Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity
arXiv:2009.13146
Abstract
Learning-based 3D object reconstruction enables single- or few-shot estimation of 3D object models. For robotics, this holds the potential to allow model-based methods to rapidly adapt to novel objects and scenes. Existing 3D reconstruction techniques optimize for visual reconstruction fidelity, typically measured by chamfer distance or voxel IOU. We find that when applied to realistic, cluttered robotics environments, these systems produce reconstructions with low physical realism, resulting in poor task performance when used for model-based control. We propose ARM, an amodal 3D reconstruction system that introduces (1) a stability prior over object shapes, (2) a connectivity prior, and (3) a multi-channel input representation that allows for reasoning over relationships between groups of objects. By using these priors over the physical properties of objects, our system improves reconstruction quality not just by standard visual metrics, but also performance of model-based control on a variety of robotics manipulation tasks in challenging, cluttered environments. Code is available at github.com/wagnew3/ARM.
References in corpus (9)
- Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
- Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
- Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
- Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
- Learning to Reconstruct Shapes from Unseen Classes
- Model Predictive Path Integral Control using Covariance Variable Importance Sampling
- Robust Grasp Planning Over Uncertain Shape Completions
- Beyond Top-Grasps Through Scene Completion
- Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense