mlsanityData to 7 Oct 2026

Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours

arXiv 1509.06825 ↗First posted 23 Sep 2015cs.LG cs.CV cs.ROcited by 208

Not on the map. Why?

Cited by 31 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Current learning-based robot grasping approaches exploit human-labeled datasets for training the models. However, there are two problems with such a methodology: (a) since each object can be grasped in multiple ways, manually labeling grasp locations is not a trivial task; (b) human labeling is biased by semantics. While there have been attempts to train robots using trial-and-error experiments, the amount of data used in such experiments remains substantially low and hence makes the learner prone to over-fitting. In this paper, we take the leap of increasing the available training data to 40 times more than prior work, leading to a dataset size of 50K data points collected over 700 hours of robot grasping attempts. This allows us to train a Convolutional Neural Network (CNN) for the task of predicting grasp locations without severe overfitting. In our formulation, we recast the regression problem to an 18-way binary classification over image patches. We also present a multi-stage learning approach where a CNN trained in one stage is used to collect hard negatives in subsequent stages. Our experiments clearly show the benefit of using large-scale datasets (and multi-stage training) for the task of grasping. We also compare to several baselines and show state-of-the-art performance on generalization to unseen objects for grasping.

Key facts. Cited by 208 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Sep 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 5; 2021: 51; 2022: 46; 2023: 48; 2024: 29; 2025: 14; 2026: 12.

208 papers.

Sort:

By area:

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  4. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  5. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  6. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  7. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  8. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  9. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  10. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  11. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  12. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
38 more
  1. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  2. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  3. 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 298
  4. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  5. 2022Masked Visual Pre-training for Motor Controlcited by 246
  6. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 241
  7. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 226
  8. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  9. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  10. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  11. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  12. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  13. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 166
  14. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  15. 2023Open-World Object Manipulation using Pre-trained Vision-Language Modelscited by 155
  16. 2023Structured World Models from Human Videoscited by 144
  17. 2021ContactOpt: Optimizing Contact to Improve Graspscited by 137
  18. 2023RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketchescited by 131
  19. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  20. 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 121
  21. 2021Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videoscited by 116
  22. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  23. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 107
  24. 2022Navigating to Objects in the Real Worldcited by 104
  25. 2023HomeRobot: Open-Vocabulary Mobile Manipulationcited by 104
  26. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 101
  27. 2023On Bringing Robots Homecited by 101
  28. 2023Language Embedded Radiance Fields for Zero-Shot Task-Oriented Graspingcited by 91
  29. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 90
  30. 2020COG: Connecting New Skills to Past Experience with Offline Reinforcement Learningcited by 83
  31. 2024AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agentscited by 83
  32. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 70
  33. 2022Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?cited by 70
  34. 2021Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximationcited by 69
  35. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 68
  36. 2023Multi-Stage Cable Routing through Hierarchical Imitation Learningcited by 59
  37. 2023NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesiscited by 56
  38. 2025FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policiescited by 56

50 most cited of 208 All 208 (JSON)