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

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

Beijing Baidu Netcom Science Technology Co., Ltd

Wenchuang Qin

Ke Tang

Jiayong Huang

Qiyang Shao

Xiapeng Peng

Xuguang Lv

The present disclosure provides a method and an apparatus for autonomously driving a vehicle. The method includes: recognizing a centerline of a lane on which a current vehicle is driving; acquiring a lateral distance between the current vehicle and the centerline of the lane, and a real-time speed and a real-time motion curvature of the current vehicle; calculating the lateral distance, the real-time speed, and the real-time motion curvature, based on a preset first spiral line equation, to acquire parameters of a reference spiral line; calculating the parameters, the real-time speed, and the real-time motion curvature, based on a preset second spiral line equation, to acquire a current spiral line; and determining an steering angle instruction of a steering wheel based on a first curvature of the current spiral line; and controlling the current vehicle for autonomous driving based on the steering angle instruction.

Methods, devices, and media for autonomously driving vehicle

Provided are a speed planning method and apparatus for self-driving, a device and a medium, relating to artificial intelligence technologies such as self-driving and deep learning. The solution includes acquiring the current state of a vehicle and interpolating actions based on the current state and a predetermined state table to obtain the target action of the current state. The current state includes at least the remaining running distance and the current speed. The state table is determined based on a reinforcement learning method and includes multiple states and an action performed in each state. The action performed in each state includes at least acceleration.

Speed planning method and apparatus for self-driving, device, medium and vehicle

The present application discloses a vehicle driving control method, an apparatus, a vehicle, an electronic device and a storage medium, relates to artificial intelligence, automatic driving and intelligent transportation in computer technology. Including: dividing a preset driving time period of a vehicle, to acquire multiple driving time points, successively acquiring driving information at a first time point in adjacent driving time points, acquiring driving information at a second time point in the adjacent driving time points according to the driving information at the first time point and a pre-configured driving control amount, calibrating the driving control amount according to the driving information at the first time point and the driving information at the second time point, and determining a driving path between the adjacent driving time points based on the calibrated driving control amount, and controlling a driving of the vehicle according to the driving path.

Vehicle driving control method, apparatus, vehicle, electronic device and storage medium

The present disclosure provides a control method and apparatus for an autonomous vehicle, a computer device and a storage medium. The current steering wheel angle, vehicle speed and yaw rate are obtained, the current steering wheel angle is corrected based on the first correction deviation coefficient and the second correction deviation coefficient of the previous cycle, the corrected steering wheel angle and the current vehicle speed are input into the preset vehicle dynamic model to obtain the estimated yaw rate, the first yaw rate deviation value between the current yaw rate and the estimated yaw rate is obtained, and processed by the preset closed-loop algorithm to obtain the first correction deviation coefficient and the second correction deviation coefficient of the current cycle, and the target steering wheel angle is corrected, and the vehicle is driven based on the corrected target steering wheel angle.

Growing community of inventors

Beijing, China

Wenchuang Qin