The Driving School System: Learning Basic Driving Skills from a Teacher in a Real Car
Autor: | Irene Markelic, Anders Kjaer-Nielsen, Karl Pauwels, Lars Baunegaard With Jensen, Nikolay Chumerin, Aušra Vidugiriene, Minija Tamosiunaite, Alexander Rotter, Marc Van Hulle, Norbert Kruger, Florentin Worgotter |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2011 |
Předmět: |
Engineering
Coprocessor imitation learning Graphics processing unit 02 engineering and technology Data-driven independently moving object Real-time Control System Human–computer interaction 0502 economics and business driving 0202 electrical engineering electronic engineering information engineering Real-time data Advanced individualized driver-assistance system Real-time operating system Simulation 050210 logistics & transportation business.industry Mechanical Engineering 05 social sciences IMO Computer Science Applications Multithreading Automotive Engineering real-time system 020201 artificial intelligence & image processing Central processing unit business |
Popis: | To offer increased security and comfort, advanced driver-assistance systems (ADASs) should consider individual driving styles. Here, we present a system that learns a human's basic driving behavior and demonstrate its use as ADAS by issuing alerts when detecting inconsistent driving behavior. In contrast to much other work in this area, which is based on or obtained from simulation, our system is implemented as a multithreaded parallel central processing unit (CPU)/graphics processing unit (GPU) architecture in a real car and trained with real driving data to generate steering and acceleration control for road following. It also implements a method for detecting independently moving objects (IMOs) for spotting obstacles. Both learning and IMO detection algorithms are data driven and thus improve above the limitations of model-based approaches. The system's ability to imitate the teacher's behavior is analyzed on known and unknown streets, and results suggest its use for steering assistance but limit the use of the acceleration signal to curve negotiation. We propose that this ability to adapt to the driver can lead to better acceptance of ADAS, which is an important sales argument. Manuscript received March 12, 2010; revised November 5, 2010 and March 15, 2011; accepted April 6, 2011. The Associate Editor for this paper was S. Tang. Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TITS.2011.215769 ispartof: IEEE Transactions on Intelligent Transportation Systems vol:12 issue:99 pages:1135-1146 status: published |
Databáze: | OpenAIRE |
Externí odkaz: |