Abstract: Techniques are discussed herein for generating trajectories for controlling motion and/or other behaviors of vehicles in complex driving environments. In certain examples, a search algorithm may be used to determine and evaluate a set of possible candidate actions for a vehicle, including candidate actions based on a predetermined exploration policy and additional candidate actions based on machine learned models that output predicted behaviors for the vehicle based on the current driving environment. Costs associated the various candidate actions may be evaluated based on state transition costs and/or future state predictions of the driving environment. Certain examples may include a tree search using a combination of predetermined heuristic candidate actions and adaptive-learning candidate actions at various nodes within a tree structure representing a driving route from a current vehicle state to an intended end state.

Abstract: In various examples, one or more systems detect, via received sensor data, intervention or disengagement events associated with one or more autonomous or semi-autonomous robotics systems included in a fleet of robotics systems. Based on a detected intervention or disengagement event, the one or more systems may generate an alert requesting human assistance or guidance. The one or more systems may also analyze a detected intervention or disengagement event and generate a natural language description of the event, classify the event into one or more categories and/or failure modes, generate novel entries in a training dataset based on the detected event, or initiate an automated retraining of one or more autonomous or semi-autonomous control routines based on the detected event.

Abstract: Techniques for enabling dynamic routing are described herein. A vehicle may receive a destination and generate a path to the destination. Further, the vehicle may generate a local graph that includes one or more driving lanes. The vehicle may use the path and the local graph to determine overlap data indicative of a distance that the path overlaps with the driving lane(s). The vehicle may utilize the overlap data to determine a color value(s) to associate with the driving lane(s) in a top-down image. Accordingly, based on determining the color value(s), the vehicle may generate colored top-down image(s) of the driving lane(s) and use such data to control the vehicle.

Abstract: In various examples, a technique for generating simulation data includes generating, via one or more simulations, simulation data associated with operation of a first machine in an environment. The technique also includes determining a command to the first machine based at least on the simulation data and a goal associated with the first machine and updating the simulation data based at least on the command. The technique further includes storing the simulation data, the command, and the updated simulation data in one or more data records, and causing a second machine to perform one or more actions based at least on the one or more data records.

Abstract: In various examples, a technique for performing end-to-end navigation using a generative world model includes converting a set of sensory inputs received by a machine at a current time step into a set of embedded features. The technique also includes generating, via execution of one or more neural networks, one or more states associated with the current time step based at least on the set of embedded features, a history of states preceding the current time step, and a first set of actions associated with a previous time step. The technique further includes converting, via execution of the one or more neural networks, the one or more states into a set of predictions associated with the current time step, and performing, by the machine, a second set of actions associated with the current time step based on the set of predictions.

Abstract: In various examples, a technique for performing a task includes converting one or more sensory inputs obtained using one or more sensors of a machine into a plurality of segments. The technique also includes, for each segment included in the plurality of segments, generating, via execution of a machine learning model, a caption for the segment, and storing, in a data store, a representation of the caption in association with the segment. The technique further includes performing, by the machine, one or more actions based at least on one or more queries of the data store.

Abstract: Techniques for enabling dynamic routing are described herein. A vehicle may receive a destination and generate a path to the destination. Further, the vehicle may generate a local graph that includes one or more driving lanes. The vehicle may use the path and the local graph to determine overlap data indicative of a distance that the path overlaps with the driving lane(s). The vehicle may utilize the overlap data to determine a color value(s) to associate with the driving lane(s) in a top-down image. Accordingly, based on determining the color value(s), the vehicle may generate colored top-down image(s) of the driving lane(s) and use such data to control the vehicle.

Abstract: A machine-learned architecture for estimating the cost determined by a cost function for a prediction node of a tree search for exploring potential paths for controlling a vehicle may include two portions: a set up portion that includes models trained to process static data and a second portion that processes dynamic object data. The respective portions of the architecture may comprise various models that determine intermediate outputs that may be projected into a space associated with estimated cost. That estimated cost may identify an estimate of an output of the cost function for paths that are based on a particular prediction node of the tree search.

Abstract: Techniques for determining a vehicle trajectory that causes a vehicle to navigate in an environment relative to one or more objects are described herein. In some cases, the techniques described herein relate to selectively expanding a tree structure (e.g., a decision tree structure) to efficiently search for simulation data that can be used to evaluate vehicle control trajectories. The tree structure may include state nodes representing observed and/or predicted environment states, and action nodes representing candidate actions the vehicle may take. By selectively and incrementally expanding the tree structure, more optimal trajectories can be determined without exhaustively evaluating every possible outcome.

Abstract: A machine-learned architecture for estimating the cost determined by a cost function for a prediction node of a tree search for exploring potential paths for controlling a vehicle may include two portions: a set up portion that includes models trained to process static data and a second portion that processes dynamic object data. The respective portions of the architecture may comprise various models that determine intermediate outputs that may be projected into a space associated with estimated cost. That estimated cost may identify an estimate of an output of the cost function for paths that are based on a particular prediction node of the tree search.

Abstract: There is provided a system configured to receive data associated with a vehicle operating within an environment; generate, based at least in part on the data, a graph comprising a plurality of nodes, a node of the plurality associated with one or more of a vehicle operating in the environment, a road feature, an additional vehicle, or a pedestrian; input the graph into a self-supervised machine learned model comprising an encoder, wherein the machine learned model is trained to output a representation associated with the node; receive, from the self-supervised machine learned model, a representation associated with the node; and transmit the representation to a downstream machine learned model trained to output control data based at least in part on the representation, wherein the control data is configured to control the vehicle or another vehicle.

