31results about How to "Improve autonomous driving performance" patented technology

Disclosed are a road surface condition sensing system and method. The road surface condition sensing system includes an acoustic sensing unit for sensing an acoustic signal of a floor of a vehicle, and a control unit for calculating a feature vector by Fourier transforming the sensed acoustic signal, comparing the calculated feature vector with a plurality of previously stored feature vectors and returning a first feature vector having the smallest relative distance to the calculated feature vector, and outputting a road surface condition corresponding to the first feature vector.

The invention discloses a transverse and roll comprehensive control method for an automatic driving distributed driving electric automobile, and belongs to the technical field of automobile intelligent safety and automatic driving. Travelling state information and reference path information of the automatic driving distributed driving electric automobile are collected through a vehicle-mounted sensing system, a roll effect and an actuator fault are considered, a Takagi-Sugeno fuzzy transverse control model with parameter uncertainty and time-varying characteristics is established, the robust transverse and roll angle comprehensive control method for the automatic driving distributed driving electric vehicle is designed, and meanwhile, an observer based on the Takagi-Sugeno model is provided for the unmeasurability of the roll angle and the roll angle speed in the driving process of the automatic driving distributed driving electric automobile. The influence of the roll effect and the actuator fault on transverse motion control of the automatic driving distributed driving electric automobile is overcome, and the autonomous driving performance of the automatic driving distributed driving electric vehicle is improved.

An autonomous driving module mounting structure, includes a roof panel configuring an upper portion of a vehicle body, an open portion provided at the roof panel, and an autonomous driving module that includes a plurality of devices, that is mounted on an upper surface of an outer section of the roof panel, and that is disposed at a position that does not coincide with the open portion in top view.

Embodiments of the present disclosure disclose a method, device, device and computer-readable medium for generating obstacle detection information. A specific embodiment of the method includes: acquiring an image to be detected; generating a first target image and a second target image based on the image to be detected; generating a first regression prediction result set, a first classification prediction result set, a second regression A prediction result set and a second classification prediction result set; decoding the first regression prediction result set and the second regression prediction result set respectively to obtain a first decoding result set and a second decoding result set; generating a first detection information set; generating a second detection information set; performing data fusion processing on the first detection information set and the second detection information set to generate an obstacle detection information set. This embodiment realizes the generation of obstacle detection information, improves the generation quality of obstacle detection information, and provides convenience for automatic driving of vehicles.

The present application relates to an obstacle position recognition method, device, computer equipment and storage medium. The method includes: acquiring depth information, plane area information, and body area information corresponding to the obstacle; determining the target obstacle when the depth information, plane area information, and body area information are similarly matched; Set the location information, calculate the distance error information between the depth information, the plane area information and the main area information and the preset location information respectively; calculate the conditional probability distribution of the sensor observation information under the preset location information according to the distance error information; The distribution is estimated to obtain the target position information corresponding to the target obstacle. Using this method can improve the accuracy of estimating the position of obstacles that partially enter the field of view of the camera, thereby improving the performance of automatic driving.

The present invention proposes a method, device and electronic equipment for adjusting the processing frequency of a vehicle control model, wherein the method includes: acquiring the running state information of the vehicle, determining the target frequency for data processing of the vehicle control model according to the running state information of the vehicle, and The target frequency is configured with the first timer, and the second timer used by the vehicle control model is changed to the first timer, so that the first timer is used to control the vehicle control model to process data based on the target frequency, which realizes that in the case of limited resources , the target frequency of the model is determined through the vehicle running status information, and the frequency of data processing of the control model is dynamically adjusted by changing the timer used, which realizes the reasonable allocation of limited system resources, and the performance of the vehicle is too high The method solves the technical problem that the frequency of the control model cannot be dynamically adjusted in the prior art, resulting in unreasonable resource allocation.

The present invention provides a target recognition and learning method suitable for automatic driving of a vehicle-mounted short-distance communication network. For a specific road section, the roadside node at the starting point is configured with the identification factor of the road section, and the corresponding weak classifier and historical experience weight value will be The configured information is sent to the vehicle driving on the road section. During the driving process of the road section, the vehicle uses the weak classifier to build a strong classifier according to the real-time collected road condition information, and uses the strong classifier to identify each identification factor. The vehicle updates the weight value of the weak classifier according to the recognition result and actual operation, and updates the strong classifier. When the vehicle drives out of the road section, it sends the updated weight value of the weak classifier to the roadside node at the end point, and the roadside node at the end point The node sends the weight value of the weak classifier to the roadside node at the starting point as the historical experience weight value of the weak classifier. In the above process, it continuously learns the driving mode on this road section, and gradually improves the automatic driving that meets the characteristics of this road section. performance.