Hybrid lane-changing decision-making method for emergency vehicles based on reinforcement learning and avoidance strategy

Abstract

The invention relates to a mixed lane-changing decision-making method for emergency vehicles based on reinforcement learning and avoidance strategy, including: determining the optimal road section and the execution strategy of the ICCV and ICEV to be planned; initializing the DQN network of the ICEV to be planned; The state information of the six neighboring vehicles and the implementation of the avoidance strategy of the preceding vehicle are obtained to obtain the state space of the DQN network; the output value is obtained based on the state space of the DQN network, and the preliminary decision and action space are obtained based on the output value; an action selection barrier is established to The obtained preliminary decision is verified and selected until the final action selected from the output value or action space satisfies the traffic rules and road physical structure; the reward function is defined to calculate the total reward corresponding to the action; the DQN network Perform training to obtain a trained DQN network. The invention can be widely used in the field of road lane change decision control.

Description

technical field [0001] The invention belongs to the field of road lane-changing decision-making control, and in particular relates to a mixed lane-changing decision-making method for emergency vehicles based on reinforcement learning and an avoidance strategy. Background technique [0002] At present, most of the relevant research on reducing the response time of emergency vehicles focuses on route optimization and traffic light control, trying to solve the problem from the perspective of macro-scheduling, such as: Dijkstra algorithm, ant colony algorithm (ACA), A* and hybrid leapfrog algorithm (SFLA). However, these macro-level approaches do not take full advantage of real-time traffic data, seldom provide micro-level control of autonomous emergency vehicles, hardly consider the impact on normal traffic flow, and ignore the delay of response time on straight roads. [0003] In addition, a small number of studies have mentioned deterministic algorithms for micro-controlling...

AI Technical Summary

Problems solved by technology

However, these macro-level approaches do not take full advantage of real-time traffic data, seldom provide micro-level control of self-driving emergency vehicles, hardly consider the impact on normal traffic flow, and ignore the delay of response time on straight roads.

[0003] In addition, a small number of studies have mentioned deterministic algorithms for micro-controlling the automatic driving of emergency vehicles on straight roads, such as a series of car-following and lane-changing strategies, including some targeted avoidance strategies, but the strategies obtained by deep reinforcement learning They are more difficult to generalize to various traffic scenarios than them, and are not necessarily optimal in exploring faster speeds

Images