自製具手臂四輪移動平台之最佳路徑規劃與抓取

Optimal path planning and grasping of self-made four-wheel mobile platform with an arm

王偉權(Wang Wei-Chuan)

指導教授 ： 呂藝光

國立臺灣師範大學/科技與工程學院/電機工程學系/碩士(2022年)

https://doi.org/10.6345/NTNU202201345

摘要

本文自行設計具手臂的四輪移動平台，其中四輪移動平台的機械手臂擁有兩個自由度，可以垂直伸縮也可以水平伸縮，具有抓取物品功能。四輪移動平台本身可驅動前進、後退、左轉、右轉，因此四輪移動平台可以自由的移動，並且利用最佳路徑規劃到達指定地點。具手臂四輪移動平台，控制的核心是使用32位元的微控制器，將控制訊號傳至馬達驅動器來控制車輪與手臂的馬達。同時利用超音波感測器做為模糊控制的輸入並輸出相對應的目標轉速，使用霍爾感測器取得目前車子移動的狀態以及PIDNN (Proportional-Integral-Derivative Neural Network)控制器給予對應的控制訊號維持當前的速度。
最佳路徑規劃是使用A-star演算法，實驗的場地會在各個轉彎處使用QR Code作為標記點，以利於四輪移動平台知道自己的位置並且執行對應的指令。最後，透過實驗驗證具手臂四輪移動平台能以最佳路徑移動至目標倉庫前執行抓取的任務。

關鍵字

四輪移動平台 ； 機械手臂 ； PIDNN控制 ； 模糊控制 ； 最佳路徑規劃 ； A-star

並列摘要

This paper designs a four-wheeled mobile platform with a robotic arm. The arm of the four-wheeled mobile platform has two degrees of freedom and can be extended vertically or horizontally and has the function of grasping objects. The four-wheeled mobile platform can turn and drive forward, backward, left and right autonomously. Therefore, the four-wheeled mobile platform can move freely and use the best path planning to reach the specified location. For the four-wheeled mobile platform, the core of the control is the use of a 32-bit microcontroller that transmits control signals to the wheel and arm motors via motor drivers. Ultrasonic sensors are used as inputs for fuzzy control, Hall sensors are used to obtain the current motion state, and the PIDNN (Proportional-Integral-Derivative Neural Network) controller signal is used to maintain the desired speed.
We use the A-star algorithm to design the optimal path. The experimental site uses QR codes as marker points at each turn so that the four-wheeled mobile platform can know its position and execute the corresponding commands. Finally, the platform will be validated through experiments. The experimental results show that the four-wheeled mobile platform is able to perform the grasping task with the best path and reach the target location.

並列關鍵字

Four-wheel mobile platform ； robotic arm ； PIDNN control ； fuzzy control ； optimal path planning ； A-star

參考文獻

[1] S. Vechet, J. Krejsa, and K.-S. Chen, "AGVs mission control support in smart factories by decision networks," in 2020 19th International Conference on Mechatronics-Mechatronika (ME), IEEE, pp. 1-4,2020.

[2] Kiva 機器人，from https://technews.tw/2019/01/25/amazon-built-an- electronic-vest-to-improve-worker-robot-interactions/

[3] W. Chun-Fu, W. Xiao-Long, C. Qing-Xie, C. Xiao-Wei, and L. Guo-Dong, "Research on visual navigation algorithm of AGV used in the small agile warehouse," in 2017 Chinese Automation Congress (CAC), IEEE, pp. 217-222, 2017.

[4] K. Kodagoda, W. S. Wijesoma, and E. K. Teoh, "Fuzzy speed and steering control of an AGV," IEEE Transactions on control systems technology, vol. 10, no. 1, pp. 112-120, 2002

[5] B. Sha, L. Zhu, Y. Zhu, and J. Cheng, "Path Planning of Agv Complex Environment Based on Ant Colony Algorithm," in 2022 International Seminar on Computer Science and Engineering Technology (SCSET), IEEE, pp. 72-75, 2022.