Pith. sign in

REVIEW 17 cited by

Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.03949 v3 pith:PMC47M46 submitted 2024-03-06 cs.RO cs.AIcs.LG

classification cs.ROcs.AIcs.LG
keywords real-worldrialtodatahumanlearningrobustcollectionenvironments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Imitation learning methods need significant human supervision to learn policies robust to changes in object poses, physical disturbances, and visual distractors. Reinforcement learning, on the other hand, can explore the environment autonomously to learn robust behaviors but may require impractical amounts of unsafe real-world data collection. To learn performant, robust policies without the burden of unsafe real-world data collection or extensive human supervision, we propose RialTo, a system for robustifying real-world imitation learning policies via reinforcement learning in "digital twin" simulation environments constructed on the fly from small amounts of real-world data. To enable this real-to-sim-to-real pipeline, RialTo proposes an easy-to-use interface for quickly scanning and constructing digital twins of real-world environments. We also introduce a novel "inverse distillation" procedure for bringing real-world demonstrations into simulated environments for efficient fine-tuning, with minimal human intervention and engineering required. We evaluate RialTo across a variety of robotic manipulation problems in the real world, such as robustly stacking dishes on a rack, placing books on a shelf, and six other tasks. RialTo increases (over 67%) in policy robustness without requiring extensive human data collection. Project website and videos at https://real-to-sim-to-real.github.io/RialTo/

Discussion (0). Sign in to comment.

Forward citations

Cited by 17 Pith papers

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

  1. GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models

    cs.AI 2026-08 conditional novelty 7.0 of 10

    A new real-world-grounded benchmark shows that physics engines and video world models each fail differently, with video models often fitting the shape of a physical law while recovering wrong parameters.

  2. Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference

    cs.RO 2025-09 conditional novelty 7.0 of 10

    Fail2Progress generates failure-targeted simulation data via Stein variational inference and fine-tunes skill effect models, improving long-horizon manipulation success rates and generalizing to unseen object counts a...

  3. Prompting with the Future: Open-World Model Predictive Control with Interactive Digital Twins

    cs.RO 2025-06 conditional novelty 7.0 of 10

    A VLM-driven model predictive controller that evaluates simulated future outcomes rendered from a physics-based digital twin.

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

    cs.RO 2026-06 unverdicted novelty 6.0 of 10

    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...

  5. Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation

    cs.RO 2026-06 unverdicted novelty 6.0 of 10

    PACT uses demo-trained progress localization plus intervention preference pairs to correct inflated Bellman targets and align the actor, raising average real-robot success by 24.5% over HIL-SERL.

  6. Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

    cs.RO 2026-02 conditional novelty 6.0 of 10

    Adding a real-world supervised loss to simulation reinforcement learning improves real-robot success and data efficiency for VLA co-training.

  7. TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A training-free pipeline generates instance-level, physically interactive 3D tabletop scenes from text or one image, with a differentiable rotation optimizer and top-view spatial alignment for collision-free layouts.

  8. Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)

    cs.RO 2025-09 conditional novelty 6.0 of 10

    A robot policy trained on one real demonstration plus AI-generated 3D views succeeds from novel initial poses, including opposite-side starts, across six real manipulation tasks.

  9. ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

    cs.RO 2025-06 conditional novelty 6.0 of 10

    ControlVLA adapts a DROID-pretrained diffusion VLA policy to new manipulation tasks with 10 to 20 demos by injecting object-centric features through zero-initialized cross-attention layers, achieving 76.7% success acr...

  10. AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making

    cs.RO 2025-06 conditional novelty 6.0 of 10

    AntiGrounding lifts candidate robot trajectories into the VLM's visual space via multi-view rendering and structured VQA, and reports 57.5% average success across eight manipulation tasks, beating three intermediate-r...

  11. Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A rectified flow model conditioned on 3D hand trajectories and rendered scene video generates realistic hand-scene interaction sounds, with a human study finding near-chance discrimination (47% misclassified).

  12. Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller

    cs.RO 2026-07 conditional novelty 5.0 of 10

    A multi-agent SAC controller using a shared voxel-map BEV representation achieves 90.3% simulated corridor success and 100% success across 50 real two-drone indoor trials after A*-based imitation fine-tuning.

  13. Active Real-World Factor-Based Evaluation for Generalist Robot Policies

    cs.LG 2026-07 conditional novelty 5.0 of 10

    An active evaluation framework selects the most informative task configurations for real-robot tests, matching random testing's accuracy in 20-40% fewer trials.

  14. ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction

    cs.RO 2026-01 conditional novelty 5.0 of 10

    Coupling Gaussian-surfel reconstruction with back-face-aware uncertainty and next-best-path lookahead yields object scans that are more complete and photorealistic while reducing path length about 4–5× versus greedy planners.

  15. SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training

    cs.RO 2025-07 conditional novelty 5.0 of 10

    Simulation-pretrained policies, with digital-twin demos for critic bootstrapping and action proposals, cut real-world RL training time while reaching near-perfect success on three manipulation tasks.

  16. Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning

    cs.RO 2025-05 conditional novelty 5.0 of 10

    SMS combines 3D Gaussian Splatting, SAM 2 segmentation, GPT-4o material inference, and rigid-body simulation to plan physically dynamic robot actions in billiards and quadrotor landing tasks.

  17. RoomCraft: Controllable and Complete 3D Indoor Scene Generation

    cs.CV 2025-06 conditional novelty 4.0 of 10

    RoomCraft generates 3D indoor scenes from text, sketches, or images by extracting structured furniture relations with a VLM and resolving placement conflicts with a weighted positioning heuristic.

Pith tools