Learning Effective Abstractions for Planning (LEAP)

Overview

Despite significant recent advances, planning remains a fundamentally hard problem, especially when considering robotic applications with long-horizon tasks, sparse feedback, and continuous state and action spaces. Abstraction is one of the main tools we have to overcome such challenges. State abstraction allows agents to focus on the important aspects of a planning problem, and action abstraction allows agents to reason across long horizons and exploit hierarchy in task execution. Designing abstractions by hand is labor-intensive and difficult: even for an expert, it is difficult to anticipate the influence of the abstraction on planning performance. This motivates learning abstractions for efficient and effective robotic planning.

This workshop will bring together researchers from several related but often disjoint subcommunities who share an interest in learning abstractions for robotic planning. Key questions for discussion include:

1. What is the right objective for abstraction learning for robotic planning? To what extent should we consider soundness, completeness, planning efficiency, task distributions?
2. To what extent should the abstractions used for robotic planning be interpretable or explainable to a human? How can this be achieved?
3. When, where, and from what data should abstractions be learned? In the robot factory once and for all? In the “wild” from interaction with humans or the world?
4. How can and should pretrained language models (e.g., GPT-4) and vision-language models (e.g., CLIP) be leveraged towards abstraction learning for robotic planning?
5. To what extent is natural language a useful representation for abstraction learning? What are the virtues of alternative or additional representations?

This workshop comes at a pivotal time as the field works to understand the implications of large pretrained language and vision models for robotic planning. As suggested by the latter discussion questions, these foundation models will be a central workshop theme. We believe there are rich opportunities not only for foundation models to aid robotic planning, but also for robotic planning research to inform the further development of foundation models. For example, the “right objective” for abstraction learning could be used for foundation model training if those models are ultimately meant for robotic planning.

Objectives of LEAP Workshop

Current research on abstraction learning for robotic planning is fragmented across several subcommunities including task and motion planning, reinforcement learning (hierarchical, model-based), planning with linear temporal logic, planning with natural language, and neuro-symbolic AI. This workshop aims to create a common forum to share insights, discuss key questions, and chart a path forward. For this to succeed, we will need to establish a shared understanding of what abstraction means in the context of robot planning. This will require bridge-building between different sub-disciplines, which we will facilitate in two ways: (1) a diverse selection of papers and invited speakers; and (2) a highly interactive workshop.

Areas of Interest

We solicit papers of the following topics:

• Learning state abstractions and action abstractions
• Natural language as an abstraction for learning-based planning
• Learning other knowledge representations for planning
• Learning for planning with linear temporal logic (LTL)
• Learning for task and motion planning (TAMP)
• Learning for hierarchical planning
• Neuro-symbolic approaches for planning
• Hierarchical reinforcement learning
• Model-based reinforcement learning with latent representations
• Large language models (LLMs) and/or Foundation Models for Robot Planning

Submission Guidelines

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 or IEEE conference (ICRA or IROS) styles. 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.

Submissions will be accepted through OpenReview.