Learning Effective Abstractions for Planning (LEAP)

Overview

Complex long-horizon and sparse reward robotics tasks are challenging for scaling end-to-end learning methods. By contrast, planning approaches have shown great potential to handle such complex tasks effectively. One of the major criticisms of planning-based approaches has been the lack of availability of accurate world models (aka abstractions) to utilize.

There has been a renewed interest in using learning-based approaches to learn symbolic representations that support planning. However, this research is often fragmented in disjoint sub-communities such as task and motion planning, reinforcement learning (hierarchical, model-based), planning with formal logic, planning with natural language (language models), and neuro-symbolic AI. This workshop aims to create a common forum to share insights, discuss key questions, and chart a path forward via abstraction.

We aim to facilitate this bridge-building in two ways: (1) a diverse selection of papers and invited speakers; and (2) a highly interactive workshop. Concretely, the workshop will highlight approaches that use different learning methods, mainly to learn symbolic and composable representations of world models. Key questions for discussion include:

1. What is the right objective for abstraction learning for robotic planning? To what extent should we consider factors such as soundness, completeness, target planner and planning efficiency, and task distribution?
2. What level of abstraction is needed for it to be effective? How general-purpose or specific do these abstractions have to be for long-term autonomy? Do learned abstractions need to be hierarchical or at a single level?
3. To what extent should the abstractions used for robotic planning be interpretable or explainable to a human? How can this be achieved?
4. How can existing pre-trained foundational models (large language models (LLMs) and vision-language models (VLMs)) be utilized for learning symbolic abstractions while ensuring guarantees about correctness?
5. When, where, and from what data should abstractions be learned? Should they be learned as priors in the robot factory, using expert demonstrations, or in the “wild” from interaction with humans or the world?

Following the success of the previous offering of the workshop at CoRL 2023, we propose a second iteration of the workshop at CoRL 2024. Specifically, the previous iteration of the workshop received a total of 26 submissions highlighting important characteristics and challenges of learning abstractions. They highlighted how pre-trained foundational models, specifically LLMs or VLMs, enable learning various forms of abstractions for a diverse set of robotics tasks. This iteration of the workshop would have a stronger emphasis on learning provably correct symbolic abstractions using different techniques.

Areas of Interest

We solicit papers of the following topics:

• Learning generalizable and composable representations for robot planning
• Learning for task and motion planning (TAMP)
• Learning state abstractions and action abstractions
• Natural language as an abstraction for learning-based planning
• Learning other knowledge representations for planning
• Learning for hierarchical planning
• Learning for LTL-based planning
• Neuro-symbolic approaches for task and motion planning
• Hierarchical reinforcement learning for robotics

Submission Guidelines

Submission Portal: OpenReview Closed!

We solicit workshop paper submissions relevant to the above call of the following types:

• Long papers - up to 8 pages plus unlimited references / appendices
• Short papers - up to 4 pages plus unlimited references / appendices

Please format submissions in CoRL, ICLR or IEEE conference (ICRA or IROS) styles. Submissions do not need to be anonymized. To authors submitting papers rejected from other conferences: please ensure that comments given by the reviewers are addressed prior to submission.

Note: Please feel free to submit work under review or accepted for presentation at other workshops and/or conferences as we will not require copyright transfer.

Important Dates

Schedule

Invited Speakers

Georgia Chalvatzaki

TU Darmstadt
Germany

Caelan Garrett

Nvidia

Leslie Pack Kaelbling

Massachusetts Institute of Technology
USA

Eric Rosen

The AI Institute
Boston Dynamics

Siddharth Srivastava

Arizona State University
USA

Gregory Stein

George Mason University
USA

Marc Toussaint

TU Berlin
Germany

Organizing Committees

Naman Shah

Brown University
USA

David Paulius

Brown University
USA

Nishanth Kumar

Massachusetts Institute of Technology
USA

Jiayuan Mao

Massachusetts Institute of Technology
USA

Yiqing Xu

Natitonal University of Singapore
Singapore

Nakul Gopalan

Arizona State University
USA

Rudolph Lioutikov

Karlsruhe Institute of Technology
Germany

George Konidaris

Brown University
USA

Program Committee