Cross Validation for CNN based Affordance Learning and Control for Autonomous Driving

Sun, Chen; Su, Lang; Gu, Sunsheng; Vianney, Jean Marie Uwabeza; Qin, Kongjian; Cao, Dongpu

doi:10.1109/itsc.2019.8917385

Cited by 7 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some cases, a large number and variety of sensors are used to infer, through the application of machine learning methods, some explicit characteristics that allow for taking appropriate decisions. This approach is typically called mediated perception [12] and is currently used by some of the most notable autonomous driving 2 of 24 systems, allowing for route planning and more elaborate control. Another advantage of multimodal approaches that use multiple sensors is that they allow for solving situations in which some sensors do not deliver adequate information; for example, in the case of detecting the road by means of a camera in adverse weather conditions [13].…”

Section: Introductionmentioning

confidence: 99%

Lane following Learning Based on Semantic Segmentation with Chroma Key and Image Superposition

et al. 2021

View full text Add to dashboard Cite

There are various techniques to approach learning in autonomous driving; however, all of them suffer from some problems. In the case of imitation learning based on artificial neural networks, the system must learn to correctly identify the elements of the environment. In some cases, it takes a lot of effort to tag the images with the proper semantics. This is also relevant given the need to have very varied scenarios to train and to thus obtain an acceptable generalization capacity. In the present work, we propose a technique for automated semantic labeling. It is based on various learning phases using image superposition combining both scenarios with chromas and real indoor scenarios. This allows the generation of augmented datasets that facilitate the learning process. Further improvements by applying noise techniques are also studied. To carry out the validation, a small-scale car model is used that learns to automatically drive on a reduced circuit. A comparison with models that do not rely on semantic segmentation is also performed. The main contribution of our proposal is the possibility of generating datasets for real indoor scenarios with automatic semantic segmentation, without the need for endless human labeling tasks.

show abstract

Section: Introductionmentioning

confidence: 99%