Pith

open record

sign in

arxiv: 2410.07408 · v3 · pith:BEHWCIL3 · submitted 2024-10-09 · cs.RO

Automated Creation of Digital Cousins for Robust Policy Learning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:BEHWCIL3record.jsonopen to challenge →

classification cs.RO
keywords digitaltrainingcousinspoliciesautomatedscenescenesvirtual
0
0 comments X
read the original abstract

Training robot policies in the real world can be unsafe, costly, and difficult to scale. Simulation serves as an inexpensive and potentially limitless source of training data, but suffers from the semantics and physics disparity between simulated and real-world environments. These discrepancies can be minimized by training in digital twins, which serve as virtual replicas of a real scene but are expensive to generate and cannot produce cross-domain generalization. To address these limitations, we propose the concept of digital cousins, a virtual asset or scene that, unlike a digital twin, does not explicitly model a real-world counterpart but still exhibits similar geometric and semantic affordances. As a result, digital cousins simultaneously reduce the cost of generating an analogous virtual environment while also facilitating better robustness during sim-to-real domain transfer by providing a distribution of similar training scenes. Leveraging digital cousins, we introduce a novel method for their automated creation, and propose a fully automated real-to-sim-to-real pipeline for generating fully interactive scenes and training robot policies that can be deployed zero-shot in the original scene. We find that digital cousin scenes that preserve geometric and semantic affordances can be produced automatically, and can be used to train policies that outperform policies trained on digital twins, achieving 90% vs. 25% success rates under zero-shot sim-to-real transfer. Additional details are available at https://digital-cousins.github.io/.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image

    cs.CV 2026-06 unverdicted novelty 7.0

    UnfoldArt uses a two-round structured debate between high-level semantic agents and low-level parameter agents, grounded in generated video, to infer articulation and reconstruct full articulated 3D objects including ...

  2. UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image

    cs.CV 2026-06 unverdicted novelty 7.0

    UnfoldArt uses multi-agent debate grounded in vision-language and video models to infer articulation parameters and reconstruct full 3D objects including occluded parts from text or image inputs.

  3. GRAFT: Graph-Based Affordance Transfer via Part Correspondence

    cs.RO 2026-06 unverdicted novelty 7.0

    GRAFT transfers manipulation contact points to unseen objects via part-graph retrieval and correspondence from a single demonstration.

  4. ART: Articulated Reconstruction Transformer

    cs.CV 2025-12 unverdicted novelty 7.0

    ART is a category-agnostic transformer that maps sparse multi-state RGB images to per-part 3D geometry, texture, and articulation parameters via learnable part slots.

  5. SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

    cs.CV 2026-07 conditional novelty 6.0

    SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.

  6. SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation

    cs.RO 2026-06 unverdicted novelty 6.0

    SimFoundry automates zero-shot real-to-sim scene generation from video, producing digital twins and cousins that enable policy training with 0.911 mean Pearson correlation to real-world results and 17-40% success gain...

  7. $\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction

    cs.CV 2026-06 unverdicted novelty 6.0

    φ-Scene performs image-to-3D scene reconstruction via topology-driven physical assembly that resolves penetrations with SDF optimization and settles objects with rigid-body simulation.

  8. GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images

    cs.CV 2026-06 unverdicted novelty 6.0

    GARDEN uses gravity alignment and conditional 3D point classification to factorize RGB reconstructions into explicit rigid bodies plus decoupled background for direct physics simulation.

  9. IGen: Scalable Data Generation for Robot Learning from Open-World Images

    cs.RO 2025-12 unverdicted novelty 6.0

    IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.

  10. ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation

    cs.RO 2026-04 unverdicted novelty 5.0

    Compositional Simulation generates scalable real-world robot training data by combining classical simulation with neural simulation in a closed-loop real-sim-real augmentation pipeline.

  11. CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment

    cs.RO 2026-04 unverdicted novelty 5.0

    CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer ...

  12. RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing

    cs.CV 2025-12 unverdicted novelty 5.0

    RoomPilot introduces a multimodal framework that maps text and floor plans to an Indoor Domain-Specific Language and uses a hierarchical pipeline for controllable indoor scene synthesis.

  13. AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery

    cs.AI 2026-05 unverdicted novelty 4.0

    A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.