Learning to drive by imitation: An overview of deep behavior cloning methods

AO Ly, M Akhloufi - IEEE Transactions on Intelligent Vehicles, 2020 - ieeexplore.ieee.org
There is currently a huge interest around autonomous vehicles from both industry and
academia. This is mainly due to recent advances in machine learning and deep learning …

Enhancing scientific discoveries in molecular biology with deep generative models

R Lopez, A Gayoso, N Yosef - Molecular systems biology, 2020 - embopress.org
Generative models provide a well‐established statistical framework for evaluating
uncertainty and deriving conclusions from large data sets especially in the presence of …

Exploring the limitations of behavior cloning for autonomous driving

F Codevilla, E Santana, AM López… - Proceedings of the …, 2019 - openaccess.thecvf.com
Driving requires reacting to a wide variety of complex environment conditions and agent
behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation …

Deep federated learning for autonomous driving

A Nguyen, T Do, M Tran, BX Nguyen… - 2022 IEEE Intelligent …, 2022 - ieeexplore.ieee.org
Autonomous driving is an active research topic in both academia and industry. However,
most of the existing solutions focus on improving the accuracy by training learnable models …

Learning robust control policies for end-to-end autonomous driving from data-driven simulation

A Amini, I Gilitschenski, J Phillips… - IEEE Robotics and …, 2020 - ieeexplore.ieee.org
In this work, we present a data-driven simulation and training engine capable of learning
end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging …

Multimodal end-to-end autonomous driving

Y **ao, F Codevilla, A Gurram… - IEEE Transactions …, 2020 - ieeexplore.ieee.org
A crucial component of an autonomous vehicle (AV) is the artificial intelligence (AI) is able to
drive towards a desired destination. Today, there are different paradigms addressing the …

Uncovering and mitigating algorithmic bias through learned latent structure

A Amini, AP Soleimany, W Schwarting… - Proceedings of the …, 2019 - dl.acm.org
Recent research has highlighted the vulnerabilities of modern machine learning based
systems to bias, especially towards segments of society that are under-represented in …

Vista 2.0: An open, data-driven simulator for multimodal sensing and policy learning for autonomous vehicles

A Amini, TH Wang, I Gilitschenski… - … on Robotics and …, 2022 - ieeexplore.ieee.org
Simulation has the potential to transform the development of robust algorithms for mobile
agents deployed in safety-critical scenarios. However, the poor photorealism and lack of …

Variational end-to-end navigation and localization

A Amini, G Rosman, S Karaman… - … Conference on Robotics …, 2019 - ieeexplore.ieee.org
Deep learning has revolutionized the ability to learn “end-to-end” autonomous vehicle
control directly from raw sensory data. While there have been recent extensions to handle …

Driving in dense traffic with model-free reinforcement learning

DM Saxena, S Bae, A Nakhaei… - … on Robotics and …, 2020 - ieeexplore.ieee.org
Traditional planning and control methods could fail to find a feasible trajectory for an
autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle …