Jake Welde: Geometry, Design, and Control for Robotics

Jake Welde is an Assistant Professor in the Sibley School of Mechanical and Aerospace Engineering at Cornell University. Prior to joining MAE at Cornell, he spent a decade at the University of Pennsylvania, where he completed his undergraduate and doctoral degrees Mechanical Engineering and Applied Mechanics and his masters in Robotics. His PhD thesis, “Geometric Methods for Efficient and Explainable Control of Underactuated Robotic Systems”, was supervised by Vijay Kumar in the GRASP Laboratory.

In his research, Jake explores the role of differential geometry and dynamical systems theory in control synthesis and design for robotic systems, exploiting structural properties to explainably synthesize efficient controllers, accelerate learning algorithms, and develop more capable robot morphologies. He envisions a future in which robots move through their surroundings as capably and dynamically as their counterparts in Nature.

In the classroom, Jake enjoys teaching abstract ways of thinking through hands-on experiences. He is also passionate about protecting the natural miracles of our one and only Earth, working towards a world that recognizes the intrinsic dignity and equality of all people, and furthering our collective understanding of Nature for the benefit of all. Outside work, Jake loves spending time outdoors, cooking spicy food, and playing fetch with his dog Sprout.

Curriculum Vitae (Summer 2025)

Recent Updates

July 2025 I am starting as an Assistant Professor in the Sibley School of Mechanical and Aerospace Engineering at Cornell University!
July 2025 I defended my doctoral thesis in Mechanical Engineering and Applied Mechanics, titled "Geometric Methods for Efficient and Explainable Control of Underactuated Robotic Systems", supervised by Vijay Kumar in the GRASP Laboratory. This concludes a decade well-spent at Penn!
June 2025 With Rob Mahony, Stephan Weiss, and Maani Ghaffari, I co-organized the Equivariant Systems workshop at RSS 2025 in Los Angeles, CA, and gave a background lecture on the mathematical foundations of symmetry in robotics (video and slides available).
Dec 2024 Our work exploiting symmetry to learn tracking controllers won a Best Paper Award at the Workshop on Symmetry and Geometry in Neural Representations at NeurIPS 2024!
Oct 2024 Together with colleagues from Penn, Princeton, the University of Twente, and GE Healthcare, we are organizing the workshop "Equivariant Robotics: The Role of Symmetry Across Perception, Estimation, and Control" at IROS 2024. Join us to hear from researchers exploring symmetry across a wide range of problems and applications in robotics!
May 2024 I was accepted into the 2024 cohort of RSS Pioneers, an intensive career workshop that each year "brings together a cohort of the world’s top early-career researchers" in robotics, hosted at the Robotics: Science and Systems conference.
January 2024 I was invited to give a talk at the 2024 Joint Mathematics Meetings in San Francisco in the special session on "Geometry and Symmetry in Differential Equations, Control, and Applications".
December 2023 I will be at CDC 2023 in Singapore, presenting our work on almost global asymptotic stability in cascade systems.
July 2023 I gave a contributed talk about our work on the connections between differential flatness and Noetherian symmetry at the 2023 SIAM Conference on Control and Its Applications here in Philadelphia.
May 2023 I was at ICRA 2023 in London, sharing our work on the identification of equivariant flat outputs for mechanical systems by exploiting symmetry and numerical optimization.