revanth senthilkumaran

M.S. Robotics, Carnegie Mellon University
Robot Learning Intern, Bosch Center for AI

I build robot learning systems that reason about physical interaction and transfer manipulation skills across embodiments, tasks, and environments.

research

My goal is to develop general-purpose manipulation policies that combine perception, reasoning, and action—and can reuse knowledge across different robot bodies rather than learning every skill from scratch.

currently

At CMU and the Bosch Center for AI, I study embodied reasoning and cross-embodiment robot learning, co-advised by Dr. Jonathan Francis and Prof. Ding Zhao. I am especially interested in how demonstrations, video, and interaction data can help robots acquire manipulation skills that generalize.

questions I want to explore

How can a robot reason about objects, contacts, and task constraints before it acts?
How can demonstrations and human video provide scalable supervision for manipulation?
What representations let a learned skill transfer across embodiments and environments?

Background: Before CMU, I earned a B.S. in Computer Engineering from Purdue and completed internships at AeroVironment as a Robotics Software Engineer and at Prof. Karthik Desingh's Robotics Perception and Manipulation Lab (RPM Lab) at the University of Minnesota. I also conducted research at Purdue's SMART Lab with Prof. Byung-Cheol Min, IDEAS Lab with Prof. Aniket Bera, and the Air Force Research Laboratory with Prof. James Goppert. Outside research, I play piano and love playing and watching sports. Every week, I also try finding new food and coffee spots in town!

latest updates

Nov 2026 REMM Presented and won the BEST POSTER award at CoRL Learn@Deploy Workshop 2026
Jun 2026 Humanoid Touch Dream accepted to IEEE-IROS 2026
Aug 2025 Started M.S. in Robotics at Carnegie Mellon University
Jun 2024 MOCAS dataset accepted to IEEE-TAFFC 2024
Apr 2024 Presented ARTEMIS at Purdue Spring Undergraduate Research Expo and won 2nd place in College of Science Category
Jun 2023 UPPLIED accepted to IEEE-IROS 2023

selected research

EgoX cross-embodiment manipulation framework

EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming

Authors: Yaru Niu*, Binghong Chen*, Changwei Yao*, Shangtao Li*, Zhenlong Fang, Revanth Krishna Senthilkumaran, Shuai Zhou, Yuemin Mao, Kalie Ching, Po-Ju Chao, Yudong Luo, Peiqi Yu, Heng Zhang, Hao Zhang, Bingqing Chen, Chen Qiu, H. Eric Tseng, Ye Yuan, Umar Iqbal, Changliu Liu, Jonathan Francis, Ding Zhao

* Equal Contribution

Status: Preprint 2026

Abstract Project Page Paper arXiv GitHub Video

REMM: Revisable Embodied Memory for Manipulation

Authors: Revanth Krishna Senthilkumaran, Ruwan Wickramarachchi, Alessandro Oltramari, Jonathan Francis

Status: CoRL Learn@Deploy Workshop 2026 (BEST POSTER)

Abstract Project Page LinkedIn X thread

Humanoid Touch Dream: Learning Versatile Humanoid Manipulation with Touch Dreaming

Authors: Yaru Niu, Zhenlong Fang, Binghong Chen, Shuai Zhou, Revanth K. Senthilkumaran, Hao Zhang, Bingqing Chen, Chen Qiu, H. Eric Tseng, Jonathan Francis, Ding Zhao

Status: IEEE-IROS 2026, RSS WCBM Workshop 2026 (ORAL), RSS SemRob Workshop 2026, RSS Tactile for FM Workshop 2026

Abstract Project Page Paper GitHub Summary