Gras** of an object by a robot based on grasp strategy determined using machine learning model (s)
U Nagarajan, B Homberg - US Patent 11,097,418, 2021 - Google Patents
Gras** of an object, by an end effector of a robot, based on a grasp strategy that is
selected using one or more machine learning models. The grasp strategy utilized for a given …
selected using one or more machine learning models. The grasp strategy utilized for a given …
Robot interaction with objects based on semantic information associated with embedding spaces
U Nagarajan - US Patent 10,754,318, 2020 - Google Patents
Techniques described herein relate to using reduced-dimensionality embeddings generated
from robot sensor data to identify predetermined semantic labels that guide robot interaction …
from robot sensor data to identify predetermined semantic labels that guide robot interaction …
Generating and managing deep tensor neural networks
Techniques for generating and managing, including simu lating and training, deep tensor
neural networks are pre sented. A deep tensor neural network comprises a graph of nodes …
neural networks are pre sented. A deep tensor neural network comprises a graph of nodes …
Systems and methods for training machine learning model based on cross-domain data
Z Zhao, Y Guo - US Patent App. 17/131,790, 2022 - Google Patents
Systems and methods for training an initial machine learning model is provided. The system
may train an initial machine learning model using source domain training data with sample …
may train an initial machine learning model using source domain training data with sample …
Auxiliary parts damage determination
R Ranca, M Horstmann, B Mattsson, J Oellrich… - US Patent …, 2022 - Google Patents
(57) ABSTRACT A method of determining, one or more damage states of one or more
auxiliary parts of a damaged vehicle, the vehicle comprising a plurality of normalized parts …
auxiliary parts of a damaged vehicle, the vehicle comprising a plurality of normalized parts …
Hybrid machine learning-based systems and methods for training an object picking robot with real and simulated performance data
For training an object picking robot with real and simulated grasp performance data, grasp
locations on an object are assigned based on object physical properties. A simulation …
locations on an object are assigned based on object physical properties. A simulation …
Paint blending determination
R Ranca, M Horstmann, B Mattsson, J Oellrich… - US Patent …, 2022 - Google Patents
The present invention relates to assessing the damage and repairs needed to damaged
vehicles. More particularly, the present invention relates to assessing vehicle damage using …
vehicles. More particularly, the present invention relates to assessing vehicle damage using …
Control policies for robotic agents
Methods, systems, and apparatus, including computer pro grams encoded on computer
storage media, of training a global policy neural network. One of the methods includes …
storage media, of training a global policy neural network. One of the methods includes …
Using simulation and domain adaptation for robotic control
US11341364B2 - Using simulation and domain adaptation for robotic control - Google
Patents US11341364B2 - Using simulation and domain adaptation for robotic control …
Patents US11341364B2 - Using simulation and domain adaptation for robotic control …
Machine learning methods and apparatus for robotic manipulation and that utilize multi-task domain adaptation
Implementations are directed to training a machine learning model that, once trained, is
used in performance of robotic gras** and/or other manipulation task (s) by a robot. The …
used in performance of robotic gras** and/or other manipulation task (s) by a robot. The …