Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Network

04/10/2018
by   Qingkai Lu, et al.
0

We propose a novel approach to multi-fingered grasp planning leveraging learned deep neural network models. We train a convolutional neural network to predict grasp success as a function of both visual information of an object and grasp configuration. We can then formulate grasp planning as inferring the grasp configuration which maximizes the probability of grasp success. We efficiently perform this inference using a gradient-ascent optimization inside the neural network using the backpropagation algorithm. Our work is the first to directly plan high quality multifingered grasps in configuration space using a deep neural network without the need of an external planner. We validate our inference method performing both multifinger and two-finger grasps on real robots. Our experimental results show that our planning method outperforms existing planning methods for neural networks; while offering several other benefits including being data-efficient in learning and fast enough to be deployed in real robotic applications.

READ FULL TEXT
research
01/25/2020

Multi-Fingered Grasp Planning via Inference in Deep Neural Networks

We propose a novel approach to multi-fingered grasp planning leveraging ...
research
01/10/2019

Modeling Grasp Type Improves Learning-Based Grasp Planning

Different manipulation tasks require different types of grasps. For exam...
research
09/12/2018

Attention based visual analysis for fast grasp planning with multi-fingered robotic hand

We present an attention based visual analysis framework to compute grasp...
research
06/06/2020

Multi-Fingered Active Grasp Learning

Learning-based approaches to grasp planning are preferred over analytica...
research
06/29/2018

Workspace Aware Online Grasp Planning

This work provides a framework for a workspace aware online grasp planne...
research
07/09/2021

Excavation Learning for Rigid Objects in Clutter

Autonomous excavation for hard or compact materials, especially irregula...
research
10/17/2017

Domain Randomization and Generative Models for Robotic Grasping

Deep learning-based robotic grasping has made significant progress the p...

Please sign up or login with your details

Forgot password? Click here to reset