Vehicle speed control device and method

Abstract

The invention discloses a vehicle speed control device and method. The vehicle speed control device comprises an environment sensing and integration module, a pedestrian jaywalking behavior cognition module and an automatic driving decision-making module, wherein the environment sensing and integration module is used for detecting the information of a jaywalking pedestrian in front of a running vehicle and outputting the information of the jaywalking pedestrian; the pedestrian jaywalking behavior cognition module is used for receiving the information of the jaywalking pedestrian and outputting the pedestrian's behavior cognition information according to the received information of the jaywalking pedestrian combined with the dynamic time series information and the interaction between the vehicle and the pedestrian; and the automatic driving decision-making module is used for receiving environment information and pedestrian's behavior cognition parameters, giving the current traffic speed of the vehicle, and outputting the current traffic speed of the vehicle. According to the vehicle speed control device and method disclosed by the invention, in the running process of the vehicle, the pedestrian target in front of the vehicle can be accurately recognized, the pedestrian's intention can be predicted, real-time judgment is performed, reasonable decision can be made, and autonomous recognition and decision-making of an autonomous vehicle can be realized when a pedestrian crosses the road, so that the vehicle can safely and smoothly give way to the pedestrian crossing the road.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to a vehicle speed control device and method. Background technique [0002] Self-driving vehicles realize autonomous driving through technologies such as environmental perception, cognition, decision-making, and vehicle control. Self-driving vehicles have a positive effect on traffic safety, traffic efficiency, environmental protection and energy saving. Governments and road-related operators around the world are increasingly interested in self-driving cars, hoping that self-driving cars can make road traffic safer, more efficient and more environmentally friendly. Self-driving vehicles improve the reaction speed to the traffic environment by autonomously sensing the environment, cognition, decision-making and control, and quickly perform corresponding operations in different scenarios, including dangerous scenarios, such as braking and steering, thereby improving traffic safety. ...

AI Technical Summary

Problems solved by technology

Pedestrian recognition mainly uses sensors such as monocular or binocular cameras and multi-line lidar. Through feature extraction, the features are used as the input for classification, and the supervised learning algorithm is used for classification learning. Its classification ability is good, but its ability to identify motion parameters is poor.

The pedestrian behavior cognition method mainly builds a cognitive model through the Markov theory, which is mainly aimed at the pedestrian itself, without considering the interaction between vehicles and pedestrians.

The research on the pedestrian protection system is mainly on the pedestrian recognition method, lack of research on the pedestrian behavior cognition method, comprehensively consider the research on pedestrian recognition and behavior cognition methods, and do not further consider the impact of pedestrian recognition and behavior cognition results on vehicles. impact of decision

[0004] At this stage, for autonomous driving technology, pedestrian recognition and behavior cognition have the following problems: 1) Unable to autonomously recognize and learn and predict the behavior of pedestrians crossing the road, and the intelligent level of the decision-making system is low

2) Does not consider the interaction and interaction between pedestrians and vehicles in the driving road environment

3) When pedestrians cross the road or have the intention of crossing the road, simply setting the distance threshold for decision-making cannot meet the needs of complex traffic environments

4) It is difficult to accurately detect pedestrians and give corresponding information such as position and movement with the help of a single camera

Among them, although binocular vision can identify the target category and give target depth information, the computational complexity is relatively high, and it cannot meet the real-time recognition requirements of automatic driving.

Monocular vision cannot output target depth information, which is not conducive to automatic driving decision-making

5) Recognizing and judging pedestrians with the help of sensors such as multi-line laser radar, the cost is high, and it is difficult to realize industrialization and the promotion and application of automatic driving

Images