Eyal Weiss

Postdoctoral scholar | AI & Robotics | Planning, Search & Optimization
Robotics Institute, Carnegie Mellon University

What I’m passionate about: AI and robotics, particularly through the lens of planning, search and control.

I am a postdoc at the Robotics Institute at Carnegie Mellon University, affiliated with the Search-based Planning Laboratory (SBPL) led by Prof. Maxim Likhachev and the ARCS Lab led by Prof. Jiaoyang Li . My current research spans Search, AI Planning, Motion Planning for robotics, and Combinatorial Optimization.

Prior to joining CMU I was a postdoc at the Computational Robotics Lab (CRL) led by Prof. Oren Salzman , in the CS Faculty at the Technion .

I had the privilege to conduct my PhD under the supervision of Prof. Gal A. Kaminka , affiliated with the MAVERICK research group, in the CS department at BIU . My research was, and partially still is, devoted to generalizing automated planning with dynamically estimated action models, where we combined tools from AI planning, graph theory and combinatorial optimization, to endow agents with enhanced planning capabilities in challenging (non-classical) setups.

Previously, I earned my BSc and MSc in Electrical Engineering at Tel Aviv University, where I was fortunate to work with Prof. Michael Margaliot , in the EE school at TAU , on problems in the fields of control theory and dynamical systems.

📄 My complete CV

When Your Neighbors Are Wrong, Listening to Them Makes You Worse

A cost-sensitive neighborhood aggregation method for GNNs that routes neighbors by similarity — and what its failures reveal about two fundamentally different kinds of heterophily.

What if warehouse robots planned around the packages, not themselves?

A simple change in perspective — planning paths for items instead of robots — leads to provably optimal warehouse rearrangement and up to 2x faster completion times.

Motion planning time for robots is almost immediate

Have you ever watched a robot try to perform a task in the real world—perhaps a robotic arm trying to grab a specific object out of a cluttered bin, or a humanoid robot trying to navigate a messy room? If you have, you might have noticed a slight hesitation. The robot pauses, computes, moves a little, pauses again, and then commits to the action. That pause isn’t uncertainty; it’s intense calculation. The robot is desperately trying to figure out how to get from Point A to Point B without smashing its elbow into a table or colliding with a human. ...