Jiangsu University

Other

Innolight Technology (Suzhou) Ltd.

Innolight Technology Pte. Ltd.

Kunshan Go-Visionox Opto-Electronics Co., Ltd.

Yungu (Gu'an) Technology Co., Ltd.

Jiangsu Jitri Molecular Engineering Inst. Co., Ltd.

Long Chen

Yingfeng Cai

Chengli Li

Zhen Zhu

Yuzhou Sun

Changgao Xia

Xiang Tian

Dengqun Yu

Xiaodong Sun

Jiangyi Han

Dehua Shi

Guolan Yue

Chaochun Yuan

Ruochen Wang

Xing Xu

Donghan Wang

Falin Zeng

Hai Feng Wang

Jie Sheng

Jiajia Wang

Xiangzhong Wang

Haobin Jiang

Feng Wang

Chaofeng Pan

Juncheng Wang

Yihan Zhang

Rui Hou

Qingchao Liu

Lingxin Zeng

Xiongfei Zhai

Zhenzhong Wang

Chao Zhang

Shengyun Nie

Weilong Li

Xigui Fang

Meng Fang

Yulin Deng

Jianguo Zhu

Weilong Lee

Weiqi Zhou

Xiaobo Chen

Yong Wang

Wenxiang Zhao

Jinghua Ji

Guohai Liu

Guizhou Qiao

Xiuyu Zhang

Wei Yu

Huawei Zhou

Longhui Lai

Rong Zou

Renkai Ding

Sikai Lu

Yicheng Li

Xiaoliang Zhang

Jiamei Nie

Wei Liu

Junhui Lou

Kewu Wang

Xiangqian Wang

Chi Zhang

Li Xing Wu

Qian Chen

Limei Wang

Dong Lu

Xiuliang Zhao

Sibing Qiao

Ying Xu

Xiangpeng Meng

Zeyu Sun

Xuping Zhang

Yixin Zhang

Shun Wang

Shidian Ma

Xiaoqiang Sun

Youguo He

Zhen Lu

Ying Zhang

Zhigang He

Yuchen Qian

Jian Xie

Ding Luo

Lei Dou

Fei Xiong

Xiaohong Chen

Zhijia Jin

Jun Liang

Dongqing Wang

Yu-zhou Sun

Tongyang Zhao

Yujie Shen

Zhenqiang Chen

Yanpeng Yang

Zhenchao Zhao

Xiaoxia Xiong

Zebin Yang

Zhenxing Huang

Ke Li

Hai He

Shaohua Wang

The present disclosure provides a cooperative distributed model predictive control (Co-DMPC)-based chassis multi-agent system (MAS) cooperative control method for autonomous vehicles, a controller, and a storage medium. A distributed state-space equation with state coupling and control input coupling characteristics is established. Meanings and transformation methods of predicted trajectories, assumed trajectories, and optimal trajectories of the states and control inputs are designed, providing a communication basis for information exchange between the agents. In order to coordinate the global performance indexes of a vehicle, a local agent optimization problem considering cost coupling is established, and the influence of the cooperative relationship on the control effect is quantitatively analyzed through adaptive weight coefficients. A method of performing a plurality of iterations within a unit sampling time is adopted, and iteration errors are utilized to enable the controller to achieve a balance between solution accuracy and efficiency.

Co-DMPC-based chassis multi-agent system (MAS) cooperative control method for autonomous vehicles, controller, and storage medium

An optical circulator and an optical module are provided. The optical circulator includes a first polarization beam splitter member having a common optical port, a second polarization beam splitter member having an emittance optical port and at least two receiving optical ports, and a first polarization adjustment member. The two receiving optical ports respectively receive two linearly polarized light beams. The two linearly polarized light beams respectively pass through the second polarization beam splitter member, and sequentially pass through the first polarization adjustment member and the first polarization beam splitter member to be combined into a first combined light beam for being output from the common optical port. The common optical port receives a compound optical signal that passes through the first polarization beam splitter member to be split into another two linearly polarized light beams that are combined into a second combined light beam for being output.

