Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future that meet a criterion, allowing for more efficient sampling. A predicted position of the object in the future may be determined by sampling from the distribution.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future. A predicted position of the object at a subsequent timestep may be determined by sampling from the distribution of predicted positions according to various sampling strategies. Alternatively, the predicted position of the object may be overwritten using a candidate position of the object.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a predicted position of the object at a subsequent timestep. Further, a predicted trajectory of the object may be determined using predicted positions of the object at various timesteps.

Abstract: The invention provides a method for generating a non-invasive measure of blood vessel rigidity for a subject. The method includes obtaining 2D ultrasound data and 3D ultrasound data of the blood vessel from a given measurement location. The 2D ultrasound data provides information relating to a movement of the blood vessel and the 3D ultrasound data provides information relating to a shape of the blood vessel. A motion of the blood vessel is then determined based on the movement of the blood vessel. The method then includes providing the determined motion of the blood vessel, the shape of the blood vessel and an obtained non-invasive pressure measurement to a biomechanical model. A measure of rigidity is then determined based on the biomechanical model.

Abstract: The invention relates to compounds and methods of treating diseases including but not limited to, cancer, non-cancer proliferative disease, sepsis, autoimmune disease, viral infection, atherosclerosis, Type 1 or 2 diabetes, obesity, inflammatory disease, or Myc-dependent disorder including by modulating biological processes by the inhibition of cell cycle checkpoint targets CDKs, and/or PI3 kinase, and/or bromodomain protein binding to substrates, comprising the administration of a compound(s) of Formula 1-V1 (or pharmaceutically acceptable salts thereof) as defined herein.

Abstract: A computer system is disclosed comprising a processor arrangement communicatively coupled to a data storage arrangement storing a digital model of a section of a lumen system of a patient; and a communication module communicatively coupled to said processor arrangement and arranged to receive sensor data pertaining to an internal parameter of said lumen system from a sensor within said section of the lumen system. The processor arrangement is arranged to receive said sensor data from the communication module; retrieve said digital model from the data storage arrangement; simulate an actual physical condition of said lumen system by developing said digital model based on the received sensor data; and generate an output relating to said simulated actual physical condition for updating an electronic device. Also disclosed is a method of monitoring a patient with such a computer system, a computer program product for implementing such a method and a patient monitoring system.

Abstract: The invention relates to compounds and methods of treating diseases including but not limited to, cancer, non-cancer proliferative disease, sepsis, autoimmune disease, viral infection, atherosclerosis. Type 1 or 2 diabetes, obesity, inflammatory disease, or Myc-dependent disorder including by modulating biological processes by the inhibition of cell cycle checkpoint targets CDKs, and/or PI3 kinase, and/or bromodomain protein binding to substrates, comprising the administration of a compound(s) of Formula 1-V1 (or pharmaceutically acceptable salts thereof) as defined herein.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on object movement are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) may capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle, a pedestrian, a bicycle). A multi-channel image representing a top-down view of the object(s) and the environment may be generated based in part on the sensor data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) may also be encoded in the image. Multiple images may be generated representing the environment over time and input into a prediction system configured to output a trajectory template (e.g., general intent for future movement) and a predicted trajectory (e.g., more accurate predicted movement) associated with each object. The prediction system may include a machine learned model configured to output the trajectory template(s) and the predicted trajector(ies).

Abstract: The present disclosure relates to a system for patient-specific intervention planning, the system comprising a physical model of an anatomical structure, wherein the physical model is a patient-specific model based on medical image data; a virtual model of the anatomical structure, wherein the virtual model is a patient-specific model based on medical image data; a tracking device configured to track a position of a physical representation of an interventional tool with respect to the physical model of the anatomical structure; a processor configured to perform the step of: registering the physical model of the anatomical structure with the virtual model of the anatomical structure and registering the physical representation of the interventional tool with a virtual representation of the interventional tool based on the position of the physical representation of the interventional tool and the physical model of the anatomical structure.

