Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand

Abstract

Grasping objects with limited or no prior knowledge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem, especially when it comes to only partial observability and versatile grasping with multi-fingered hands. We present a novel, fast, and high fidelity deep learning pipeline consisting of a shape completion module that is based on a single depth image, and followed by a grasp predictor that is based on the predicted object shape. The shape completion network is based on VQDIF and predicts spatial occupancy values at arbitrary query points. As grasp predictor, we use our two-stage architecture that first generates hand poses using an autoregressive model and then regresses finger joint configurations per pose. Critical factors turn out to be sufficient data realism and augmentation, as well as special attention to difficult cases during training. Experiments on a physical robot platform demonstrate successful grasping of a wide range of household objects based on a depth image from a single viewpoint. The whole pipeline is fast, taking only about 1 s for completing the object's shape (0.7 s) and generating 1000 grasps (0.3 s).

8 pages, 10 figures, 3 tables, 1 algorithm. Published in Humanoids 2023. Project page: https://aidx-lab.org/grasping/humanoids23

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• ShapeNet: An Information-Rich 3D Model Repository
• Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols
• DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
• Learning 3D Shape Completion under Weak Supervision
• Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Hand
• TransSC: Transformer-based Shape Completion for Grasp Evaluation
• Speeding Up Optimization-based Motion Planning through Deep Learning
• Self-Contained Calibration of an Elastic Humanoid Upper Body Using Only a Head-Mounted RGB Camera
• Shape Completion with Prediction of Uncertain Regions

Cited by in corpus (1)

• Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning Critic