Reproducible Benchmarking of Robotic Grasping and Manipulation:
From Advanced AI to Generalized Humanoid Intelligence

I am pleased to announce the Call for Contributions for the workshop "Reproducible Benchmarking of Robotic Grasping and Manipulation" in conjunction with the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026).

We are looking forward to receiving your submission! For more details, visit the workshop webpage:

Overview

Advances in robotics, perception, and AI are raising expectations for robots to achieve high-level capabilities that enable them to autonomously, accurately, and robustly perform complex manipulation tasks. These include autonomous assembly and disassembly, in-hand manipulation, heterogeneous object picking in cluttered environments, and human-robot collaboration. Despite significant research efforts over the past decades, many of these crucial capabilities remain far from solved.

Most existing solutions are demonstrated through custom pipelines and validation procedures developed within individual laboratories, often relying on different sensing modalities, workflows, and evaluation criteria. As a result, it is difficult to fairly compare approaches or reproduce results across research groups. Benchmarking, therefore, plays a critical role in enabling reproducibility, transparent evaluation, and meaningful comparison of different methods, ultimately accelerating progress in challenging robotic manipulation problems.

Goals

This workshop aims to bring together researchers, practitioners, and stakeholders from academia, industry, and standardization organizations to discuss the current status, challenges, and future directions of reproducible benchmarking in autonomous robotic grasping and manipulation. Particular attention will be given to the growing interaction between research innovation and practical engineering solutions needed to develop efficient, robust, and trustworthy robotic systems that operate reliably in real-world environments outside the laboratory.

Focusing on benchmarking and competitions, we will:

• Engage with experts on the tasks and the winners of recent competitions
• Provide insights into the evolution of grasping and manipulation research
• Draw guidelines and directions for the reproducibility and comparison of future solutions
• Identify new challenges that arise from the discussion, includind humanoids and advanced artificial intelligence systems.

Call for Contributions

Important dates

Note: Submission deadlines are at 11:59 pm Anywhere on Earth.

Extended Abstracts (Unpublished Works)

We invite interested authors to submit Extended Abstracts (2 pages) of ongoing or unpublished works.

Submitted extended abstracts will be peer-reviewed. Accepted abstracts will be posted on the workshop website and can be presented during the poster session. The best extended abstract will have the chance to give a talk during the main event of the workshop.

Extended abstracts should be in the form of a single PDF in IROS format (LaTex or Word) and submitted via the Microsoft CMT platform (Select the Extended Abstract track).

Abstracts (Published Works)

We also invite interested authors of relevant, already peer-reviewed and published works to submit title, abstract, and link to their journal article or conference paper via the Microsoft CMT platform (select Abstract track).

Submitted works will be checked for fitting to the workshop and can be presented during the poster session of the workshop.

Topics of Interest

Topics of interest include but are not limited to:

• Grasping
• Manipulation
• Datasets related to robotic manipulation and grasping
• Learning grasping and manipulation from datasets
• Human-to-robot handovers
• Performance metrics and benchmarks
• Competitions for pick-and-place in logistics, daily living manipulation, manufacturing

Organizers

• Salvatore D'Avella, Scuola Superiore Sant'Anna
• Alessio Xompero, Independent Researcher
• Changjae Oh, Queen Mary University of London
• Andrea Cavallaro, EPFL
• Florian T. Pokorny, KTH
• Omar Aboul-Enein, NIST
• Yu Sun, University of South Florida

Join Us!

If you're working on robotic grasping, manipulation, benchmarking, we encourage you to submit your latest research and join the discussion. Whether you're working on grasping algorithms, manipulation strategies, benchmarking frameworks, competition design, reproducibility, or AI for robotics, we encourage you to submit your latest research and join the discussion at the workshop. We look forward to receiving your submissions and welcoming you to Pittsburgh for an engaging exchange of ideas on the future of robotic grasping, manipulation, reproducible benchmarking, and generalized humanoid intelligence. This is a great opportunity to share your work, connect with leading researchers in the field, and help shape the future of robotic grasping and manipulation research.