Skripsi
SISTEM KENDALI LENGAN SERVICE ROBOT BERBASIS METODE HYBRID TYPE 2 FUZZY LOGIC DAN FINITE STATE MACHINE
Service robots are designed to assist humans in performing various activities, and one of their key components is the robotic arm, which enables direct interaction with humans. To operate effectively, the arm requires a control system capable of handling dynamic tasks with high accuracy. However, existing control systems still exhibit low accuracy in real-time applications. This study proposes a hybrid control system for a five-degree-of-freedom (DoF) service robot arm by combining a finite state machine (FSM) and type-2 fuzzy logic. Object detection is performed in real time using a deep learning–based camera, with three main input parameters for the fuzzy system: the X coordinate, the Y coordinate of the object’s bounding box, and the estimated distance. The FSM manages the logical flow of arm movements through structured states, while type-2 fuzzy logic addresses uncertainties in flexible motion control. Simulation results in MATLAB Simulink show that the hybrid FSM–type-2 fuzzy method with seven membership functions achieves superior performance, with a rise time of 0.0773 seconds, an overshoot of 3.43%, and a steady-state error of 1.23%. Real-time tests demonstrate successful manipulation of objects such as bottles, cups, air conditioner remotes, markers, and whiteboard erasers with an 80–100% success rate and an average execution time of 18–25 seconds. Furthermore, the system successfully performs real-time handshaking interactions with humans. These findings indicate that the proposed hybrid method is both effective and adaptive for controlling service robot arms in dynamic and interactive environments.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2507005342 | T182148 | T1821482025 | Central Library (References) | Available but not for loan - Not for Loan |
No other version available