Cloud-based robot grasping with the google object recognition engine

By Ben Kehoe, Akihiro Matsukawa, Salvatore Candido, James J. Kuffner Jr., Ken Goldberg. 2013

270 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Mechanical Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Mechanical Engineering

In Robotics & Control

Citations in the corpus

Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates (2016, background): “Accelerating robotic learning by pooling experience from multiple robots has long been recognized as a promising direction in the domain of cloud robotics, where it is typically referred to as collective robotic learning [31], [32], [33], [34].”
Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection (2016, background): “…broadly, the ability of robotic systems to learn more quickly by pooling their collective experience has been proposed in a number of prior works, and has been referred to as collective robot learning and an instance of cloud robotics (Inaba et al., 2000; Kuffner, 2010; Kehoe et al., 2013; 2015).”
Collective robot reinforcement learning with distributed asynchronous guided policy search (2016, background): “The ability of robotic systems to learn more quickly and effectively by pooling their collective experience has long been recognized in the domain of cloud robotics, where it is typically referred to as collective robotic learning [11, 12, 13, 14].”
Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics (2017, methodology): “known objects to models in the database [4, 5, 8, 23, 27].”
Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-to-End Learning from Demonstration (2017, background): “Some researchers proposed cloudbased and crowdsourced data collection techniques [9], [10], [11] or the use of simulation environments [12].”
Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks (2018, neutral): “with stored objects based on visual and geometric similarity [6, 11, 19, 20, 29].”
Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data (2020, background): “In order to execute these predicted grasps in the real world, the 3D object models have to be identified, located and their pose estimated [7], [8], [14], [5].”
Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds (2015, background): “ferent controllers to accomplish complicated tasks such as baking cookies [8] and folding the laundry [33], or focus on specific motions such as learning to grasp [24] and open doors [11].”
A Survey of Research on Cloud Robotics and Automation (2015, background): “New approaches are required that are robust to dirty data.”
Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a Multi-Armed Bandit model with correlated rewards (2016, methodology): “[21] created a Cloud-based system to transfer grasps evaluated by PF on 100 objects in a database to a physical robot by indexing the objects with the Google Goggles object recognition engine.”
Image Object Label 3 D CAD Model Candidate Grasps Google Object Recognition Engine Google Cloud Storage Select Feasible Grasp with Highest Success Probability Pose EstimationCamera Robots Cloud 3 D Sensor (2014, methodology): “4), has been incorporated into a Cloud-based system for robot grasping [89] as illustrated in Fig.”
Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices (2015, background): “For example, some papers [25, 27] deploy a recognition system that allows clients to upload images to the server for object classification.”
Domain Randomization and Generative Models for Robotic Grasping (2017, methodology): “Some methods attempt to make these estimates more robust to gripper and object pose uncertainty and sensor error by instead maximizing the expected value of a metric under uncertainty [15], [48].”
Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data (2019, methodology): “Concretely, this approach has been used in mapping [18] and localization [19], perception [20], grasping [21], visuomotor control [22], speech processing [23], and other applications.”
Learning ambidextrous robot grasping policies (2019, methodology): “One approach to UP is to create a database of grasps on threedimensional (3D) object models using grasp performance metrics derived from geometry and physics (1, 2) with stochastic sampling to model uncertainty (3, 4).”
Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates (2018, methodology): “We start by introducing the deﬁnitions (S.73c) 1) Bound for y ej : We iterate equation (S.15) to get X X X Note that using Gershgorin’s theorem [2] the above assumption can be satisﬁed by satisfying the following constraints on the step-size µ : (S.74) q We now also impose the following conditions…”