Unprotected left-turn driving control method based on deep reinforcement learning

Abstract

The invention discloses an unprotected left-turn driving control method based on deep reinforcement learning, and the method comprises the following steps: 1, building a simulation and training environment: 1) building two same closed road environment simulation scenes; 2) setting proper simulation running time, and generating any number of unprotected LTAP / OD events; 3) setting a plurality of straight vehicles and three left-turn vehicle candidate paths; 2, designing a reward function, and processing a complex unprotected LTAP / OD event by adopting the driving skill of a human driver; 3, designing a strategy structure, updating parameters of the deep convolution fuzzy system by using a learning algorithm, and searching an optimal value function; and 4, designing a learning algorithm, and improving the training efficiency by adopting the data of the human driver and a deep convolution fuzzy system algorithm. The combination of the driving skill of the human driver and the deep convolution fuzzy system algorithm effectively improves the interpretability of the deep reinforcement learning algorithm, the error correction capability of the training efficiency and the passing efficiency of the vehicle.

Description

technical field [0001] The invention belongs to the field of motion control of middle and high-level automatic driving vehicles, and in particular relates to a method for training an unprotected left-turn control model used to generate an automatic driving strategy. Background technique [0002] Scenarios where a straight-going vehicle (SDV) and a left-turning vehicle (TV) are traveling in opposite directions at an intersection without traffic signals or other stop signs (LTAP / OD, figure 1 ), efficiently and safely complete an unprotected left turn, which is highly challenging not only for autonomous vehicles, but also for human drivers. Existing self-driving cars pay more attention to the robustness of the algorithm when completing an unprotected left turn, and mostly rely on manual customization of rules, often adopting an overly conservative strategy. Although the safety is guaranteed to a certain extent, the traffic efficiency is low low. In contrast, experienced human...

AI Technical Summary

Problems solved by technology

However, due to the inexplicability of the deep neural network model, the training efficiency and error correction ability of the model are greatly limited.

Images