Baidu Online Network Technology (beijing) Co., Ltd.

Tsinghua University

Chinese Academy of Sciences

Apollo Intelligent Driving Technology (beijing) Co., Ltd.

Plant Bioscience Limited

New H3c Security Technologies Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Gaona Aero Material Co., Ltd.

Institute of Genetics and Developmental Biology

Tian Xia

Han Gao

Xun Sun

Yuqiang Zhai

Ji Wan

Shufu Xie

Yu Ma

Ji Tao

Jiajia Chen

Bin Wang

Hao Wang

Li Wang

Qi Cheng Li

Rui Wang

Qinglai Guo

Hongbin Sun

Wenchuan Wu

Na Li

Xing Hu

Guo Qiang Li

Michael W Bevan

Yunhai Li

Yucheng Wang

Jack Dumenil

Haotian Liu

Yilin Gui

Bo Li

Liang Wang

Xiao Xi Liu

Guang Cheng Li

Chang Huang

Tianlei Zhang

Haisong Wang

Yifeng Shi

Dongming Chen

Jiang Tao Wang

Shijia Chen

Zhongnan Bi

Mingyu Li

Shaoming Zhang

Xiaoyi Zou

Shixi Chen

Yuanqing Lin

Ming Li

Mingjian Liu

Xuehui Wang

Jinglong Qu

Shoubo Han

Guangbao Sun

Huiping Ma

The present disclosure provides a message forwarding method and apparatus, a domain name address query method and apparatus, a network address translation device, and a computer-readable medium. The message forwarding method includes: receiving a first address query request for a target domain name sent by a client; if not finding the network address corresponding to the target domain name locally, sending a second address query request for the target domain name to a domain name system; receiving a second response message returned by the domain name system for the second address query request, which includes a first network address and address translation information; sending a first response message to the client; and after receiving a service message whose destination address is the first network address sent by the client, according to the address translation information, translating the destination address of the service message to the second network address, and sending the service message with the translated destination address to the target server. The method can realize the automatic operation and maintenance of the network address translation equipment and ensure the timely and accurate cross-protocol forwarding of network messages.

Message forwarding and domain name address querying

A power grid reactive voltage control model training method. The method comprises: establishing a power grid simulation model; establishing a reactive voltage optimization model, according to a power grid reactive voltage control target; building interactive training environment based on Adversarial Markov Decision Process, in combination with the power grid simulation model and the reactive voltage optimization model; training the power grid reactive voltage control model through a joint adversarial training algorithm; and transferring the trained power grid reactive voltage control model to an online system. The power grid reactive voltage control model trained by using the method according to the present disclosure has transferability as compared with the traditional method, and may be directly used for online power grid reactive voltage control.

Power grid reactive voltage control model training method and system

A ranging method based on a laser radar system, a device and a readable storage medium are provided. The ranging method includes receiving ranging data obtained by measuring via a plurality of laser radars of a laser radar system, where the ranging data includes distances between the laser radars and obstacles in measurement ranges of the laser radars; establishing a three-dimensional coordinate model according to the ranging data; and determining a distance between a target unmanned device and each obstacle according to the three-dimensional coordinate model. The ranging method can realize a ranging calibration task for a larger distance range, thereby effectively improving a calibration efficiency and accuracy of the visual image algorithm, compared with the existing method of ranging calibration of the visual image algorithm by a single laser radar.

Ranging method based on laser radar system, device and readable storage medium

A method and apparatus for establishing a fast-forwarding table are provided. The method comprises: when a communication packet is received, determining, according to matching rules of services set in a packet processing policy, a target service matching the communication packet; if a fast-forwarding table corresponding to the communication packet is not stored locally, obtaining a preset target priority of the target service, and determining a target resource utilization threshold corresponding to the target priority according to a preset correspondence between priorities and resource utilization thresholds; determining whether a current resource utilization is greater than the target resource utilization threshold; and establishing a fast-forwarding table corresponding to the communication packet if the current resource utilization is not greater than the target resource utilization threshold. With this disclosure, the memory pressure of the network device can be reduced, and the network device can be avoided to hang or restart.

Establishment of fast forwarding table

A method, device, apparatus and a computer-readable storage medium for detecting a height of an obstacle are provided. The method can include: acquiring observation data of a plurality of reference obstacles from a frame; according to the observation data of each of the reference obstacles, fitting a function F: Z=F(ymax), wherein the observation data of a reference obstacle comprises a longitudinal coordinate of a bottom of the reference obstacle in the frame, and a distance between the reference obstacle and a camera capturing the frame; and determining a distance between the obstacle to be detected and the camera, according to the longitudinal coordinate of the bottom of the obstacle in the frame and the function F; and determining an evaluation value of the height of the obstacle to be detected according to the distance between the obstacle to be detected and the camera.

Method, device, apparatus and storage medium for detecting a height of an obstacle

This invention relates to a plant E3 ubiquitin ligase (termed DA2) which acts synergistically with DA1 to control seed and organ size. Methods of increasing plant yield are provided that comprise reducing the expression or activity of DA2 in a plant that is deficient in DA1 expression or activity. Plants with increased yield and methods of producing such plants are also provided.

