智慧型輪椅機器人基於Q-學習之人員跟隨模糊控制器與舒適度新標準

Abstract

由於輪椅使用者通常有行動較不方便的問題，因此輪椅的操作往往需要仰賴照護者，長久以來，容易對照護者造成身體上或健康上的負擔。為了改善這個問題，我們期望輪椅機器人能具有自動人員跟隨的功能，機器人載著輪椅使用者的同時可以穩定地跟隨前方或側方的照護者。本論文提出一個Q-學習模糊控制器來實現這個目標，依據照護者與輪椅機器人之間的距離與角度來自動學習及更新我們所設計的增強式訊號，藉著自我學習的方式讓輪椅機器人達到穩定跟隨照護者直走或轉彎的目的。 除了功能與安全之外，考量乘坐者的舒適度對於輪椅機器人的使用者來說也是非常地重要。因為輪椅的乘坐者大多是老人或行動不便者，機器人跟隨前方的照護者時，也必須避免讓乘坐者感到不舒適。但是，目前並沒有一個客觀的標準來描述輪椅機器人上乘坐者的舒適性。ISO 2631-1透過三軸加速度之總振動值來評估舒適度，總振動值的計算方式為頻率加權之均方根加速度。 本實驗選擇了室內與室外共四種路面來進行人員跟隨，伴隨者行走的路線是直線之後再轉彎，而這四種路面在Z軸上有不同的振動程度。在人員跟隨時，乘坐者同時填寫起步、行進、轉彎、煞車之舒適度感受。然而，乘坐者的問卷結果與ISO 2631-1 所定義的舒適度閥值有所偏差。所以，本論文提出了一個適用於輪椅機器人的舒適度新標準，相較於乘坐者的問卷結果與原本 ISO 2631-1所定義的標準只有42.48%的準確率，而本論文根據粒子群最佳化演算法(PSO)提出一個與問卷結果有90.67 %準確率的新標準。就我們所知，本論文是第一篇提出基於輪椅機器人乘坐者的舒適度標準。

The wheelchair users often struggle to drive safely and accompanied by caregivers. Wheelchair robots can employ the autonomous functions to avoid obstacles and reduce the workload of the caregivers. To achieve the goal, the accompanist needs to be steadily recognized and tracked by the robots. A Q-learning based fuzzy controller (QLFC) is proposed to follow the accompanist. By judging the distance and orientation between the wheelchair robot and the human, Q values are updated by the designed reinforcement signals. The wheelchair robots can steadily follow the accompanist by self-learning controller. Meanwhile, it is important to make the people on wheelchair robots feel comfortable. Based on ISO 2631-1, the ride qualities are obtained by averaging the acceleration data in the frequency bands, and the critical thresholds utilizing to assess the ride comfort are also determined inside. To make the level of bumpiness be as multiple as possible, four kinds of pavements are chosen in the experiments. The results show that the feelings of the passengers on the wheelchair robot are quite different from the ride comfort defined in ISO 2631-1, so a new standard is proposed to assess the ride comfort in this study. The accuracy of the proposed standard is 90.67% which is higher than that of ISO 2631-1, 42.48%. Furthermore, to our best knowledge, this thesis is thought to be the first one to present the comfort criterion and assessment for wheelchair robots.