ROAIMar 6, 2025

Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation

arXiv:2503.04931v12 citationsh-index: 4ICRA
Originality Incremental advance
AI Analysis

This addresses the problem of inefficient adaptation to unforeseen changes in robotics, offering a solution that is incremental by building on existing hybrid methods.

The paper tackles the challenge of adapting to dynamic, uncertain open-world environments in robotics by proposing a hybrid planning and learning system that integrates neural network-based models with symbolic planning, resulting in faster convergence and outperforming state-of-the-art hybrid methods in robotic manipulation tasks.

Adapting quickly to dynamic, uncertain environments-often called "open worlds"-remains a major challenge in robotics. Traditional Task and Motion Planning (TAMP) approaches struggle to cope with unforeseen changes, are data-inefficient when adapting, and do not leverage world models during learning. We address this issue with a hybrid planning and learning system that integrates two models: a low level neural network based model that learns stochastic transitions and drives exploration via an Intrinsic Curiosity Module (ICM), and a high level symbolic planning model that captures abstract transitions using operators, enabling the agent to plan in an "imaginary" space and generate reward machines. Our evaluation in a robotic manipulation domain with sequential novelty injections demonstrates that our approach converges faster and outperforms state-of-the-art hybrid methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes