mlsanityData to 14 Oct 2026

PinchBot: Long-Horizon Deformable Manipulation with Guided Diffusion Policy

arXiv 2507.17846 ↗First posted 23 Jul 2025cs.ROcited by 1

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Pottery creation is a complicated art form that requires dexterous, precise and delicate actions to slowly morph a block of clay to a meaningful, and often useful 3D goal shape. In this work, we aim to create a robotic system that can create simple pottery goals with only pinch-based actions. This pinch pottery task allows us to explore the challenges of a highly multi-modal and long-horizon deformable manipulation task. To this end, we present PinchBot, a goal-conditioned diffusion policy model that when combined with pre-trained 3D point cloud embeddings, task progress prediction and collision-constrained action projection, is able to successfully create a variety of simple pottery goals. For experimental videos and access to the demonstration dataset, please visit our project website: https://sites.google.com/andrew.cmu.edu/pinchbot/home.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 26 of its 30 references that are in the map. First posted on arXiv 23 Jul 2025.

Builds on

26 of 30 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learning18 Jun
  2. 2025Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulation15 Mar
  3. 2024SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy15 Mar
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 22

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  6. 2023RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Toolscited by 76
  7. 2022RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networkscited by 72
  8. 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learningcited by 45
  9. 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physicscited by 23
  10. 2022Learning Closed-loop Dough Manipulation Using a Differentiable Reset Modulecited by 11
  11. 2024Differentiable Particles for General-Purpose Deformable Object Manipulationcited by 11
  12. 2024DoughNet: A Visual Predictive Model for Topological Manipulation of Deformable Objectscited by 9
10 more
  1. 2023SculptBot: Pre-Trained Models for 3D Deformable Object Manipulationcited by 8
  2. 2024LLM-Craft: Robotic Crafting of Elasto-Plastic Objects with Large Language Modelscited by 7
  3. 2024SSFold: Learning to Fold Arbitrary Crumpled Cloth Using Graph Dynamics from Human Demonstrationcited by 7
  4. 2024General-purpose Clothes Manipulation with Semantic Keypointscited by 5
  5. 2023DexDLO: Learning Goal-Conditioned Dexterous Policy for Dynamic Manipulation of Deformable Linear Objectscited by 4
  6. 2024RoPotter: Toward Robotic Pottery and Deformable Object Manipulation with Structural Priorscited by 2
  7. 2024Planning and Reasoning with 3D Deformable Objects for Hierarchical Text-to-3D Robotic Shapingcited by 2
  8. 2025Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Controlcited by 2
  9. 2022Robotic Dough Shapingcited by 1
  10. 2023Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Toolscited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learningcited by 59

Similar, not cited

Close in wording, no citation either way

  1. 2025DiffDef: A Diffusion Model for Generating Multimodal Goal Shapes From Demonstrations for Deformable Object Manipulation
  2. 2026PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation
  3. 2022ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Clouds
  4. 2025AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation
  5. 2026RoboBrain 2.5: Depth in Sight, Time in Mind
  6. 2023Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum
  7. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
  8. 2024D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation