Abstract
This paper investigates the trajectory generation problem for an advanced driver assistance system that could sense the driving state of the vehicle, so that a collision free trajectory can be generated safely. Specifically, the problem of trajectory generation is solved for the safety assessment of the driving state and to manipulate the vehicle in order to avoid any possible collisions. The vehicle senses the environment so as to obtain information about other vehicles and static obstacles ahead. Vehicles may share the perception of the environment via an inter-vehicle communication system. The planning algorithm is based on a visibility graph. A lateral repulsive potential is applied to adaptively maintain a trade-off between the trajectory length and vehicle clearance, which is the greatest problem associated with visibility graphs. As opposed to adaptive roadmap approaches, the algorithm exploits the structured nature of the environment for construction of the roadmap. Furthermore, the mostly organized nature of traffic systems is exploited to obtain orientation invariance, which is another limitation of both visibility graphs and adaptive roadmaps. Simulation results show that the algorithm can successfully solve the problem for a variety of commonly found scenarios.
Highlights
Advanced Driver Assistance Systems (ADASs) [1] are seen to be the bridge between the current, driver oriented automotive design and future autonomous vehicle design
ADASs come in a variety of formats, from pedestrian detection [2], to lane keeping assistance/lane departure warning [3]
The same reference shows that personal cars and taxis account for the largest percentage of these, in total 48.88%, with pedestrians in second, marking pedestrian detection and avoidance systems as a necessity for future vehicles
Summary
Advanced Driver Assistance Systems (ADASs) [1] are seen to be the bridge between the current, driver oriented automotive design and future autonomous vehicle design. ADASs come in a variety of formats, from pedestrian detection [2], to lane keeping assistance/lane departure warning [3] These systems are in place to reduce the amount that human drivers have to do in order to control a vehicle; this is a necessary task, as 34,826 road casualties occurred in 2009 within the European. In order for these systems to function, sensors must be employed for the collection of information, which can be used as inputs to trajectory planning algorithms The interconnection of these advanced driver assistance systems is what is likely to lead to the first commercially available autonomous vehicle. That false positives in sensing provide additional concerns [8]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
