公开(公告)号：US20240420487A1

公开(公告)日：2024-12-19

申请号：US18575391

申请日：2023-05-06

Applicant: JIANGSU UNIVERSITY

Inventor： Hai WANG ,  Guirong ZHANG ,  Yingfeng CAI ,  Long CHEN ,  Yicheng LI ,  Qingchao LIU

IPC: G06V20/56 ,  G06V10/26 ,  G06V10/32 ,  G06V10/77 ,  G06V10/776 ,  G06V10/80 ,  G06V10/82

Abstract: A multi-task joint perception network model and detection method for traffic road surface information can simultaneously detect a lane line and a drivable area. A coordinate attention mechanism is integrated into a traditional feature extraction network to ensure that a feature extraction effect is enhanced while a calculated amount is not increased. In a neck network, a dilated convolution residual module is proposed to enhance performance of prediction of details by the network, and a decoder part shares features of the drivable area into lane line detection to enhance a lane line detection effect under complex road conditions. In a training stage, there is provided a alternating optimization training method to improve integral segmentation performance of the model. The multi-task joint perception network model and detection method realizes quite high accuracy and excellent speed performance in a challenging BDD100K dataset.

公开(公告)号：US20240190442A1

公开(公告)日：2024-06-13

申请号：US17802143

申请日：2022-01-07

Applicant: JIANGSU UNIVERSITY

Inventor： Yingfeng CAI ,  Chenglong TENG ,  Xiaoxia XIONG ,  Hai WANG ,  Xiaodong SUN ,  Qingchao LIU

IPC: B60W40/09 ,  B60W40/107

CPC classification number: B60W40/09 ,  B60W40/107 ,  B60W2520/105 ,  B60W2540/30

Abstract: Based on a perception of an external environment of an autonomous vehicle, a driving style is recognized according to driving characteristic parameters indicating a driving aggressiveness degree and a mode shift preference, in response to a complexity of an individual driving behavior cognition. After the driving style is recognized, in accordance with group behavior characteristics of the motion bodies in the environment, a time-varying complex dynamical network is established based on a complex network with the motion bodies as nodes and roads as constraints, to serve as a complex environment model of the autonomous vehicle. Finally, the nodes in the complex environment model are parametrically represented to realize the node difference cognition of the complex environment. The nodes in the complex environment model are hierarchized by using an agglomerative algorithm to realize the hierarchical cognition of the complex environment.

公开(公告)号：US20240038066A1

公开(公告)日：2024-02-01

申请号：US18026835

申请日：2022-08-04

Applicant: JIANGSU UNIVERSITY

Inventor： Yingfeng CAI ,  Sikai LU ,  Long CHEN ,  Hai WANG ,  Chaochun YUAN ,  Qingchao LIU ,  Yicheng LI

IPC: G08G1/08

CPC classification number: G08G1/08

Abstract: A multi-intelligence federated reinforcement learning (FRL)-based vehicle-road cooperative control system and method at the complex intersection use a vehicle-road cooperative control framework based on the Road Side Unit (RSU) static processing module and the vehicle-based dynamic processing module. The historical road information is supplied by the proposed RSU module. The Federated Twin Delayed Deep Deterministic policy gradient (FTD3) algorithm is proposed to connect the federated learning (FL) module and the reinforcement learning (RL) module. The FTD3 algorithm transmits only neural network parameters instead of vehicle samples to protect privacy. Firstly, FTD3 selects only specific networks for aggregation to reduce the communication cost. Secondly, FTD3 realizes the deep combination of FL and RL by aggregating target critic networks with smaller Q-values. Thirdly, RSU neural network participates in aggregation rather than training, and only shared global model parameters are used.