Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Abstract: Provided herein are systems, devices, and methods for performing a medical procedure on a patient. The system comprises an ablation catheter comprising a shaft, at least one therapeutic element positioned on the shaft, and one or more tissue-contact sensing components configured to provide a contact signal related to the level of contact between the at least one therapeutic element and tissue. The system further comprises: an energy delivery unit configured to deliver ablative energy to the at least one therapeutic element to create a lesion in target tissue, and to provide an energy delivery data; a force module configured to receive the contact signal and provide contact data; and a processing unit configured to determine an ablation index based on both the energy delivery data and the contact data. The ablation index can represent the status of the lesion being created.

Abstract: An organic field-effect transistor and a fabrication method therefor, including: providing a gate; depositing polymer material onto the gate to form a dielectric layer; performing supercritical fluids treatment on the gate having the dielectric layer deposited; depositing organic semiconductor layer material on the dielectric layer having been processed, to form an organic semiconductor layer; depositing electrode layer material on the organic semiconductor layer and forming an electrode layer. The dielectric properties of the dielectric layer after adopting the supercritical fluids treatment have been significantly improved. While the hysteresis effect of the dielectric layers in the OFET devices has been basically eliminated, the sub-threshold slope of the OFET is also significantly reduced, the carrier mobility is effectively improved. Additionally, an OFET switching rate after being processed is improved, and, by connecting the LEDs in series, the switching rate of the LED is increased.

Abstract: A cardiac information dynamic display system comprises: one or more electrodes configured to record sets of electric potential data representing cardiac activity at a plurality of time intervals; and a cardiac information console, comprising: a signal processor configured to: calculate sets of cardiac activity data at the plurality of time intervals using the recorded sets of electric potential data, wherein the cardiac activity data is associated with surface locations of one or more cardiac chambers; and a user interface module configured to display a series of images, each image comprising: a graphical representation of the cardiac activity. Methods of providing cardiac activity data are also provided.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent behavior prediction using keypoint data. One of the methods includes obtaining data characterizing a scene in an environment, the data comprising: (i) context data comprising data characterizing historical trajectories of a plurality of agents up to the current time point; and (ii) keypoint data for a target agent; processing the context data using a context data encoder neural network to generate a context embedding for the target agent; processing the keypoint data using a keypoint encoder neural network to generate a keypoint embedding for the target agent; generating a combined embedding for the target agent from the context embedding and the keypoint embedding; and processing the combined embedding using a decoder neural network to generate a behavior prediction output for the target agent that characterizes predicted behavior of the target agent after the current time point.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that determine yield behavior for an autonomous vehicle, and can include identifying an agent that is in a vicinity of an autonomous vehicle navigating through a scene at a current time point. Scene features can be obtained and can include features of (i) the agent and (ii) the autonomous vehicle. An input that can include the scene features can be processed using a first machine learning model that is configured to generate (i) a crossing intent prediction that includes a crossing intent score that represents a likelihood that the agent intends to cross a roadway in a future time window after the current time, and (ii) a crossing action prediction that includes a crossing action score that represents a likelihood that the agent will cross the roadway in the future time window after the current time.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting gaze and awareness using a neural network model. One of the methods includes obtaining sensor data (i) that is captured by one or more sensors of an autonomous vehicle and (ii) that characterizes an agent that is in a vicinity of the autonomous vehicle in an environment at a current time point. The sensor data is processed using a gaze prediction neural network to generate a gaze prediction that predicts a gaze of the agent at the current time point. The gaze prediction neural network includes an embedding subnetwork that is configured to process the sensor data to generate an embedding characterizing the agent, and a gaze subnetwork that is configured to process the embedding to generate the gaze prediction.

Abstract: A cardiac information dynamic display system comprises: one or more electrodes configured to record sets of electric potential data representing cardiac activity at a plurality of time intervals; and a cardiac information console, comprising: a signal processor configured to: calculate sets of cardiac activity data at the plurality of time intervals using the recorded sets of electric potential data, wherein the cardiac activity data is associated with surface locations of one or more cardiac chambers; and a user interface module configured to display a series of images, each image comprising: a graphical representation of the cardiac activity. Methods of providing cardiac activity data are also provided.

Abstract: Provided herein are systems for modeling a patients cardiac electrical activity data, including at least one diagnostic catheter for insertion into the heart of the patient and a processing unit. The at least one diagnostic catheter includes at least one recording element to record patient data over multiple cardiac cycles. The patient data includes biopotential data and localization data of the at least one recording element. The processing unit includes a clustering routine that: receives the recorded patient data; segments the recorded patient data by cardiac cycle to produce segmented patient data; groups the segments based on one or more characteristics of the segments to produce segmented data groups; and combines the segmented patient data within each segmented data group to produce one or more composite recordings. The systems create one or more models of cardiac electrical activity of the patient based on the one or more composite recordings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Abstract: A method for magnetic resonance imaging reconstructs images that have reduced under-sampling artifacts from highly accelerated multi-spectral imaging acquisitions. The method includes performing by a magnetic resonance imaging (MRI) apparatus an accelerated multi-spectral imaging (MSI) acquisition within a field of view of the MRI apparatus, where the sampling trajectories of different spectral bins in the acquisition are different; and reconstructing bin images using neural network priors learned from training data as regularization to reduce under-sampling artifacts.

Abstract: Provided are a localization system and method useful in the acquisition and analysis of cardiac information. The localization system and method can be used with systems that perform cardiac mapping, diagnosis and treatment of cardiac abnormalities, as examples, and in the retrieval, processing, and interpretation of such types of information. The localization system and method use high impedance inputs, improved isolation, and relatively high drive currents for pairs of electrodes used to establish a multi-axis coordinate system. The axes can be rotated and scaled to improve localization.

Abstract: A method for magnetic resonance imaging suppresses off-resonance gradient-induced image artifacts due to metal. The method includes performing by a magnetic resonance imaging (MRI) apparatus two multi-spectral imaging (MSI) acquisitions within a field of view of the MRI apparatus, where the two MSI acquisitions have alternating-sign readout gradients. The two MSI acquisitions are then processed and combined by the MRI apparatus using a weighted image combination to produce a final image.

Abstract: Provided are a localization system and method useful in the acquisition and analysis of cardiac information. The localization system and method can be used with systems that perform cardiac mapping, diagnosis and treatment of cardiac abnormalities, as examples, and in the retrieval, processing, and interpretation of such types of information. The localization system and method use high impedance inputs, improved isolation, and relatively high drive currents for pairs of electrodes used to establish a multi-axis coordinate system. The axes can be rotated and scaled to improve localization.

Abstract: A method for magnetic resonance imaging reconstructs images that have reduced under-sampling artifacts from highly accelerated multi-spectral imaging acquisitions. The method includes performing by a magnetic resonance imaging (MRI) apparatus an accelerated multi-spectral imaging (MSI) acquisition within a field of view of the MRI apparatus, where the sampling trajectories of different spectral bins in the acquisition are different; and reconstructing bin images using neural network priors learned from training data as regularization to reduce under-sampling artifacts.

Abstract: Provided are a localization system and method useful in the acquisition and analysis of cardiac information. The localization system and method can be used with systems that perform cardiac mapping, diagnosis and treatment of cardiac abnormalities, as examples, and in the retrieval, processing, and interpretation of such types of information. The localization system and method use high impedance inputs, improved isolation, and relatively high drive currents for pairs of electrodes used to establish a multi-axis coordinate system. The axes can be rotated and scaled to improve localization.

Abstract: A cardiac information dynamic display system comprises: one or more electrodes configured to record sets of electric potential data representing cardiac activity at a plurality of time intervals; and a cardiac information console, comprising: a signal processor configured to: calculate sets of cardiac activity data at the plurality of time intervals using the recorded sets of electric potential data, wherein the cardiac activity data is associated with surface locations of one or more cardiac chambers; and a user interface module configured to display a series of images, each image comprising: a graphical representation of the cardiac activity. Methods of providing cardiac activity data are also provided.

Abstract: Provided are a localization system and method useful in the acquisition and analysis of cardiac information. The localization system and method can be used with systems that perform cardiac mapping, diagnosis and treatment of cardiac abnormalities, as examples, and in the retrieval, processing, and interpretation of such types of information. The localization system and method use high impedance inputs, improved isolation, and relatively high drive currents for pairs of electrodes used to establish a multi-axis coordinate system. The axes can be rotated and scaled to improve localization.

Abstract: A method for magnetic resonance imaging suppresses off-resonance gradient-induced image artifacts due to metal. The method includes performing by a magnetic resonance imaging (MRI) apparatus two multi-spectral imaging (MSI) acquisitions within a field of view of the MRI apparatus, where the two MSI acquisitions have alternating-sign readout gradients. The two MSI acquisitions are then processed and combined by the MRI apparatus using a weighted image combination to produce a final image.