Thesis Defense: Ravi Tejwani

Thesis Defense: Robot Guidance Control
Speaker: Ravi Tejwani
Abstract: When human instructors guide learners through motor tasks, they naturally coordinate physical touch with verbal explanations – yet robots applying physical forces without verbal context can feel invasive or unsettling. This thesis presents a robot guidance control method that coordinates physical and verbal guidance as human instructors do. The robot adaptively balances these modalities based on real-time estimation of human compliance: when learners struggle, it provides firmer physical corrections with explicit instructions; as they improve, it transitions to lighter touch with encouraging phrases. This thesis proposes three key components: (1) a compliance estimator that infers physical and verbal responsiveness from tracking errors, (2) an optimization method that dynamically allocates guidance between force and language, and (3) a force-to-language model that generates contextually appropriate utterances. Through user studies, this thesis demonstrates how adaptive coordination of different forms of guidance enhances human-robot collaborative learning. While validated in rehabilitation therapy contexts, this approach generalizes to broader human-robot collaborative learning scenarios, offering insights into how robots can provide more natural and effective guidance that adapts to individual learner needs.

Date: Tuesday, June 17, 2025
Time: 2:00 PM
Room: 3-333
Advisor: Prof. Harry Asada
Committee: Gerald Jay Sussman and Tomas Lozano-Perez 

Details

• Date: Tuesday, June 17
• Time: 2:00 pm - 4:00 pm
• Category: Thesis Defense
• Location: 3-333