Abstract: A machine-learned architecture for estimating the cost determined by a cost function for a prediction node of a tree search for exploring potential paths for controlling a vehicle may include two portions: a set up portion that includes models trained to process static data and a second portion that processes dynamic object data. The respective portions of the architecture may comprise various models that determine intermediate outputs that may be projected into a space associated with estimated cost. That estimated cost may identify an estimate of an output of the cost function for paths that are based on a particular prediction node of the tree search.

Abstract: In one embodiment, example systems and methods related to a manner of optimizing LiDAR sensor placement on autonomous vehicles are provided. A range-of-interest is defined for the autonomous vehicle that includes the distances from which the autonomous vehicle is interested in collecting sensor data. The range-of-interest is segmented into multiple cubes of the same size. For each LiDAR sensor, a shape is determined based on information such as the number of lasers in each LiDAR sensor and the angle associated with each laser. An optimization problem is solved using the determined shape for each LiDAR sensor and the cubes of the range-of-interest to determine the locations to place each LiDAR sensor to maximize the number of cubes that are captured. The optimization problem may further determine the optimal pitch angle and roll angle to use for each LiDAR sensor to maximize the number of cubes that are captured.

Abstract: In one embodiment, a computing system of a vehicle may receive vehicle driving data associated with a vehicle driving in an environment and detected environment data associated with the environment. The system may generate a reference trajectory of the vehicle driving in the environment based on the vehicle driving data. The system may determine driving constraints associated with the environment based on the detected environmental data. The system may generate a trajectory of the vehicle based on the driving constraints. The system may determine a difference in at least one parameter associated with the trajectory relative to at least one corresponding parameter associated with the reference trajectory. The system may adjust weight values associated with cost functions of the trajectory based on the difference between the at least one parameter associated with the trajectory and the corresponding parameter associated with the reference trajectory.

Abstract: In one embodiment, a computing system of a vehicle may receive vehicle driving data associated with a vehicle driving in an environment and detected environment data associated with the environment. The system may generate a reference trajectory of the vehicle driving in the environment based on the vehicle driving data. The system may determine driving constraints associated with the environment based on the detected environmental data. The system may generate a trajectory of the vehicle based on the driving constraints. The system may determine a difference in at least one parameter associated with the trajectory relative to at least one corresponding parameter associated with the reference trajectory. The system may adjust weight values associated with cost functions of the trajectory based on the difference between the at least one parameter associated with the trajectory and the corresponding parameter associated with the reference trajectory.

Abstract: Examples disclosed herein may involve (i) generating a set of candidate trajectories for a vehicle that each comprise a respective series of planned states for the vehicle, (ii) scoring the candidate trajectories in the generated set of candidate trajectories using one or more reference models that are each configured to (a) receive input values for a respective set of feature variables that are correlated to a respective scoring parameter and (b) output a value for the respective scoring parameter that is reflective of human-driving behavior, (iii) based at least in part on the scoring, selecting a candidate trajectory from the generated set of candidate trajectories to serve as a planned trajectory for vehicle, and (iv) using the selected candidate trajectory as the planned trajectory for the vehicle.

Abstract: Disclosed herein is a 31.75 mm (1.25?) system that represents a new and improved custom frameless cabinet design and manufacturing method specifically for the North American market where imperial measurement system is used. The system is based on the concept of worldwide prevailing 32 mm European frameless cabinet making system and uses all existing 32 mm system machinery and tools. By using ready-to-use panel parts and corner cabinets, this system greatly increases custom cabinetry's manufacturing efficiency and all but eliminates the conversion proximity and error when using standard European 32 mm system.

Abstract: In one embodiment, example systems and methods related to a manner of optimizing LiDAR sensor placement on autonomous vehicles are provided. A range-of-interest is defined for the autonomous vehicle that includes the distances from which the autonomous vehicle is interested in collecting sensor data. The range-of-interest is segmented into multiple cubes of the same size. For each LiDAR sensor, a shape is determined based on information such as the number of lasers in each LiDAR sensor and the angle associated with each laser. An optimization problem is solved using the determined shape for each LiDAR sensor and the cubes of the range-of-interest to determine the locations to place each LiDAR sensor to maximize the number of cubes that are captured. The optimization problem may further determine the optimal pitch angle and roll angle to use for each LiDAR sensor to maximize the number of cubes that are captured.

Abstract: Embodiments of the present invention provide a method and an apparatus for eliminating interference among transmission channels of a transmitter. The method includes: generating a compensation parameter according to an output signal of an analog module on a transmission channel to be processed by the transmitter and an input signal of a digital module on each transmission channel among all transmission channels of the transmitter; generating a cancellation signal according to the compensation parameter and an input or output signal of a digital module on another transmission channel except for the transmission channel to be processed; and performing, according to the cancellation signal, interference elimination processing on the transmission channel to be processed. The method and apparatus according to the embodiments of the present invention avoid an increase of a transmitter product size, and improve an effect of eliminating interference among transmission channels.

Abstract: The present invention is directed to methods and compositions for augmenting treatment of cancers and other proliferative disorders. In particular embodiments, the invention combines the administration of an agent that inhibits the anti-apoptotic activity of galectin-3 (e.g., a “galectin-3 inhibitor”) so as to potentiate the toxicity of a chemotherapeutic agent. In certain preferred embodiments, the conjoint therapies of the present invention can be used to improve the efficacy of those chemotherapeutic agents whose cytotoxicity is influenced by the status of an anti-apoptotic Bcl-2 protein for the treated cell. For instance, galectin-3 inhibitors can be administered in combination with a chemotherapeutic agent that interferes with DNA replication fidelity or cell-cycle progression of cells undergoing unwanted proliferation.