Semantic traffic law adaptive decision-making for self-driving vehicles

J Liu, H Wang, Z Cao, W Yu, C Zhao… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Facts proved that obeying traffic laws keeps the promise to promote the safety of self-driving
vehicles. Current self-driving vehicles usually have fixed algorithms during autonomous …

Autonomous driving policy continual learning with one-shot disengagement case

Z Cao, X Li, K Jiang, W Zhou, X Liu… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Disengagement cases during naturalistic driving are rare or even one-shot, but valuable for
autonomous driving. The autonomous vehicles are necessary to continually learn from these …

Stochastic pedestrian avoidance for autonomous vehicles using hybrid reinforcement learning

H Li, J Huang, Z Cao, D Yang, Z Zhong - Frontiers of Information …, 2023 - Springer
Ensuring the safety of pedestrians is essential and challenging when autonomous vehicles
are involved. Classical pedestrian avoidance strategies cannot handle uncertainty, and …

Identify, estimate and bound the uncertainty of reinforcement learning for autonomous driving

W Zhou, Z Cao, N Deng, K Jiang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) has emerged as a promising approach for developing
more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a …

Driving with caution about fully occluded areas based on occupancy maps

Y Zhong, H Peng - 2023 IEEE 26th International Conference on …, 2023 - ieeexplore.ieee.org
Safety is one of the key challenges for autonomous vehicles and correct handling of an
occluded environment is a critical safety problem. To get prepared for hidden road users …

基于混合强化学习的自动驾驶汽车行人避撞方法

H LI, J HUANG, Z CAO, D YANG, Z ZHONG, AH LI… - Frontiers, 2023 - jzus.zju.edu.cn
确保行人的安全对自动驾驶汽车而言至关重要, 同时也具有一定挑战. 经典的行人避撞策略无法
应对不确定性, 而基于学习的方法缺乏明确的性能保障. 本文提出一种基于混合强化学习的行人 …

Occlusion-aware Perception and Planning for Automated Vehicles

Y Zhong - 2023 - deepblue.lib.umich.edu
The perception system is a key component of automated vehicles, as it relies on onboard
sensors to gather information. However, the system faces challenges due to occlusions that …