Towards urban driverless vehicles

Abstract

This paper addresses the problem of autonomous navigation of a car-like robot evolving in an urban environment. Such an environment exhibits an heterogeneous geometry and is cluttered with moving obstacles. Furthermore, in this context, motion safety is a critical issue. The proposed approach to the problem lies in the design of perception and planning modules that consider explicitly the dynamic nature of the vehicle and the environment while enforcing the safety constraint. The main contributions of this work are the development of such modules and integration into a single application. Initial full scale experiments validating the approach are presented.

An Architecture for Automated Driving in Urban Environments

“…In other words, the detection and tracking of the moving objects is performed in the Cycab layer, not the Navigation layer. Experiments have been carried out using video cameras and laser range sensor, and the tracking techniques presented in [14] and [9] (Fig. 3-bottom left).…”

“…It is achieved thanks to the two concepts of Partial Motion Planning (PMP) [9] and Inevitable Collision States (ICS) [10]. PMP is a planning scheme that takes into account the real-time constraint explicitly by generating partial motions iteratively at each time-step.…”

The changing nature of GIS and the provision of formal GIS education in the UK: a case study

“…Many drivers and pedestrians would now be quite literally lost when travelling without unknowingly employing the spatial analytic tool of network analysis in a navigation system connected to global positioning satellites. Current developments in respect of driverless vehicles take the concept of automated machine awareness of geographical space to a new level [Benenson et al, 2008], presenting a situation in which vehicles not people follow instructions to navigate a route. It is not surprising given such scenarios for future methods of personal transportation that the challenge of defining GIS has taxed educators, researchers and professionals since the term was first coined (examples see, Burrough, 1986: 6;Maguire, 1989: 171;Kraak and Ormeling, 1996: 9;Heywood, Cornelius and Carver, 2006: 19).…”

Knowledge discovery applied in modal rail

“…employing information systems is an alternative to deal on several problems, e.g. autonomous navigations [1] and learning [9] [10]. The need of intelligent ways to assist the vehicles is an uncontestable reality too, in domains like transport system [13], control [20], to optimize the global function modeled as a set of constraints on railroad driving [11], to distributed vehicle virtual experiment platform constructed for research about Vehicle Driving Control at energy-saving [16] and public transport [23].…”