Unmanned mining truck tracking control system and method based on deep reinforcement learning

Abstract

The invention provides an unmanned mining truck tracking control system and method based on deep reinforcement learning. In a learning stage, environment state information and control action information are received through a simulation platform to simulate a tracking process of an unmanned mining truck, the states of the unmanned mining truck at all moments on a preset route are collected, and deep reinforcement learning training is performed by taking the states at all moments as input quantities and the control action information at all moments as output quantities to obtain an algorithm kernel; in an application stage, the state of the unmanned mining truck at the current moment and the target state of the unmanned mining truck at the next moment are acquired and sent to the algorithmkernel; and the control action information at the current moment is predicted based on the algorithm kernel. According to the invention, accurate control of the motion trail of the unmanned mining truck can be realized, automatic tracking can be carried out according to an algorithm trained by deep reinforcement learning under different working conditions and different working environments and states, and the system and the method have the characteristics of high intelligence, self-learning and self-adaptation. Moreover, the efficiency of mining truck tracking control is improved, and the fuelconsumption can be reduced.

Description

technical field [0001] The invention relates to an unmanned mine truck tracking control system and method based on deep reinforcement learning, which belongs to the technical field of automation control. Background technique [0002] In metal mines, mining trucks are an important transportation equipment in metal mines. A large number of ores, equipment, materials, and personnel depend on the transportation of mining trucks. The operating route of the mining truck is fixed, the operating route is closed, and the operation process is easy to achieve program standardization. There is an objective basis for the realization of unmanned driving of mining trucks. Unmanned mining trucks are an important link in the realization of digital mines, which can achieve maximum safety in transportation and avoid accidents such as collisions, derailments, and rear-end collisions that cause harm to personnel. The unmanned mining truck transportation system can carry ore in more dangerous pl...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the control problem of low trajectory tracking accuracy caused by the high-dimensional continuous behavior space and nonlinear properties of unmanned mining trucks in the prior art, the present invention provides a tracking control of unmanned mining trucks based on deep reinforcement learning System and method

Images