Optical circulator and optical module

The provided are a federated reinforcement learning (FRL) end-to-end autonomous driving control system and method, as well as vehicular equipment, based on complex network cognition. An FRL algorithm framework is provided, designated as FLDPPO, for dense urban traffic. This framework combines rule-based complex network cognition with end-to-end FRL through the design of a loss function. FLDPPO employs a dynamic driving guidance system to assist agents in learning rules, thereby enabling them to navigate complex urban driving environments and dense traffic scenarios. Moreover, the provided framework utilizes a multi-agent FRL architecture, whereby models are trained through parameter aggregation to safeguard vehicle-side privacy, accelerate network convergence, reduce communication consumption, and achieve a balance between sampling efficiency and high robustness of the model.

Complex network cognition-based federated reinforcement learning end-to-end autonomous driving control system, method, and vehicular device

The present disclosure relates to a display device and an OLED display panel thereof. The OLED display panel includes a substrate, a first OLED pixel unit and a second OLED pixel unit, an encapsulation layer, a polarizer, and a cover plate, in which an opening of the polarizer between the cover plate and the encapsulation layer is filled with a transparent filler. In a first aspect of the present disclosure, the first OLED pixel unit and the second OLED pixel unit are respectively arranged in a transparent display area and a non-transparent display area, so that when the first OLED pixel unit and the second OLED pixel unit are driven, the transparent display area and the non-transparent display area form a full screen; when the first OLED pixel unit is not driven, the transparent display area performs a light-transmission function.

Display devices and OLED display panels thereof

An arc fault detection circuit includes a signal collection circuit that collects a current signal on power supply lines and to output a first signal; a window gating circuit that generates a window gating signal corresponding to the first signal; and a signal processing circuit, coupled to the signal collection circuit and the window gating circuit, for generating an arc fault signal based on the window gating signal and the first signal. By using the window gating circuit, the arc fault detection circuit performs arc detection only during certain time intervals of the AC period where the harmful arcs will be present. This improves the accuracy of arc detection and reduces the probability of false tripping.

Arc fault detection circuit employing a window gating circuit

A leakage current detection and interruption device includes a switch module for connecting and disconnecting an electrical connection between input and output ends of current carrying lines; a leakage current detection module coupled to the current carrying lines, for detecting a leakage current signal on the current carrying lines and generating a detected signal in response thereto; a leakage current processing module coupled to the leakage current detection module, for receiving the detected signal and generating a leakage fault signal based on the amplitude and frequency of the detected signal; and a drive module coupled to the switch module and the leakage current processing module, for receiving the leakage fault signal and driving the switch module to disconnect the electrical connection in response thereto.

Leakage current detection and interruption device

A leakage current detection and interruption device includes a switch module for connecting and disconnecting input and output ends of current carrying lines; a leakage current detection module for detecting a leakage current signal on the current carrying lines and generating a leakage fault signal in response thereto; an over-temperature protection module for detecting a temperature of a predefined location and/or component of the device and generating an over-temperature fault signal when the detected temperature exceeds a predetermined temperature threshold; a drive module for driving the switch module to disconnect the electrical connection in response to the leakage fault signal and/or over-temperature fault signal; and a self-test module for periodically generating a simulated leakage current signal to detect a malfunction in the leakage current detection module and/or drive module, and generating a self-test fault signal when detecting the malfunction. The device has a simple structure, is low cost and safe.

Leakage current detection and interruption device and related electrical connectors and electrical appliances

A mechanical-electrical-hydraulic composite transmission device and a control method thereof are provided. The device includes an input shaft assembly, a power-split assembly, a hydraulic transmission assembly, an electrical variable transmission assembly, a mechanical transmission assembly, a power-convergence assembly, and an output shaft. Three types of transmission modes including single transmission modes, power-split composite transmission modes, and power-convergence composite transmission modes are implemented by controlling engagement and disengagement of clutches and a brake. Free switching between various transmission modes is realized, the requirements of engineering machinery for a transmission device with multiple modes in different working conditions are satisfied, the engine power utilization is improved, and the fuel economy is increased. The shift impact is effectively reduced and the speed ratio adjustment range is expanded. The hydraulic transmission enables quick startup and stable operation and implements speed variation and direction change easily and rapidly without causing impact.

