Stable Object Reorientation using Contact Plane Registration
Not on the map. Why?
Abstract (arXiv)
We present a system for accurately predicting stable orientations for diverse rigid objects. We propose to overcome the critical issue of modelling multimodality in the space of rotations by using a conditional generative model to accurately classify contact surfaces. Our system is capable of operating from noisy and partially-observed pointcloud observations captured by real world depth cameras. Our method substantially outperforms the current state-of-the-art systems on a simulated stacking task requiring highly accurate rotations, and demonstrates strong sim2real zero-shot transfer results across a variety of unseen objects on a real world reorientation task. Project website: urlhttps://richardrl.github.io/stable-reorientation/
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 18 Aug 2022.
Builds on
21 of 34 references.
References · 21
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
- 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
- 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
- 2018Open3D: A Modern Library for 3D Data Processingcited by 717
- 2021Implicit Behavioral Cloningcited by 442
- 2016Tutorial on Variational Autoencoderscited by 404
- 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 322
- 2017One-Shot Imitation Learningcited by 232
- 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
- 2016Variational Lossy Autoencodercited by 175
- 2016Learning to Poke by Poking: Experiential Learning of Intuitive Physicscited by 152
- 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
9 more
- 2020An Analysis of SVD for Deep Rotation Estimationcited by 85
- 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
- 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
- 2019Towards Practical Multi-Object Manipulation using Relational Reinforcement Learningcited by 54
- 2018Reasoning About Physical Interactions with Object-Oriented Prediction and Planningcited by 51
- 2020Probabilistic orientation estimation with matrix Fisher distributionscited by 36
- 2019On Object Symmetries and 6D Pose Estimation from Imagescited by 33
- 2020A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertaintycited by 29
- 2018A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Imagescited by 19
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.