Learning-based Robot Co-design: Generative and Iterative Approaches

IROS 2026, Pittsburgh, Pennsylvania, USA

Thursday, October 1, 2026, 8:00 AM -- 12:30 PM

ABSTRACT

Recent advances in foundation models, large language models, and generative models are beginning to reshape how researchers approach robot co-design. At the same time, robot co-design has long relied on iterative paradigms such as reinforcement learning, optimization, and evolutionary search. While both directions have shown promise, their relative strengths, limitations, and opportunities for integration remain unclear. This workshop focuses on learning-based robot co-design, with particular emphasis on two complementary paradigms: generative approaches that propose novel robot embodiments and morphologies, and iterative approaches that improve designs through reinforcement learning, optimization, or evolutionary search. By bringing these perspectives together, the workshop aims to foster discussion on how recent advances in generative AI are changing the co-design landscape, when different paradigms are most effective, and whether hybrid approaches can unlock new capabilities. The workshop will bring together researchers working on robot co-design, generative design, reinforcement learning, and optimization-based design, providing a platform to present recent advances and discuss future directions for learning-based robot co-design.

Topics of Interest Include:

• Generative design for novel robot morphologies (e.g., using LLMs or diffusion models)

• RL- and optimization-based co-design of structure

• Sim-to-real transfer and real-world experimentation

• Hardware constraints, physical fabrication, and feedback-driven refinement

Invited Speakers

Rika Antonova

University of Cambridge

Boyuan Chen

Duke University

Kento Kawaharazuka

The University of Tokyo

Sam Kriegman

Northwestern University

Nathan Lepora

University of Bristol

Gioele Zardini

Massachusetts Institute of Technology

Tentative Schedule

08:30–08:40 Welcome
08:40–10:00 Invited Talks
10:00–10:15 Flash Talks for Posters
10:15–11:15 Break and Poster Session
11:15–11:35 Young Researcher Talks
11:35–12:15 Invited Talks
12:15–12:30 Panel: Zero Shot vs. Iterative Design

Young Researcher Talks

Kevin Qiu · University of Warsaw
Yanyuan Qiao · EPFL
Aadditional speaker · TBC

Call For Contributions

Extended Abstract

We welcome extended abstracts on learning-based robot co-design, including generative robot design, morphology–control co-design, learning-based design optimization, fabrication, sim-to-real transfer, and real-world evaluation.

We welcome original research, work in progress, concurrently submitted work, and recently published work. The workshop is non-archival: accepted submissions will not appear in the IEEE IROS proceedings, and authors retain the right to submit their work elsewhere.

Accepted submissions will be presented in a poster session during the workshop.

Format: 2-page extended abstract in IEEE conference format, excluding references.

Submission link: ⁠OpenReview

Important Dates

Submission opens: August 5, 2026
Submission deadline: September 4, 6:00 am CEST
Notification of acceptance: Rolling (no later than mid-September 2026)
Workshop: October 1, 2026