Bilkent University
Department of Computer Engineering

---

M.S.THESIS PRESENTATION

 

Way-Tu: A Framework for Tool Selection and Manipulation Using Waypoint Representations

 

Ece Kunduracıoğlu
Master Student
(Supervisor: Asst.Prof.Özgür S.Öğüz)
Computer Engineering Department
Bilkent University

Abstract: The ability to manipulate tools is essential for integrating intelligent robots in real-world settings, allowing them to significantly expand the range of tasks they can perform in daily life. Effective tool use requires an understanding of the geometry of the tool and the motion plan necessary to accomplish the task. To address this challenge, we introduce Way-TU, a novel framework that learns to generate waypoint representations (3D oriented keypoints) for motion planning in tool-use tasks. Our approach perceives the full environment, reasons over object geometry, and generates waypoints to guide the motion optimizer toward task completion, simultaneously enabling tool selection by identifying the most suitable tool among candidates. We evaluated our framework on three diverse tasks—minigolf, lifting, and hammering—and demonstrated a competitive manipulation performance compared to baselines, along with effective tool-selection capabilities.

 

DATE: August 29, Friday @ 09:30 Place: EA 409