Path Planning of a Multifunctional Elderly Intelligent Wheelchair Based on the Sensor and Fuzzy Bayesian Network Algorithm

Abstract

An intelligent wheelchair is a kind of service robot. The most critical part of its research field is the safe navigation control of a wheelchair, and path planning is the core part of the navigation control system. The use of a reasonable obstacle avoidance algorithm can not only ensure the safe navigation of wheelchair but also protect the personal safety of users. This paper analyzes the actual needs of the wheelchair following system according to the application scenarios and determines the way to follow the target. The sensor scheme and the wheelchair mobile platform are selected through the analysis of the following methods and the characteristics of each sensor, and the overall architecture of the wheelchair hardware system is designed. Then, the key components such as processor, laser ranging radar, signal strength positioning module, and ultrasonic sensor in the hardware system are selected, and the corresponding peripheral circuit is designed according to the interface type and working voltage of the sensor. In order to solve the problems of the complex calculation process, one-way reasoning, and poor accuracy of the original fault tree method, this paper designs an expert knowledge inference machine based on the Bayesian network. After completing the definition of component vulnerability, the inference engine can be activated, the construction of the directed acyclic network is completed based on the knowledge model mapping of the fault tree, the conditional probability table definition of the directed edge is completed, and the bidirectional probability inference of the Bayesian network can be started. Diagnostic inference obtains the posterior probability to characterize the system impact degree of the bottom event failure. Based on a comprehensive analysis of the research status and research trend of intelligent wheelchair obstacle avoidance path planning methods, this paper mainly studies the intelligent wheelchair path planning method. The environment modeling and path planning of global path planning for static obstacles and dynamic obstacles are realized, and a simulation platform for wheelchair obstacle avoidance path planning based on MATLAB is designed, and simulation experiments are carried out on this basis. The effectiveness of the studied algorithms and strategies in the dynamic obstacle environment is verified by simulation experiments.

Design of Intelligent Wheelchair for the Disabled Elderly of Mild and Moderate Type

“…The central control navigation wireless communication module is positioned at the front of the left armrest, primarily assisting users with navigation and communication functions. It records the locations where elderly individuals frequently use the wheelchair, plans the most commonly used routes, and thereby enhances travel efficiency [16][17]. The control lever module is located at the front of the right armrest, with a visually intuitive and understandable design that aligns with user cognitive experience and operating habits, helping users better control the wheelchair's direction.…”

Shared eHMI: Bridging Human–Machine Understanding in Autonomous Wheelchair Navigation

“…A lack of clarity regarding the APMV's intentions can lead to hesitation or even feelings of danger among pedestrians [46]. The understanding of driving intentions by pedestrians is by means of trust in human-machine interactions [47]. AVs are capable of reliably detecting pedestrians, but it is challenging for both AVs and pedestrians to predict each other's intentions.…”