Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty

Abstract

This paper presents a new method for parallel-jaw grasping of isolated objects from depth images, under large gripper pose uncertainty. Whilst most approaches aim to predict the single best grasp pose from an image, our method first predicts a score for every possible grasp pose, which we denote the grasp function. With this, it is possible to achieve grasping robust to the gripper's pose uncertainty, by smoothing the grasp function with the pose uncertainty function. Therefore, if the single best pose is adjacent to a region of poor grasp quality, that pose will no longer be chosen, and instead a pose will be chosen which is surrounded by a region of high grasp quality. To learn this function, we train a Convolutional Neural Network which takes as input a single depth image of an object, and outputs a score for each grasp pose across the image. Training data for this is generated by use of physics simulation and depth image simulation with 3D object meshes, to enable acquisition of sufficient data without requiring exhaustive real-world experiments. We evaluate with both synthetic and real experiments, and show that the learned grasp score is more robust to gripper pose uncertainty than when this uncertainty is not accounted for.

IROS 2016

References in corpus (3)

• PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors
• On the Performance of ConvNet Features for Place Recognition
• Siamese Regression Networks with Efficient mid-level Feature Extraction for 3D Object Pose Estimation

Cited by in corpus (15)

• The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
• Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Beyond Top-Grasps Through Scene Completion
• Robotic Grasp Detection using Deep Convolutional Neural Networks
• Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection
• Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Network
• Jacquard: A Large Scale Dataset for Robotic Grasp Detection
• A Survey of Behavior Learning Applications in Robotics -- State of the Art and Perspectives
• Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations
• Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
• Generative grasp synthesis from demonstration using parametric mixtures
• MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network
• DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future
• Keypoint-Based Bimanual Shaping of Deformable Linear Objects under Environmental Constraints using Hierarchical Action Planning