We teach a real robot to grasp real fish, by training a virtual robot exclusively in virtual reality. Our approach implements robot imitation learning from a human supervisor in virtual reality. A deep 3D convolutional neural network computes grasps from a 3D occupancy grid obtained from depth imaging at multiple viewpoints. In virtual reality, a human supervisor can easily and intuitively demonstrate examples of how to grasp an object, such as a fish. From a few dozen of these demonstrations, we use domain randomization to generate a large synthetic training data set consisting of 100 000 example grasps of fish. Using this data set for training purposes, the network is able to guide a real robot and gripper to grasp real fish with good success rates. The newly proposed domain randomization approach constitutes the first step in how to efficiently perform robot imitation learning from a human supervisor in virtual reality in a way that transfers well to the real world.
Abstract-We present an approach to robotic deep learning from demonstration in virtual reality, which combines a deep 3D convolutional neural network, for grasp detection from 3D point clouds, with domain randomization to generate a large training data set. The use of virtual reality (VR) enables robot learning from demonstration in a virtual environment. In this environment, a human user can easily and intuitively demonstrate examples of how to grasp an object, such as a fish. From a few dozen of these demonstrations, we use domain randomization to generate a large synthetic training data set consisting of 76 000 example grasps of fish. After training the network using this data set, the network is able to guide a gripper to grasp virtual fish with good success rates. Our domain randomization approach is a step towards an efficient way to perform robotic deep learning from demonstration in virtual reality.
We consider the case of robotic bin picking of reflective steel parts, using a structured light 3D camera as a depth imaging device. In this paper, we present a new method for bin picking, based on a dual-resolution convolutional neural network trained entirely in a simulated environment. The dualresolution network consists of a high resolution focus network to compute the grasp and a low resolution context network to avoid local collisions.The reflectivity of the steel parts result in depth images that have a lot of missing data. To take this into account, training of the neural net is done by domain randomization on a large set of synthetic depth images that simulate the missing data problems of the real depth images. We demonstrate both in simulation and in a real-world test that our method can perform bin picking of reflective steel parts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.