Reinforcement learning algorithm applied to non-tracking intelligent trolley barrier-avoiding system

Abstract

The invention discloses a reinforcement learning algorithm, including a new Q learning algorithm. The new Q learning algorithm includes the implementation steps of: inputting collected data to a BP neural network, and calculating input and output of each unit of a hidden layer and an output layer in the state; calculating a maximum output value m in a t state, based on the output, judging whether a collision with a barrier occurs, if a collision occurs, recording each unit threshold value and each connection weight of the BP neural network, and otherwise calculating T+1 moment, collecting data and performing normalization, calculating input and output of each unit of the hidden layer and the output layer in the t+1 state, calculating an expected output value of a t state, adjusting output and the threshold value of each unit of the hidden layer, judging whether an error is smaller than a given threshold value or the number of times of learning is larger than a given value, if the condition is not satisfied, performing learning again, and otherwise recording the threshold value of each unit and each connection weight, finishing learning. The reinforcement learning algorithm provided by the invention has good real-time performance and good rapidity, and allows relearning in a later period.

Description

technical field [0001] The invention relates to a reinforcement learning algorithm applied to an obstacle avoidance system of a non-tracking intelligent car, belonging to the field of robotics research. Background technique [0002] In the future of automobile creation, my country, as a world power, must also occupy a place in the high-tech field. The intelligentization of future automobiles is the inevitable direction of the development of the automobile industry. In this case, the obstacle avoidance system of intelligent vehicles is particularly critical. , which will play an important role in my country's future smart car research to occupy a leading position in the world's high-tech field. [0003] How to make the obstacle avoidance system realize the automatic avoidance of obstacles in the process of autonomous driving, so as to realize the detection of unknown environments in areas that people cannot reach (need to be used in conjunction with monitoring equipment) has b...

AI Technical Summary

Problems solved by technology

[0012] The technical problem to be solved by the present invention is to provide a reinforcement learning algorithm applied to the non-tracking intelligent car obstacle avoidance system with good real-time performance, good rapidity, and relearnable later stage, and solves how to reduce the number of sensors Without changing the required collection of environmental data and how to achieve accurate and fast obstacle avoidance without manual control

Images