Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning

TL;DR

Arcadia presents a comprehensive, lifecycle-based framework for embodied lifelong learning that integrates exploration, scene generation, shared representations, and simulation-based evaluation to enable continuous improvement and generalization in physical robots.

Contribution

The paper introduces Arcadia, a novel closed-loop framework that tightly couples four stages of embodied learning, enabling scalable, continuous, and generalizable lifelong learning in embodied agents.

Findings

Achieves consistent gains on navigation and manipulation benchmarks.

Transfers robustly to physical robots, demonstrating real-world applicability.

Supports lifelong improvement through integrated data acquisition, simulation, and shared representations.

Abstract

We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, learning, or deployment) rarely sustain improvement or generalize beyond narrow settings. We introduce Arcadia, a closed-loop framework that operationalizes embodied lifelong learning by tightly coupling four stages: (1) Self-evolving exploration and grounding for autonomous data acquisition in physical environments, (2) Generative scene reconstruction and augmentation for realistic and extensible scene creation, (3) a Shared embodied representation architecture that unifies navigation and manipulation within a single multimodal backbone, and (4) Sim-from-real evaluation and evolution that closes the feedback loop through simulation-based adaptation. This coupling is non-decomposable: removing any stage breaks the improvement loop and reverts to one-shot training. Arcadia delivers consistent gains on navigation and manipulation benchmarks and transfers robustly to physical robots, indicating that a tightly coupled lifecycle: continuous real-world data acquisition, generative simulation update, and shared-representation learning, supports lifelong improvement and end-to-end generalization. We release standardized interfaces enabling reproducible evaluation and cross-model comparison in reusable environments, positioning Arcadia as a scalable foundation for general-purpose embodied agents.