Methods of modulating seed and organ size in plants

A power grid reactive voltage control method and control system based on two-stage deep reinforcement learning, comprising steps of: building interactive training environment based on Markov decision process, according to a regional power grid simulation model and a reactive voltage optimization model; training a reactive voltage control model offline by using a SAC algorithm, in the interactive training environment based on Markov decision process; deploying the reactive voltage control model to a regional power grid online system; and acquiring operating state information of the regional power grid, updating the reactive voltage control model, and generating an optimal reactive voltage control policy. As compared with the existing power grid optimizing method based on reinforcement learning, the online control training according to the present disclosure has costs and safety hazards greatly reduced, and is more suitable for deployment in an actual power system.

Power grid reactive voltage control method based on two-stage deep reinforcement learning

Embodiments of the present application provide a lane line processing method and a lane line processing device. The method can include: performing a binarization processing on a first image to obtain a binary image, the first image including lane line points and non-lane line points; performing a connected domain analysis on the binary image to obtain at least one connected domain in the binary image, the connected domain including a plurality of adjacent lane line points; determining lane line points in a group corresponding to a lane line, based on the connected domain; and obtaining representation information of the lane line corresponding to the group, by using the lane line points in the group.

Lane line processing method and device

Embodiments of the present disclosure provide a method and a device for assisting in controlling automatic driving of a vehicle, a medium, and a system. The method for assisting in controlling automatic driving of a vehicle may include: acquiring sensing information related to environment collected by a sensor, the sensor being disposed in the environment and independent of the vehicle; determining an environment sensing result related to the environment by processing the acquired sensing information, the environment sensing result indicating relevant information about a plurality of objects including the vehicle in the environment; and providing the environment sensing result to a vehicle-side control device associated with the vehicle for assisting in controlling a driving behavior of the vehicle.

Method and device for assisting in controlling automatic driving of vehicle, and system

Embodiments of the present disclosure disclose a method for position detection, a device, and a storage medium. The method includes: detecting a first lane line in a current image captured by a camera; performing an optimization on an initial transformation matrix reflecting a mapping relationship between a world coordinate system and a camera coordinate system based on a detection result of the first lane line; and obtaining a first 3D coordinate of a target object in the current image according to a transformation matrix optimized, and determining an ultimate 3D coordinate of the target object according to the first 3D coordinate.

Method for position detection, device, and storage medium

The present application provides autonomous vehicle based position detection method and apparatus, a device and a medium, where the method includes: identifying an obtained first visual perception image according to an underlying neural network layer in a slender convolution kernel neural network model to determine feature information of the target linear object image, and identifying the feature information of the target linear object image by using a high-level neural network layer in the slender convolution kernel neural network model to determine size information of the target linear object image; further, matching the size information of the target linear object image with preset coordinate system map information to determine a position of the autonomous vehicle. Embodiments of the present application can accurately determine the position of the autonomous vehicle.

Autonomous vehicle based position detection method and apparatus, device and medium

A method and device of multi-focal sensing of an obstacle. A method includes acquiring detection results of obstacles at multiple moments by utilizing a camera with long focus lens and a camera with short focus lens; performing a target tracking to the acquired detection results, to obtain at least two tracking sequences, wherein each tracking sequence includes detection results acquired at the multiple moments for a same obstacle; and matching two random tracking sequences of the at least two tracking sequences, and combining the two random tracking sequences into a combined tracking sequence, if the matching is successful.

Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium

Embodiments of the present disclosure provide a method and an apparatus for recognizing a traffic light, a device, a storage medium, and a vehicle. The method may include: obtaining semantic information of one or more traffic lights provided at an intersection, and recognizing states of the one or more traffic lights in an image captured by a camera; determining traffic lights representing same semantics from the one or more traffic lights based on the semantic information, and determining a uniform state corresponding to the traffic lights representing the same semantics according to states of the traffic lights representing the same semantics and preset confidences of respective traffic light states; and determining indication information of the traffic lights representing the same semantics according to the uniform state.

Method for recognizing traffic light, device, and vehicle

The present disclosure provides a visual perception method, an apparatus, a device and a medium based on an autonomous vehicle, the method includes inputting an obtained first visual perception image collected by the autonomous vehicle into a first neural network model, recognizing multi-channel feature information of at least one target recognition object to be recognized, to eliminate redundant feature information in the first visual perception image; further, inputting the multi-channel feature information of the at least one target recognition object to be recognized into at least one sub-neural network model in a second neural network model respectively, to obtain at least one target recognition object; where there is a one to one correspondence between the target recognition object and the sub-neural network model. The present disclosure improves the speed of recognizing the target recognition object, thereby improving sensitivity of the autonomous vehicle and ensuring driving safety of the autonomous vehicle.

Visual perception method, apparatus, device, and medium based on an autonomous vehicle

A lane line processing method and device are provided. The method can includes obtaining distances between lane line points in a first image, determining direction densities of the individual lane line points by using the distances between the lane line points, dividing lane line points into groups corresponding to lane lines by using the direction densities of the individual lane line points, and obtaining representation information of the lane lines corresponding to the groups by using the lane line points in the groups. By using the direction densities of the individual lane line points, lane line points in an image are divided into groups, the obtained groups are then more accurate, and thus the lane lines obtained by fitting are accurate, are less susceptible to image quality issues, and have high robustness.

Growing community of inventors

Beijing, China

Tian Xia