mlsanityData to 7 Oct 2026

Where To Start? Transferring Simple Skills to Complex Environments

arXiv 2212.06111 ↗First posted 12 Dec 2022cs.RO cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Robot learning provides a number of ways to teach robots simple skills, such as grasping. However, these skills are usually trained in open, clutter-free environments, and therefore would likely cause undesirable collisions in more complex, cluttered environments. In this work, we introduce an affordance model based on a graph representation of an environment, which is optimised during deployment to find suitable robot configurations to start a skill from, such that the skill can be executed without any collisions. We demonstrate that our method can generalise a priori acquired skills to previously unseen cluttered and constrained environments, in simulation and in the real world, for both a grasping and a placing task.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 12 Dec 2022.

Builds on

38 of 49 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2021How Attentive are Graph Attention Networks?cited by 818
  8. 2015Gated Graph Sequence Neural Networkscited by 792
  9. 2021Implicit Behavioral Cloningcited by 442
  10. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  11. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  12. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
26 more
  1. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
  2. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  3. 2017Heterogeneous Information Network Embedding for Recommendationcited by 133
  4. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  5. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 115
  6. 2019Self-Supervised Correspondence in Visuomotor Policy Learningcited by 106
  7. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 94
  8. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstrationcited by 92
  9. 2020Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphscited by 83
  10. 2020Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learningcited by 69
  11. 2019KETO: Learning Keypoint Representations for Tool Manipulationcited by 68
  12. 2020Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentationcited by 64
  13. 2019PyRep: Bringing V-REP to Deep Robot Learningcited by 43
  14. 2021kPAM 2.0: Feedback Control for Category-Level Robotic Manipulationcited by 38
  15. 2021Learning Models as Functionals of Signed-Distance Fields for Manipulation Planningcited by 29
  16. 2019Learning Continuous 3D Reconstructions for Geometrically Aware Graspingcited by 28
  17. 2021My House, My Rules: Learning Tidying Preferences with Graph Neural Networkscited by 27
  18. 2021Efficient and Interpretable Robot Manipulation with Graph Neural Networkscited by 21
  19. 2018Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Networkcited by 19
  20. 2022Implicit Kinematic Policies: Unifying Joint and Cartesian Action Spaces in End-to-End Robot Learningcited by 15
  21. 2021Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimationcited by 14
  22. 2021Hierarchical Policies for Cluttered-Scene Grasping with Latent Planscited by 12
  23. 2021Collision-Aware Target-Driven Object Grasping in Constrained Environmentscited by 11
  24. 2019Modeling Grasp Type Improves Learning-Based Grasp Planningcited by 4
  25. 2020Manipulation-Oriented Object Perception in Clutter through Affordance Coordinate Framescited by 4
  26. 2019Representation Learning in Heterogeneous Professional Social Networks with Ambiguous Social Connectionscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 3; 2025: 1.

9 papers.

  1. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  2. 2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 48
  3. 2024Instant Policy: In-Context Imitation Learning via Graph Diffusioncited by 38
  4. 2024Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloningcited by 19
  5. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17
  6. 2023On the Effectiveness of Retrieval, Alignment, and Replay in Manipulationcited by 15
  7. 2023Few-Shot In-Context Imitation Learning via Implicit Graph Alignmentcited by 14
  8. 2023NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptorscited by 8
  9. 2025HybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learningcited by 3