features and six driver behaviors using an elaborate web-based user study. We also compute a summarized score ...

Global positioning system (GPS) is also known as Navigation System with Time and Ranging Global Positioning System (NAVSTAR) GPS. Originally designed for military purposes, GPS is being increasingly used by civilians for various applications like marine navigation, surveying, car navigation. Signals made available for civilian use, known as the Standard Positioning Service (SPS) can be freely a...

In this report the problem of vehicular navigation based on the integration of the global positioning system and an inertial navigation system is tackled. After analysing some fundamental technical issues about reference systems, vehicle modelling and sensors, a novel solution, combining extended Kalman Filtering with particle Fitering, is developed. This solution allows to embed highly nonline...

Accurate and continuous position calculation is a key task for vehicle navigation and telematics applications. In most portable car navigation and telematics devices, the position is calculated based only on GPS data. However, in urban canyons stand-alone GPS suffers signal masking and reflections of the signal from buildings, large vehicles, and other reflective surfaces. Driving tests in such...

The use of voice commands or navigation features in the car is becoming a necessity. As keyboard and display interfaces cannot be used safely while driving, much effort has been done to make automatic speech recognition (ASR) and Text-to-Speech synthesis (TTS) ubiquitous features in the car. From voice dialing to car navigation, the requirements for voice technology vary greatly. While the use ...

In my thesis, I wish to address the problem of how to develop software for context-aware mobile computing that can adapt to constantly changing requirements at run time. By context-aware mobile computing, I understand a mode of computing characterized by three features. First, the user is involved with tasks in the real world such as navigation, car repair, building design or control of complex...

With the introduction of the digital world in all areas of life new appliances were also installed in cars. In the past, the radio and the cassette player were the main means for infotainment in a car. Today, the car navigation systems have taken over the dominant position of modern car infotainment. Current off-the-shelf navigation systems feature a satellite navigation device, media player, r...

Spoken dialogue systems are classified into three types from the viewpoint of turn taking. Dialogue can be led by the system (system initiative), the user (user initiative), and their mixture (mixed initiative). In this paper, EUROPA, a framework for developing spoken dialogue systems, is introduced. EUROPA is applied to prototyping a car navigation system called MINOS-II. MINOS-II deals with a...

We consider the problem of robots following natural language commands through previously unknown outdoor environments. A robot receives commands in natural language, such as “Navigate around the building to the car left of the fire hydrant and near the tree.” The robot needs first to classify its surrounding objects into categories, using images obtained from its sensors. The result of this cla...

In this study, the effects of information on driver’s judgment of curve sharpness were investigated by field experiment. Sixteen curves of real road were picked up. 80 subjects performed the driving test in the daytime and at nighttime. Four kinds of variables were proposed to judge curve depth: “No Information”, “Paper Map”, “Car Navigation System” and “Proposed Warning Sign”. Each subject per...