Anthropomorphic automatic driving strategy based on model predictive control

Abstract

The invention provides a personification automatic driving strategy based on model prediction control. The personification automatic driving strategy comprises the following steps: establishing a vehicle state prediction model based on a model prediction control algorithm according to a vehicle nonlinear kinematics model; based on a hybrid logic dynamic method, an automatic driving vehicle collision safety hard constraint is established in combination with the vehicle state prediction model; establishing a decision planning optimization model by taking a performance target representing comfort and controlling energy consumption as a target function according to the collision safety hard constraint; and performing weight assignment on a performance target in the decision planning optimization model based on driver personification behavior characteristics to obtain a model prediction control-based personification automatic driving strategy. According to the invention, the technical problem that the existing automatic driving decision planning can only realize obstacle avoidance driving in a simple environment and cannot accurately evaluate the vehicle driving risk in real time in a complex dynamic driving environment can be solved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to an anthropomorphic automatic driving strategy based on model predictive control. Background technique [0002] In recent years, since autonomous driving technology provides a new solution to urban congestion, environmental pollution, and traffic safety issues, it has received unprecedented development and widespread attention. Decision planning in automatic driving strategy is one of the key technologies in automatic driving, which can be divided into global path planning and local path planning. Local planning refers to planning the actual driving trajectory of the vehicle in a short period of time in the future based on the real-time running state of the vehicle and the environmental state. [0003] The local planning of autonomous vehicles can essentially be attributed to an optimization problem, that is, the solution of the optimal trajectory and state to achieve i...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies in the existing technology, the present invention proposes an anthropomorphic automatic driving strategy based on model predictive control to solve the problem that the automatic driving decision-making planning in the prior art can only realize obstacle avoidance driving in a simple environment, and in the face of complex The technical problem that the real-time and accurate assessment of vehicle driving risk cannot be performed in a dynamic driving environment

Images