Mechanical-electrical-hydraulic hybrid transmission device and control method thereof

The present invention related to a brain tumor-targeting peptide, a coding nucleic acid thereof, and a vector and host cell comprising the coding nucleic acid. The targeting peptide linked to a diagnostic marker can be used in brain tumor diagnosis, especially in brain tumor imaging; and the targeting peptide when linked to a therapeutic drug can carry the drug directly to a brain tumor lesion so as to achieve brain tumor treatment.

Brain tumor-targeting peptide and application thereof

The provided is a method and system for trajectory prediction based on Cro-IntentFormer. The method starts by preprocessing vehicle trajectory data collected by sensors to produce raw data suitable for model input. Vehicles are treated as nodes, and the distance between vehicles serves as the basis for determining whether there is an edge between two vehicle nodes. A physical relationship graph is constructed and, along with the raw data, input into a spatio-temporal feature extraction module to obtain the spatio-temporal features of the trajectory. The spatio-temporal feature matrix is then input into an intent prediction module to determine the predicted intentions of the vehicles. Based on the intent information output by the intent prediction module, a semantic relationship graph is reconstructed and input, along with the raw data, into the spatio-temporal feature extraction module to derive the semantic features of the trajectory.

Cro-IntentFormer-based method and system for predicting surrounding vehicle trajectories by integrating driving intentions

A leakage current detection and interruption device includes a switch module; a leakage current detection module for detecting leakage current signal on current carrying lines and generating a leakage fault signal in response thereto; a drive module, coupled to the switch module and the leakage current detection module, for driving the switch module to disconnect electrical connection on the current carrying lines in response to the leakage fault signal; a self-test module, coupled to the leakage current detection module and the drive module, for periodically generating a simulated leakage current signal and detecting malfunction in the leakage current detection module and/or drive module, and generating a self-test fault signal in response thereto; and an alarm module, coupled to the self-test module, for generating an alarm signal in response to the leakage fault signal and/or self-test fault signal. The device can alert the user under tripped or malfunction conditions.

An electrical fault detection and interruption device includes a switch module coupled between input and output ends of current carrying lines, for controlling an electrical connection between the two ends; a signal collection module, for detecting a fault signal on the current carrying lines and converting it to an electrical signal; a signal processing module, for determining whether a fault is present on the current carrying lines based on the electrical signal, and generating an electrical fault signal accordingly; a drive module, for driving the switch module to disconnect the electrical connection between the input and output ends in response to receiving the electrical fault signal; and an alarm module, for generating an alarm signal in response to receive the electrical fault signal. Thus, even when the device malfunctions and loses its protection function, it can still generate an alarm signal to alert the user.

Electrical fault detection and interruption device and related electrical connectors and electrical appliances

An electrical fault detection and interruption device includes a switch module coupled between input and output ends of current carrying lines, a GFCI (ground fault circuit interrupter) fault detection module for generating a ground fault signal when detecting a leakage current on the current carrying lines, an AFCI (arc fault circuit interrupter) fault detection module for generating an arc fault signal when detecting harmful arcs on the current carrying lines, a drive module for driving the switch module to disconnect the electrical connection between the input and output ends in response to the ground fault signal and/or arc fault signal, a fault signal transfer module for generate a simulated leakage current signal in response to the arc fault signal, and a monitoring module for generating a harmful arc signal to test whether the electrical fault detection and interruption device is functioning normally.

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.

Multi-task joint perception network model and detection method for traffic road surface information

A leakage current detection and interruption (LCDI) device includes a leakage current detection module, including a first and a second leakage current detection line and at least one resistive element and/or at least one semiconductor element, configured to detect a leakage current signal on the first or second current-carrying line and to generate a leakage fault signal in response to detecting the leakage current signal. The first and second leakage current detection lines are electrically insulated from each other, and respectively cover one of the first and second current-carrying lines. The at least one resistive element and/or semiconductor element is coupled in series between the first and second leakage current detection lines to form a current path for detecting an open circuit fault in the leakage current detection module. By detecting the fault in the first and second leakage current detection lines, the reliability of the LCDI device is improved.

Leakage current detection and interruption device for power cord and related electrical connectors and electrical appliances

Growing community of inventors

Jiangsu, China

Long Chen