Robotic assembly is ubiquitous in various industries such as automotive, construction, aerospace, electronics, and medical devices, as well as in daily life for assembling furniture, toys, home appliances, and more. However, robotic assembly is also the most challenging task for robot learning due to the combined challenges of accurate perception, multi-modal sensing, affordance reasoning, long-horizon task and motion planning, grasping, contact-rich and dexterous manipulation, physical simulation, sim2real transfer, and generalization over arbitrary objects with complex shapes. Our workshop aims to bring together researchers from these diverse domains and beyond to explore the application of robot learning to address these challenges. The key questions and topics in our workshop include:

• Assembly planning: Applications of robot learning for planning and optimizing assembly sequences and motion to ensure safety, feasibility, and efficiency.
• Assembly skill learning: Learning robust skills such as grasping, in-hand manipulation, insertion, screwing, and tool usage to solve contact-rich and high-accuracy assembly tasks while emphasizing training efficiency, generalization, and performance.
• Foundation models for assembly: Applications of foundation models for generalizable and robust perception, planning, and control for assembly tasks.
• Multi-modal sensing: Challenges and solutions to integrating vision, force/torque, and tactile sensing to improve the precision and reliability of robot assembly.
• Dataset and benchmark for assembly: New datasets or benchmarks related to assembly tasks featuring big quantities, task and object diversity, real-world complexity, multiple modalities and robot embodiments.
• Human-robot interaction: Learning assembly plans and skills from human demonstrations or language instructions, or collaborating with humans in a safe and efficient way.
• Learning industry-level assembly: Discussing the gap of employing robot learning to solve real-factory assembly problems with scale.

Submission guideline:

We invite submissions of short papers from all members of academia and industry focusing on the above topics. Please submit your paper via our OpenReview portal. We encourage papers to follow the official CoRL LaTeX template. Papers must be 2-8 pages in length, excluding references and appendices, and please include the references and appendix in the same PDF as the main paper. Submissions may have a supplementary video if desired.

We allow submissions of papers that are under review or have been recently published in other venues. We also welcome authors to submit even if they are not able to present their work at the workshop as we will put all accepted papers on our website, though a physical poster board at the conference cannot be guaranteed.

Review process:

The papers will be reviewed by our program committee, consisting of members of the research community. The review process will be double-blind. Please do not include your names on your submissions until after the review process is complete. Authors of accepted papers will be asked to submit a camera-ready version and make a corresponding poster.

Submission timeline:

• Sept 8, 2024: Submission portal open
• Oct 11, 2024: Submission deadline (extended!)
• Oct 18, 2024: Notification of acceptance
• Oct 25, 2024: Camera-ready deadline
• Nov 9, 2024: Workshop date