October 1st - 08:30 to 12:30
Robotic assembly has traditionally focused on well-specified industrial settings with fixed parts, structured environment and predefined goals. However, emerging applications in creative designs, household robotics, and human-robot collaboration highlight the need and interest in customized solutions for assembly tasks.
In these scenarios, the problem is often underspecified or ambiguous: the target assembly may be provided only as a 2D sketch, silhouettes, semantic descriptions or high-level concepts. Additionally, the available components may consist of generic primitive shapes or irregular non-exact corresponding parts. Solving such problems requires reasoning beyond classical task planning: the system must be able to abstract solutions, by inferring missing constraints, consistent geometry and physically stable assemblies under uncertainty. Furthermore, in assembly, the contact-rich nature of the task poses yet another challenge in motion planning and execution.
This workshop aims to address those challenges, by bringing together researchers working on assembly under uncertainty, with a focus on:
Assembly design in under specified targets;
Geometric and physical reasoning from incomplete information;
Integration of Large Language Models (LLMs) as general reasoning agents for assembly planning under uncertainty;
Addressing these challenges could unlock new strategies that extend robotic assembly beyond well-defined manufacturing domains, enabling robots to reason about and perform open-ended assembly tasks in uncertain and creative settings.
Alexander von Humboldt Professor of Robotics and Artificial Intelligence
Technical University of Munich
We invite IROS2026 attendees to submit extended abstracts related to the following topics:
Object Assembly from Abstract Input: including images, sketches, texts, partial 3Ds, speech, etc.
LLM / VLM / VLA for Task Planning
Abstraction of objects for Task Planning
Primitive shape decomposition
Object Part Segmentation
The submissions will be light peer-reviewed by the organizers, and may be composed of in-progress research, late-breaking results or recently published / presented work. The authors of the accepted submissions will be invited to present a quick introduction to their work in the Poster Spotlight section and participate in the poster session during the coffee break. The accepted submissions will be non-archived and will the posters will be available at the website at the discretion of the authors.
Language: English
Template: Please follow the IEEE Conference format available at the template selector website (IEEE-Template Selector)
Page limit: Two A4 pages (excluding references)
Supplemental material such as videos, are also accepted.
Poster size: Not larger than A0 paper size (width: 841mm x height: 1189 mm)
Accepted posters will be made publicly available on the workshop website at the discretion of the authors
Submission Opens: July 27th (Anywhere on Earth)
Submission Closes: August 31st (Anywhere on Earth)
Notification of Acceptance: September 11th (Anywhere on Earth)
Workshop Date: October 1st (Eastern Time UTC-4)
https://openreview.net/group?id=IEEE.org/IROS/2026/Workshop/Creativity_in_Assembly
Vitor Hideyo Isume
Specially Appointed Researcher
The University of Osaka
Ruixuan Liu
PhD Student
Carnegie Mellon University
Takuya Kiyokawa
Assistant Professor
The University of Osaka
Natsuki Yamanobe
National Institute of Advanced Industrial Science and Technology (AIST)
Changliu Liu
Associate Professor
Carnegie Mellon University