TY  - THES
AU  - Yi Xiao
ED  - Antonio Lopez
PY  - 2023//
TI  - Advancing Vision-based End-to-End Autonomous Driving
PB  - IMPRIMA
N2  - In autonomous driving, artificial intelligence (AI) processes the traffic environment to drive the vehicle to a desired destination. Currently, there are different paradigms that address the development of AI-enabled drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception, maneuver planning, and control. On the other hand, we find end-to-end driving approaches that attempt to learn the direct mapping of raw data from input sensors to vehicle control signals. The latter are relatively less studied but are gaining popularity as they are less demanding in terms of data labeling. Therefore, in this thesis, our goal is to investigate end-to-end autonomous driving.We propose to evaluate three approaches to tackle the challenge of end-to-endautonomous driving. First, we focus on the input, considering adding depth information as complementary to RGB data, in order to mimic the human being’sability to estimate the distance to obstacles. Notice that, in the real world, these depth maps can be obtained either from a LiDAR sensor, or a trained monoculardepth estimation module, where human labeling is not needed. Then, based onthe intuition that the latent space of end-to-end driving models encodes relevantinformation for driving, we use it as prior knowledge for training an affordancebased driving model. In this case, the trained affordance-based model can achieve good performance while requiring less human-labeled data, and it can provide interpretability regarding driving actions. Finally, we present a new pure vision-based end-to-end driving model termed CIL++, which is trained by imitation learning.CIL++ leverages modern best practices, such as a large horizontal field of view anda self-attention mechanism, which are contributing to the agent’s understanding ofthe driving scene and bringing a better imitation of human drivers. Using trainingdata without any human labeling, our model yields almost expert performance inthe CARLA NoCrash benchmark and could rival SOTA models that require large amounts of human-labeled data.
SN  - 978-84-126409-4-6
N1  - ADAS
ID  - Yi Xiao2023
U1  - Ph.D. thesis
ER  -