2

Smooth Reinforcement Learning Based Trajectory Tracking for Articulated Vehicles
This study addresses the problem of action fluctuation in the trajectory tracking control of articulated vehicles, proposing a smooth …
Liangfa Chen*, Xujie Song*, Liming Xiao, Lulu Gao, Fawang Zhang, Shengbo Eben Li, Fei Ma, Jingliang Duan
Smooth Reinforcement Learning Based Trajectory Tracking for Articulated Vehicles
Training Multilayer Neural Networks on Ising Machines
We proposed Ising learning algorithm, the first technique to train multilayer feedforward neural networks on Ising machines (quantum computers). The training time is reduced by 90% compared to CPU/GPU.
Xujie Song, Tong Liu, Jingliang Duan, Wenxuan Wang, Yin Ma, Hai Wei, Kai Wen, Shengbo Eben Li
PDF
Training Multilayer Neural Networks on Ising Machines
LiDAR Data Enhancement via Pseudo-LiDAR Point Cloud Correction
Objective Light detection and ranging (LiDAR) plays an important role in autonomous driving. Even if it is expensive, the number of …
Xujie Song, Sunhao Dai, Chunyu Lin, Shutao Zhan, Yao Zhao
PDF Code
LiDAR Data Enhancement via Pseudo-LiDAR Point Cloud Correction
Smooth Filtering Neural Network for Reinforcement Learning
We proposed a policy network for RL with low-pass filtering ability, named Smonet, to alleviate the action nonsmoothness issue by learning a low-frequency representation within hidden layers.
Wenxuan Wang, Jingliang Duan, Xujie Song, Liming Xiao, Liangfa Chen, Yinuo Wang, Bo Cheng, Shengbo Eben Li
PDF Video
Smooth Filtering Neural Network for Reinforcement Learning