dc.contributor.author | Rudzits, Reinis | |
dc.contributor.author | Pugeault, N | |
dc.date.accessioned | 2016-02-05T11:09:52Z | |
dc.date.issued | 2014-12-20 | |
dc.description.abstract | Autonomous driving is an extremely challenging problem and existing driverless cars use non-visual sensing to palliate the limitations of machine vision approaches. This paper presents a driving school framework for learning incrementally a fast and robust steering behaviour from visual gist only. The framework is based on an autonomous steering program interfacing in real time with a racing simulator: hence the teacher is a racing program having perfect insight into its position on the road, whereas the student learns to steer from visual gist only. Experiments show that (i) such a framework allows the visual driver to drive around the track successfully after a few iterations, demonstrating that visual gist is sufficient input to drive the car successfully; and (ii) the number of training rounds required to drive around a track reduces when the student has experienced other tracks, showing that the learnt model generalises well to unseen tracks. | en_GB |
dc.identifier.citation | Vol. 29 (1), pp. 51 - 57 | en_GB |
dc.identifier.doi | 10.1007/s13218-014-0340-1 | |
dc.identifier.uri | http://hdl.handle.net/10871/19621 | |
dc.language.iso | en | en_GB |
dc.publisher | Springer Berlin Heidelberg | en_GB |
dc.rights | © Springer-Verlag Berlin Heidelberg 2014 | en_GB |
dc.title | Efficient Learning of Pre-attentive Steering in a Driving School Framework | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2016-02-05T11:09:52Z | |
dc.identifier.issn | 0933-1875 | |
exeter.article-number | 1 | |
dc.description | The final publication is available at Springer via http://dx.doi.org/10.1007/s13218-014-0340-1 | en_GB |
dc.identifier.eissn | 1610-1987 | |
dc.identifier.journal | KI - Künstliche Intelligenz | en_GB |