Self-adaptive hunting device using multiple robot pursuers to hunt single moving target and method

Abstract

The invention discloses a self-adaptive hunting device using multiple robot pursuers to hunt a single moving target and a method. The method comprises multiple-stage dividing of a hunting process, a pursuing policy based on a bionic neural network, angular relationship surrounding and multiple virtual potential points. According to the step of multiple-stage dividing of the hunting process, multiple-stage modeling is carried out for the hunting process; a hunting task is divided into four stages of searching, pursuing, surrounding and arresting; and policies corresponding to four stages are used for controlling. According to the pursuing policy based on the bionic neural network, a bionic neural network method used in a multiple-robot system is migrated to a hunting environment, and hunting guide is carried out on multiple robot pursuers. According to angular relationship surrounding, an angular relationship is used to adjust the movement direction of the pursuers. According to multiple virtual potential points, multiple virtual potential points are arranged to form an arresting formation, and the final hunting task is completed. According to the invention, the hunting process is divided into different stages; in the pursuing stage, the bionic neural network method is used to solve uncertainty, dynamics and instantaneity of an environment; and efficient obstacle avoidance and hunting are completed.

Description

technical field [0001] The invention relates to the technical field related to robot chasing and rounding up, in particular to an adaptive rounding up device and method for multi-robot hunters rounding up a single moving target. Background technique [0002] Moving target siege means that the hunter surrounds the moving target, so that the moving target has no way to escape, and then takes the next step. This requires multi-hunters not to simply hunt independently, but to cooperate to complete the round-up task efficiently. Such collaboration among multiple pursuers is regarded as a robotic system in robotics, which becomes a challenging key problem and produces a lot of research results. The current research on the multi-robot round-up problem can be roughly divided into two models: the sensor-based model and the known localization model. In sensor-based models, a common control method is to capture in an unknown environment, guide and control by introducing sensor data. ...

AI Technical Summary

Problems solved by technology

However, there are still some limitations for these two models to be transferred to the multi-robot hunter problem: the sensor-based model only uses the data of the sensors carried, and does not use communication technology, making this method difficult, and the complexity of the algorithm varies with With the increase of the number of robots and evaders, it rises sharply; the known positioning model assumes that the position of evaders is known, which is very difficult in the real world, and then cannot satisfy the characteristics of simulating reality and being close to reality

There are also some methods that need to use training data sets for learning or data mining. When applied to specific multi-robot roundups, each change of environmental information such as maps requires different data sets, which is unrealistic and inflexible.

Images