Event
Future Leaders in Robotics and AI Seminar: Shivani Kamtikar
Friday, May 9, 2025
2:30 p.m.-3:00 p.m.
https://go.umd.edu/FutureLeaders
Yancy Diaz-Mercado
301 405 6506
yancy@umd.edu
Learning-Based Manipulation and Control of Hybrid Robotic Arms
Shivani Kamtikar
PhD Student
University of Illinois Urbana Champaign
Abstract
Robotic manipulation in unstructured and cluttered environments, such as agricultural fields and disaster zones, presents significant challenges due to the diverse and constrained nature of these settings. Obstacles vary widely in shape, size, and configuration, making efficient and reliable task execution difficult for traditional robotic systems. Hybrid and soft continuum manipulators have emerged as promising solutions for these environments due to their superior dexterity, adaptability, and safe interaction capabilities. Their flexible and deformable structures allow them to navigate through cluttered spaces more effectively than their rigid counterparts. However, planning and controlling these manipulators remains complex due to their high degrees of freedom, limited sensing capabilities, and the intricate coordination required between rigid and flexible segments.
While learning-based control techniques have been widely applied to rigid robotic arms, their potential for hybrid and soft manipulators remains underexplored due to the complex internal dynamics and unpredictable behaviors of these systems. Learning-based approaches, particularly model-free methods, offer a promising path forward by bypassing the need for precise system modeling. Recent work has demonstrated the potential of such techniques in enhancing manipulation capabilities for hybrid arms in challenging, real-world environments.
In this presentation, I will discuss my research on learning-based manipulation and control strategies for hybrid continuum arms in unstructured environments. I will present the challenges associated with planning and control for these systems, along with the techniques we’ve developed to overcome these obstacles. The talk will highlight the potential applications of this work in domains such as precision agriculture, human-assistive devices, and disaster response robotics.
Biography
Shivani Kamtikar is a Ph.D. candidate in Computer Science at the University of Illinois at Urbana-Champaign (UIUC), advised by Prof. Girish Chowdhary. She is currently an Applied Scientist Co-op at Amazon Robotics, working on dexterous manipulation with Dr. Taskin Padir. She received her master’s degree in Computer Science from the University of Illinois at Urbana-Champaign and her Bachelor’s from Pune University, India. She was a research intern at the University of Notre Dame, where she was advised by Prof. Zhiyong Zhang. Her research lies at the intersection of robotics and computer vision, focusing on developing learning-based methods for the manipulation and control of hybrid and soft robots in cluttered environments.
About the Seminar Series
The Maryland Robotics Center's Future Leaders in Robotics and AI Seminar Series at the University of Maryland is a nationwide online seminar series for PhD students, postdoctoral researchers, and early-career professionals. The seminar series highlights the latest research and innovation in the field of robotics and AI. The series is intended to provide exposure and mentorship opportunities to the speakers, build a network of innovators across the country, and support the speakers’ career planning.
The seminars are held on select dates during spring. There are two speakers per seminar. Each speaker gives a 20-minute research presentation followed by a Q&A segment. Immediately after the second seminar, the speakers participate in a discussion with faculty. For more information, please visit: https://robotics.umd.edu/FutureLeaders
