Exploring the limitations of behavior cloning for autonomous driving
Codevilla Moraes, Felipe (Centre de Visió per Computador (Bellaterra, Catalunya))
Santana, Eder (Toyota Research Institute)
López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya))
Gaidon, Adrien (Toyota Research Institute)

Publicación:	Institute of Electrical and Electronics Engineers (IEEE), cop.2019
Descripción:	10 pàg.
Resumen:	Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-of-the-art results, executing complex lateral and longitudinal maneuvers, even in unseen environments, without being explicitly programmed to do so. However, we confirm some limitations of the behavior cloning approach: Some well-known limitations (e. g. , dataset bias and overfitting), new generalization issues (e. g. , dynamic objects and the lack of a causal modeling), and training instabilities, all requiring further research before behavior cloning can graduate to real-world driving. The code, dataset, benchmark, and agent studied in this paper can be found at https://github. com/felipecode/coiltraine.
Ayudas:	Agencia Estatal de Investigación TIN2017-88709-R Agència de Gestió d'Ajuts Universitaris i de Recerca 2017/FI-B1-00162
Nota:	Altres ajuts: Antonio M. Lopez acknowledges the financial support by ICREA under the ICREA Academia Program. As CVC/UAB researchers, they also acknowledge the Generalitat de Catalunya CERCA Program and its ACCIO agency.
Derechos:	Tots els drets reservats.
Lengua:	Anglès
Documento:	Capítol de llibre ; recerca ; Versió acceptada per publicar
Materia:	Maneuvers ; Behavior ; Cloning ; Human behavior ; Dynamic stability
Publicado en:	2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, p. 9328-9337, ISBN 978-1-7281-4803-8

DOI: 10.1109/ICCV.2019.00942

Postprint 11 p, 1.5 MB

El registro aparece en las colecciones:
Libros y colecciones > Capítulos de libros