Paper Info
Title
Dynamic representations for autonomous driving
Abstract
This paper presents a method for observational learning in autonomous agents. A formalism based on deep learning implementations of variational methods and Bayesian filtering theory is presented. It is explained how the proposed method is capable of modeling the environment to mimic behaviors in an observed interaction by building internal representations and discovering temporal and causal relations. The method is evaluated in a typical surveillance scenario, i.e., perimeter monitoring. It is shown that the vehicle learns how to drive itself by simultaneously observing its surroundings and the actions taken by a human driver for a given task. That is achieved by embedding knowledge regarding perception-action couplings in dynamic representational states used to produce action flows. Thereby, representations link sensory data to control signals. In particular, the representational states associate visual features to stable action concepts such as turning or going straight.
Year
DOI
Venue
2017
10.1109/AVSS.2017.8078511
2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Keywords
Field
DocType
dynamic representations,autonomous driving,observational learning,autonomous agents,deep learning implementations,Bayesian filtering theory,internal representations,typical surveillance scenario,human driver,dynamic representational states,stable action concepts,visual features,perception-action couplings
Computer vision,Signal processing,Autonomous agent,Embedding,Observational learning,Computer science,Implementation,Vehicle dynamics,Artificial intelligence,Deep learning,Formalism (philosophy)
Conference
ISBN
Citations 
PageRank 
978-1-5386-2940-6
2
0.39
References 
Authors
13
7
Name
Order
Citations
PageRank
Juan Sebastian Olier171.26
Pablo Marín-Plaza263.55
David Martín38513.85
Lucio Marcenaro440166.21
Emilia I. Barakova521232.26
Matthias Rauterberg61212209.22
Carlo S. Regazzoni7609101.09