Authors

Abstract

In the layout of modern agricultural warehouse logistics handling industry, it is an inevitable way to realize industrial upgrading by replacing people with mobile robots. Aiming at the problems that the existing obstacle avoidance control algorithm of agricultural handling robot is easy to fall into local optimal solution, and the operation process of agricultural warehouse logistics handling robot is prone to collision, the obstacle avoidance control of agricultural warehouse logistics handling robot is studied, and a control algorithm based on improved potential field ant colony is proposed. The moving trajectory of the agricultural warehouse logistics handling robot during the handling process is studied, and the spatial kinematics equation of the robot is given. The ant colony algorithm is used to optimize the classical artificial potential field algorithm to improve the global optimization ability and balance the interaction between gravity and repulsion. In the aspect of local area obstacle avoidance of agricultural storage and handling robots, the artificial potential field is optimized twice based on the strategy gradient algorithm. By analyzing the probability of the next action command, the randomness of the travel path selection when multiple robots work at the same time is improved. After testing, the path of the proposed control algorithm is the shortest, and under the condition of complex path planning, the number of collisions between robots is also significantly less than that of the traditional obstacle avoidance control algorithm. The practical application can meet the needs of improving the efficiency of warehouse logistics management.

Abstract in Chinese

在现代化农业仓库物流搬运产业布局中，通过移动机器人取代人来实现产业升级是一条必由之路。针对现有农业搬运机器人避障控制算法存在的路径寻优易陷入局部最优解，及农业仓库物流搬运机器人作业过程易发生碰撞等问题，对农业仓库物流搬运机器人的避障控制进行了研究，并提出一种基于改进势场蚁群的控制算法；对农业仓库物流搬运机器人搬运过程中的移动轨迹进行了研究，给出了机器人空间运动学方程；采用了蚁群算法对经典人工势场算法进行优化，提升全局寻优能力并平衡引力和斥力的相互作用关系；在农业仓储搬运机器人的局部区域避障方面，基于策略梯度算法对人工势场做二次优化，通过分析下一动作指令的发生概率，改善多机器人同时作业时行进路径选择的随机性；经测试，提出控制算法的路径最短，而且在复杂路径规划条件下，机器人之间发生碰撞的次数也显著少于传统避障控制算法，经实际应用能够满足提升仓储物流管理效率的需求。