Hierarchical interpretable imitation learning for end-to-end autonomous driving

S Teng, L Chen, Y Ai, Y Zhou… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
End-to-end autonomous driving provides a simple and efficient framework for autonomous
driving systems, which can directly obtain control commands from raw perception data …

Urban driving with conditional imitation learning

J Hawke, R Shen, C Gurau, S Sharma… - … on Robotics and …, 2020 - ieeexplore.ieee.org
Hand-crafting generalised decision-making rules for real-world urban autonomous driving is
hard. Alternatively, learning behaviour from easy-to-collect human driving demonstrations is …

Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning

J Chen, SE Li, M Tomizuka - IEEE Transactions on Intelligent …, 2021 - ieeexplore.ieee.org
Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the
perception, decision and control problems in an integrated way, which can be more …

Conditional affordance learning for driving in urban environments

A Sauer, N Savinov, A Geiger - Conference on robot learning, 2018 - proceedings.mlr.press
Most existing approaches to autonomous driving fall into one of two categories: modular
pipelines, that build an extensive model of the environment, and imitation learning …

Cirl: Controllable imitative reinforcement learning for vision-based self-driving

X Liang, T Wang, L Yang… - Proceedings of the …, 2018 - openaccess.thecvf.com
Autonomous urban driving navigation with complex multi-agent dynamics is under-explored
due to the difficulty of learning an optimal driving policy. The traditional modular pipeline …

Agile autonomous driving using end-to-end deep imitation learning

Y Pan, CA Cheng, K Saigol, K Lee, X Yan… - arXiv preprint arXiv …, 2017 - arxiv.org
We present an end-to-end imitation learning system for agile, off-road autonomous driving
using only low-cost sensors. By imitating a model predictive controller equipped with …

Query-efficient imitation learning for end-to-end autonomous driving

J Zhang, K Cho - arXiv preprint arXiv:1605.06450, 2016 - arxiv.org
One way to approach end-to-end autonomous driving is to learn a policy function that maps
from a sensory input, such as an image frame from a front-facing camera, to a driving action …

Imitation learning for agile autonomous driving

Y Pan, CA Cheng, K Saigol, K Lee… - … Journal of Robotics …, 2020 - journals.sagepub.com
We present an end-to-end imitation learning system for agile, off-road autonomous driving
using only low-cost on-board sensors. By imitating a model predictive controller equipped …

Neat: Neural attention fields for end-to-end autonomous driving

K Chitta, A Prakash, A Geiger - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial
prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel …

Deductive reinforcement learning for visual autonomous urban driving navigation

C Huang, R Zhang, M Ouyang, P Wei… - … on Neural Networks …, 2021 - ieeexplore.ieee.org
Existing deep reinforcement learning (RL) are devoted to research applications on video
games, eg, The Open Racing Car Simulator (TORCS) and Atari games. However, it remains …