Deep learning for detecting robotic grasps
Explore this paper's citation graph
Summary
This work presents a two-step cascaded system with two deep networks, where the top detections from the first are re-evaluated by the second, and shows that this method improves performance on an RGBD robotic grasping dataset, and can be used to successfully execute grasps on two different robotic platforms.
- Type
- article
- Published
- 2013-01-15
- Cited by
- 1,785
- References
- 88
- Access
- Open access
- OpenAlex
- https://openalex.org/W1999156278
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:5240721
Keywords
Artificial intelligence, Computer science, Regularization (linguistics), Deep learning, RGB color model
References
- A Framework for Push-Grasping in Clutter
- Multimodal learning with deep Boltzmann machines
- Coupled Dynamical System Based Hand-Arm Grasp Planning under Real-Time Perturbations
- Grasp Moduli Spaces
- Robust Object Grasping using Force Compliant Motion Primitives
- Graspit! A versatile simulator for robotic grasping
- Planning optimal grasps
- Robotic grasping and contact: a review
- Vision-based computation of three-finger grasps on unknown planar objects
- Deep Lambertian Networks
- Semantic parsing for priming object detection in indoors RGB-D scenes
- Rigid 3D geometry matching for grasping of known objects in cluttered scenes
- Robot Grasp Synthesis Algorithms: A Survey
- From caging to grasping
- Opportunistic Use of Vision to Push Back the Path-Planning Horizon
- Acoustic Modeling Using Deep Belief Networks
- Robust Visual Servoing
- Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis
- An overview of 3D object grasp synthesis algorithms
- Grasping novel objects with depth segmentation
Cited by
- Automatic Grasp Selection using a Camera in a Hand Prosthesis
- Convolutional nets and watershed cuts for real-time semantic Labeling of RGBD videos
- High-level Reasoning and Low-level Learning for Grasping: A Probabilistic Logic Pipeline
- Place Classification With a Graph Regularized Deep Neural Network
- Multimodal deep learning for robust RGB-D object recognition
- 3D Convolutional Neural Networks for landing zone detection from LiDAR
- A Roadmap Towards Intelligent and Autonomous Object Manipulation for assembly Tasks
- Leveraging big data for grasp planning
- Affordance detection of tool parts from geometric features
- Robot Learning Manipulation Action Plans by "Watching" Unconstrained Videos from the World Wide Web
- RoboBrain: Large-Scale Knowledge Engine for Robots
- Learning preferences for manipulation tasks from online coactive feedback
- Machine Learning for Robot Grasping and Manipulation
- Real-time grasp detection using convolutional neural networks
- Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds
- Grasp type revisited: A modern perspective on a classical feature for vision
- Localizing Grasp Affordances in 3-D Points Clouds Using Taubin Quadric Fitting
- Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction
- Exploitation of environmental constraints in human and robotic grasping
- Tangled: Learning to untangle ropes with RGB-D perception
Related papers
- Wireless Animatronic Arm using Embedded Systems
- Design And Implementation Of Anthropomorphic Robotic Arm
- On two recent nonconvex penalties for regularization in machine learning
- A vision-based teleoperation method for a robotic arm with 4 degrees of freedom
- Vision-Based Trainable Robotic Arm for Individuals with Motor Disability
- Robotic Arm Manipulation Laboratory With a Six Degree of Freedom JACO Arm
- Simulation analysis of shoulder joint for biomimetic robotic arm
- Dynamics and experiments of a tendon-actuated flexible robotic arm for capturing a floating target