Path planning model of mobile robots in the context of crowds

TL;DR

This paper presents a novel robot path planning model that integrates RNN-based visual quality evaluation and image preprocessing to enhance navigation robustness in crowded environments.

Contribution

The paper introduces a new path planning model combining RNN-driven image quality assessment with crowd-aware navigation, improving robustness over existing models.

Findings

The model effectively filters background noise in complex crowd images.

Simulation results demonstrate improved robustness compared to state-of-the-art models.

The approach enhances robot navigation accuracy in crowded scenarios.

Abstract

Robot path planning model based on RNN and visual quality evaluation in the context of crowds is analyzed in this paper. Mobile robot path planning is the key to robot navigation and an important field in robot research. Let the motion space of the robot be a two-dimensional plane, and the motion of the robot is regarded as a kind of motion under the virtual artificial potential field force when the artificial potential field method is used for the path planning. Compared to simple image acquisition, image acquisition in a complex crowd environment requires image pre-processing first. We mainly use OpenCV calibration tools to pre-process the acquired images. In themethodology design, the RNN-based visual quality evaluation to filter background noise is conducted. After calibration, Gaussian noise and some other redundant information affecting the subsequent operations still exist in the image. Based on RNN, a new image quality evaluation algorithm is developed, and denoising is performed on this basis. Furthermore, the novel path planning model is designed and simulated. The expeirment compared with the state-of-the-art models have shown the robustness of the model.