A lane-changing trajectory planning method for dynamic automatic driving based on real-time environmental information

Abstract

The invention discloses a dynamic automatic drive lane-changing trajectory planning method based on real-time environment information. A rollover limitation trajectory vertical coordinate, an optimal trajectory and a collision avoidance trajectory terminus security area are calculated; the relation between the rollover limitation trajectory vertical coordinate and the security area is compared, the positional relation between the optimal trajectory vertical coordinate and the security area is further compared, and then lane-changing decision-making is conducted. According to the dynamic automatic drive lane-changing trajectory planning method based on the real-time environment information, and a polynomial trajectory equation which dose not depend on time is adopted to represent a lane-changing trajectory curve, so that the problem that hypotheses of a speed and an accelerated speed are too strong is avoided; furthermore, collision avoidance algorithm and rollover prevention algorithm which are based on reaction time are introduced to guarantee security of lane-changing; then the optimal trajectory in a safe trajectory cluster is determined through real-time speed adjusting; and finally, an optimal lane-changing trajectory of real-time dynamic state is output through a trajectory generation module to guide an autonomous vehicle to complete a lane-changing behavior, and therefore a set of complete dynamic autonomous vehicle lane-changing trajectory planning module is built.

Description

technical field [0001] The invention relates to a dynamic automatic driving lane-changing track planning method based on real-time environmental information. Background technique [0002] Autonomous driving technology is considered to be an important means to solve traffic congestion problems and improve traffic safety in the future, which is beneficial to society, drivers and pedestrians. The rapid increase in the market share of autonomous vehicles will lead to a steady decline in the overall accident rate, even if it is disturbed by the accident rate of other vehicles. And the driving mode of self-driving vehicles can be more energy-efficient, so traffic congestion and air pollution will be reduced. In recent years, the development of autonomous driving technology has been rapid. On the one hand, major automakers represented by Tesla, Mercedes-Benz, and Volvo have united with auto parts manufacturers and strengthened cross-industry cooperation to develop autonomous drivi...

AI Technical Summary

Problems solved by technology

First, it is assumed that the speed of the surrounding vehicles does not change during the lane change process, which is inconsistent with the real driving environment

Second, the current models do not consider the real-time response of the lane-changing vehicles according to the changes of the surrounding vehicle status during the lane-changing process, and the dynamic adjustment of the speed in real time, so these models may fail in real traffic environments

Third, in terms of safety, the above research believes that as long as the lane change is completed, the lane-changing vehicle and the vehicle in the target lane do not collide, and there is no need to maintain a safe distance when an emergency occurs. This method is actually Can't really guarantee the safety of changing lanes

However, this model also has some shortcomings

First of all, the model does not consider the reaction time of the system, and the reaction time has a very important impact on driving safety and system stability analysis, which cannot be easily ignored; secondly, due to the use of a time-dependent polynomial trajectory equation, the paper assumes that the starting point of the lane change The longitudinal acceleration of the vehicle at the end point is zero, and it is assumed that the end point speed of the lane change is known (the paper sets it as the average speed of the target lane), these assumptions are not consistent with the real situation

Images