mlsanityData to 7 Oct 2026

Meta-Learning Regrasping Strategies for Physical-Agnostic Objects

arXiv 2205.11110 ↗First posted 23 May 2022cs.RO cs.AI cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Grasping inhomogeneous objects in real-world applications remains a challenging task due to the unknown physical properties such as mass distribution and coefficient of friction. In this study, we propose a meta-learning algorithm called ConDex, which incorporates Conditional Neural Processes (CNP) with DexNet-2.0 to autonomously discern the underlying physical properties of objects using depth images. ConDex efficiently acquires physical embeddings from limited trials, enabling precise grasping point estimation. Furthermore, ConDex is capable of updating the predicted grasping quality iteratively from new trials in an online fashion. To the best of our knowledge, we are the first who generate two object datasets focusing on inhomogeneous physical properties with varying mass distributions and friction coefficients. Extensive evaluations in simulation demonstrate ConDex's superior performance over DexNet-2.0 and existing meta-learning-based grasping pipelines. Furthermore, ConDex shows robust generalization to previously unseen real-world objects despite training solely in the simulation. The synthetic and real-world datasets will be published as well.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

33 of 59 references.

References · 33

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  4. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  5. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  6. 2018Conditional Neural Processescited by 421
  7. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  8. 2018Neural Processescited by 307
  9. 2019Attentive Neural Processescited by 280
  10. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  11. 2019Convolutional Conditional Neural Processescited by 139
  12. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 115
21 more
  1. 2013Deep Learning for Detecting Robotic Graspscited by 114
  2. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  3. 2019Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrationscited by 104
  4. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  5. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 94
  6. 2018Jacquard: A Large Scale Dataset for Robotic Grasp Detectioncited by 86
  7. 2020EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulationcited by 61
  8. 2020Improving Generalization in Meta-learning via Task Augmentationcited by 55
  9. 2019The Functional Neural Processcited by 43
  10. 2020Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variablescited by 33
  11. 2018Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methodscited by 32
  12. 2021DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstrationcited by 20
  13. 2020Function Contrastive Learning of Transferable Meta-Representationscited by 19
  14. 2022What Matters For Meta-Learning Vision Regression Tasks?cited by 18
  15. 2021MVGrasp: Real-Time Multi-View 3D Object Grasping in Highly Cluttered Environmentscited by 10
  16. 2022DefGraspSim: Physics-based simulation of grasp outcomes for 3D deformable objectscited by 10
  17. 2021Contrastive Neural Processes for Self-Supervised Learningcited by 9
  18. 2021Robot Learning of 6 DoF Grasping using Model-based Adaptive Primitivescited by 7
  19. 2021Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddingscited by 3
  20. 2022Grasp Transfer for Deformable Objects by Functional Map Correspondencecited by 2
  21. 2022Data-efficient learning of object-centric grasp preferencescited by 1

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 1.

7 papers.

  1. 2022The Neural Process Family: Survey, Applications and Perspectivescited by 23
  2. 2023Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Cluttercited by 22
  3. 2023Memory Efficient Neural Processes via Constant Memory Attention Blockcited by 9
  4. 2023Uncertainty-driven Exploration Strategies for Online Grasp Learningcited by 6
  5. 2022Category-Agnostic 6D Pose Estimation with Conditional Neural Processescited by 4
  6. 2024Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processescited by 3
  7. 2022Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learningcited by 0