Abstract: The invention relates to compounds useful for inhibiting at least one member of the BET family and at least one kinase such as but not limited to mTOR, and to methods of treating diseases including COVID-19 by administration of a compound(s) of Formulas I-V or pharmaceutically acceptable salts thereof as defined herein.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future that meet a criterion, allowing for more efficient sampling. A predicted position of the object in the future may be determined by sampling from the distribution.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a predicted position of the object at a subsequent timestep. Further, a predicted trajectory of the object may be determined using predicted positions of the object at various timesteps.

Abstract: Techniques for determining a response of a simulated vehicle to a simulated object in a simulation are discussed herein. Log data captured by a physical vehicle in an environment can be received. Object data representing an object in the log data can be used to instantiate a simulated object in a simulation to determine a response of a simulated vehicle to the simulated object. Additionally, one or more trajectory segments in a trajectory library representing the log data can be determined and instantiated as a trajectory of the simulated object in order to increase the accuracy and realism of the simulation.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle.

Abstract: The invention relates to methods of treating diseases including but not limited to, cancer, non-cancer proliferative disease, sepsis, autoimmune disease, viral, bacterial or fungal infection, atherosclerosis, Type 1 or 2 diabetes, obesity, inflammatory disease, and/or SYK-associated disorder including by modulating biological processes through the inhibition of SYK alone, or in combination with inhibition of one or more of PI3 kinase including PI3K-gamma isoform, BET bromodomain proteins, CDK 4/6, and checkpoint proteins, comprising the administration of a compound(s) of Formula I-V (or pharmaceutically acceptable salts thereof) as defined herein.

Abstract: Techniques are discussed herein for generating and using graph neural networks (GNNs) including vectorized representations of map elements and entities within the environment of an autonomous vehicle. Various techniques may include vectorizing map data into representations of map elements, and object data representing entities in the environment of the autonomous vehicle. In some examples, the autonomous vehicle may generate and/or use a GNN representing the environment, including nodes stored as vectorized representations of map elements and entities, and edge features including the relative position and relative yaw between the objects. Machine-learning inference operations may be executed on the GNN, and the node and edge data may be extracted and decoded to predict future states of the entities in the environment.

Abstract: A stress prediction device for predicting mechanical stress exerted to a deformable object due contact between the object and an external device that is to be inserted into the object at an intended insertion position comprises a segmentation unit configured to access generic model data representing a generic reference object that comprises predefined secondary landmark features at predefined landmark positions, which are not identifiable using a predefined imaging technique, and pre-insertion object image data acquired using the imaging technique. It provides segmented object model data which comprises associated mapped landmark position data indicative of mapped landmark positions of the secondary landmark features. A stress determination unit determines and provides predictive stress information indicative of mechanical stress exerted to at least one of the secondary landmark features at the associated mapped landmark position due to mechanical contact between the object and the external device.

Abstract: Techniques are disclosed for re-executing a data processing pipeline following a failure of at least one of its components. The techniques may include a syntax for defining a compute graph associated with the data processing pipeline and receiving such a compute graph in association with a specific data processing pipeline. The technique may include executing the data processing pipeline, determining that a component of the data processing pipeline failed, and determining a portion of the data processing pipeline to execute/re-execute based at least in part on dependencies defined by the data processing pipeline in association with the failed component. Re-executing the one or more components may comprise retrieving an output saved in association with a component upon which the failed component depends.

Abstract: The present disclosure relates generally to protective devices and cover members. In some embodiments, cover members are provided that are operable to protect covered components and to allow heat dissipation from the components. Cover members of the present disclosure are suitable for use with heat exchangers including, for example, those provided with hot water pressure washers.

Abstract: The invention provides a method for generating a non-invasive measure of blood vessel rigidity for a subject. The method includes obtaining 2D ultrasound data and 3D ultrasound data of the blood vessel from a given measurement location. The 2D ultrasound data provides information relating to a movement of the blood vessel and the 3D ultrasound data provides information relating to a shape of the blood vessel. A motion of the blood vessel is then determined based on the movement of the blood vessel. The method then includes providing the determined motion of the blood vessel, the shape of the blood vessel and an obtained non-invasive pressure measurement to a biomechanical model. A measure of rigidity is then determined based on the biomechanical model.