Recent advancements in end-to-end autonomous driving using deep learning: A survey
End-to-End driving is a promising paradigm as it circumvents the drawbacks associated with
modular systems, such as their overwhelming complexity and propensity for error …
modular systems, such as their overwhelming complexity and propensity for error …
[HTML][HTML] Continual driver behaviour learning for connected vehicles and intelligent transportation systems: Framework, survey and challenges
Modelling, predicting and analysing driver behaviours are essential to advanced driver
assistance systems (ADAS) and the comprehensive understanding of complex driving …
assistance systems (ADAS) and the comprehensive understanding of complex driving …
End-to-end autonomous driving: Challenges and frontiers
The autonomous driving community has witnessed a rapid growth in approaches that
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …
Parallel learning-based steering control for autonomous driving
Steering control for autonomous vehicles at high speeds is challenging due to the highly
nonlinear vehicle dynamics. The traditional model-based controllers usually degrade …
nonlinear vehicle dynamics. The traditional model-based controllers usually degrade …
Uncertainties in onboard algorithms for autonomous vehicles: Challenges, mitigation, and perspectives
K Yang, X Tang, J Li, H Wang, G Zhong… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Autonomous driving is considered one of the revolutionary technologies shaping humanity's
future mobility and quality of life. However, safety remains a critical hurdle in the way of …
future mobility and quality of life. However, safety remains a critical hurdle in the way of …
Optimizing hyperparameters of deep reinforcement learning for autonomous driving based on whale optimization algorithm
Deep Reinforcement Learning (DRL) enables agents to make decisions based on a well-
designed reward function that suites a particular environment without any prior knowledge …
designed reward function that suites a particular environment without any prior knowledge …
Continuous improvement of self-driving cars using dynamic confidence-aware reinforcement learning
Today's self-driving vehicles have achieved impressive driving capabilities, but still suffer
from uncertain performance in long-tail cases. Training a reinforcement-learning-based self …
from uncertain performance in long-tail cases. Training a reinforcement-learning-based self …
Reward (mis) design for autonomous driving
This article considers the problem of diagnosing certain common errors in reward design. Its
insights are also applicable to the design of cost functions and performance metrics more …
insights are also applicable to the design of cost functions and performance metrics more …
Safety-balanced driving-style aware trajectory planning in intersection scenarios with uncertain environment
X Wang, K Tang, X Dai, J Xu, J Xi, R Ai… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
This paper proposes a two-stage trajectory planning method for self-driving vehicles (SDVs)
in intersection scenarios with uncertain social circumstances while considering other traffic …
in intersection scenarios with uncertain social circumstances while considering other traffic …
RL based hyper-parameters optimization algorithm (ROA) for convolutional neural network
Many real-world applications necessitate optimization in dynamic situations, where the
difficulty is to locate and follow the optima of a time-dependent objective function. To solve …
difficulty is to locate and follow the optima of a time-dependent objective function. To solve …