Research map / Label-efficient and robust learning / Noisy labels
Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias
Abhinav Gupta, Adithyavairavan Murali, Dhiraj Prakashchand Gandhi, Lerrel Pinto
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train on diverse home grasp data instead of Lab-Baxter data | Robust-Grasp · Real-LCA overall, unseen homes | grasp accuracy (%): 18.33 -> 62.08 | Improved |
| Train on diverse home grasp data instead of Lab-Baxter data | Patch-Grasp · Lab-Baxter held-out | accuracy (%): 76.9 -> 71.5 | No clear effect |
| Train on diverse home grasp data instead of Lab-LCA data | Patch-Grasp · Home-LCA held-out | accuracy (%): 56.5 -> 69.9 | Improved |
| Add latent noise modeling and marginalization (ablation) | Patch-Grasp trained on Home-LCA · Real-Sawyer | grasp accuracy (%): 56.25 -> 77.50 | Improved |
| Add latent noise modeling and marginalization (ablation) | Patch-Grasp trained on Home-LCA · Lab-Baxter held-out | accuracy (%): 71.5 -> 75.2 | Improved |
| Add latent noise modeling and marginalization (ablation) | Patch-Grasp trained on Home-LCA · Home-LCA held-out | accuracy (%): 69.9 -> 73.0 | Improved |
| Train with home data rather than lab data | Robust-Grasp · Lab-LCA held-out | accuracy (%): 71.2 -> 71.1 | No clear effect |
| Omit the initial GPN-only pretraining stage (ablation) | Robust-Grasp · Home-LCA grasp training | grasp prediction performance | Hurt |
Closest papers by meaning
- Data Scaling Laws in Imitation Learning for Robotic Manipulation (ICLR 2025 · similarity 0.88)
- ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks (ICLR 2025 · similarity 0.88)
- What Matters in Learning from Large-Scale Datasets for Robot Manipulation (ICLR 2025 · similarity 0.87)
- Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets (ICLR 2025 · similarity 0.87)
- Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation (ICLR 2025 · similarity 0.87)
- SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
