Mobile robot obstacle avoidance method based on pedestrian prediction

Abstract

The invention discloses a mobile robot obstacle avoidance method based on pedestrian prediction, and the method refers to a thought that people can analyze the movement trend of moving obstacles when facing the moving obstacles, and then carry out the avoidance in advance. The moving robot is divided into a long and narrow corridor section and a wide hall section according to different scenes in the running process of the moving robot, when the robot encounters pedestrians in front, a social force model is used for predicting the walking track of the robot in the next period of time, an inactive avoiding mode is adopted in the long and narrow corridor section, and the speed of the robot is adjusted according to the predicted positions of the pedestrians; when the pedestrian is located in a hall section, an active avoidance strategy is adopted, a dynamic window method (DWA) is improved, and an evaluation item for predicting the direction of the pedestrian is newly added in an original evaluation function, so that the improved algorithm can avoid the position to which the pedestrian wants to walk in advance. According to the mobile robot obstacle avoidance method provided by the invention, the walking intention of the pedestrian is added to the obstacle avoidance decision of the robot, and the dynamic obstacle avoidance efficiency of the mobile robot is improved.

Description

technical field [0001] The invention belongs to the technical field of automation, and in particular relates to an obstacle avoidance method for a mobile robot based on pedestrian prediction. Background technique [0002] In recent years, with the continuous advancement of science and technology, the logistics construction of logistics has now entered the era of information construction from manual management. Under the background of increasing digitalization and artificial intelligence, it is the general trend to use mobile robots to replace manual transportation of materials. For example, in the current epidemic situation, countries do not advocate close contact between people, and the method of manually distributing medicines by medical staff will increase the risk of disease transmission. At present, foreign countries have begun to use medical delivery robots in batches, and my country's unmanned delivery of medical supplies is also developing continuously. [0003] Ob...

AI Technical Summary

Problems solved by technology

These algorithms still have a good effect when the obstacle is still, but they often fall into a local optimum when the obstacle is moving, thus slowing down the overall obstacle avoidance time.

The root cause of the above problems is that the above algorithm only considers the current positional relationship between the mobile robot and the obstacle at a certain moment, so the decision made during obstacle avoidance is only the current optimal solution, and there is still room for improvement from a global perspective. room for efficiency

Images