Abstract: Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

Abstract: Approaches provide for performance of a complex (e.g., compound) task that may involve multiple discrete tasks not obvious from an instruction to perform the complex task. A set of conditions for an environment can be determined using captured image data, and the instruction analyzed to determine a set of final conditions to exist in the environment after performance of the instruction. These initial and end conditions are used to determine a sequence of discrete tasks to be performed to cause a robot or automated device to perform the instruction. This can involve use of a symbolic or visual planner in at least some embodiments, as well as a search of possible sequences of actions available for the robot or automated device. A robot can be caused to perform the sequence of discrete tasks, and feedback provided such that the sequence of tasks can be modified as appropriate.

Abstract: Approaches presented herein provide for predictive control of a robot or automated assembly in performing a specific task. A task to be performed may depend on the location and orientation of the robot performing that task. A predictive control system can determine a state of a physical environment at each of a series of time steps, and can select an appropriate location and orientation at each of those time steps. At individual time steps, an optimization process can determine a sequence of future motions or accelerations to be taken that comply with one or more constraints on that motion. For example, at individual time steps, a respective action in the sequence may be performed, then another motion sequence predicted for a next time step, which can help drive robot motion based upon predicted future motion and allow for quick reactions.

Abstract: Approaches presented herein provide for a framework to integrate human provided feedback in natural language to update a robot planning cost or value. The natural language feedback may be modeled as a cost or value associated with completing a task assigned to the robot. This cost or value may then be added to an initial task cost or value to update one or more actions to be performed by the robot. The framework can be applied to both real work and simulated environments where the robot may receive instructions, in natural language, that either provide a goal, modify an existing goal, or provide constraints to actions to achieve an existing goal.

Abstract: Apparatuses, systems, and techniques to place one or more objects in a location and orientation. In at least one embodiment, one or more circuits are to use one or more neural networks to cause one or more autonomous devices to place one or more objects in a location and orientation based, at least in part, on one or more images of the location and orientation.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: Apparatuses, systems, and techniques to train a machine learning model. In at least one embodiment, a first machine learning model is trained to infer a concept based on first information, training data is labeled using the first machine learning model, and a second machine learning model is trained to infer the concept using the labeled training data.

Abstract: A robotic system is provided for performing rearrangement tasks guided by a natural language instruction. The system can include a number of neural networks used to determine a selected rearrangement of the objects in accordance with the natural language instruction. A target object predictor network processes a point cloud of the scene and the natural language instruction to identify a set of query objects that are to-be-rearranged. A language conditioned prior network processes the point cloud, natural language instruction, and the set of query objects to sample a distribution of rearrangements to generate a number of sets of pose offsets for the set of query objects. A discriminator network then processes the samples to generate scores for the samples. The samples may be refined until a score for at least one of the sample generated by the discriminator network is above a threshold value.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: Apparatuses, systems, and techniques to perform a language-guided distributional tree search based at least in part on a natural language task. In at least one embodiment, a tree search is performed using one or more neural networks to determine an action to be performed by an autonomous agent.

Abstract: Some embodiments provide enhanced resolution imaging systems comprising: a mounting; an electro-optical image capture system; an angular jitter sensor system; an illumination source system; and an image capture control circuit is configured to: receive ling of sight displacement sensor data; obtain, during the capture frame, an angular displacement of the image capture system and monitor when the detected angular displacement of the image capture system, based on the sensor data, is beyond an angular displacement threshold envelope; and activate exposure of the image capture system to illumination, during the capture frame, when the detected angular displacement of the image capture system is within the angular displacement threshold envelope, and control a level of exposure of the image capture system to illumination, during the capture frame, when the detected angular displacement is not within the angular displacement threshold envelope.

Abstract: Some embodiments provide enhanced resolution imaging systems. These systems comprise: a mounting configured to secure with a vehicle; an electro-optical image capture system configured to sequentially obtain a series of frames per second; and a first jitter compensation system comprising: an angular velocity sensor system to detect velocity of change of line of sight angular displacement of the image capture system; and an image capture control circuit is configured to: receive, in real-time, angular velocity data from the angular velocity sensor system; identify, during the frame, when an angular velocity is less than an angular velocity threshold; and activate, during the frame, exposure of the image capture system to illumination for at least one of: at least a minimum integration period of time during the frame, and while the angular velocity is less than the angular velocity threshold during the frame.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: Apparatuses, systems, and techniques to facilitate robotic execution using neural networks to perform complex, multi-step tasks in situations for which a robot has not been trained. In at least one embodiment, a hierarchical model is trained to infer a logical state from a world state and determine executable actions for a robot based on that logical state.

Abstract: Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

Abstract: Some embodiments provide enhanced resolution imaging systems comprising: a mounting; an electro-optical image capture system; an angular jitter sensor system; an illumination source system; and an image capture control circuit is configured to: receive ling of sight displacement data; obtain, during the capture frame, an angular displacement of the image capture system and monitor when the detected angular displacement of the image capture system, based on the LOS angular displacement data, is beyond an angular displacement threshold envelope; and activate exposure of the image capture system to illumination, during the capture frame, when the detected angular displacement of the image capture system is within the angular displacement threshold envelope, and control a level of exposure of the image capture system to illumination, during the capture frame, when the detected angular displacement is not within the angular displacement threshold envelope.

Abstract: A method for producing extreme ultraviolet light includes producing a target material at a target location; supplying pump energy to a gain medium of at least one optical amplifier that has an amplification band to produce an amplified light beam; propagating the amplified light beam through the gain medium using one or more optical components of a set of optical components; delivering the amplified light beam to the target location using one or more optical components of the optical component set; producing with a guide laser a guide laser beam that has a wavelength outside of the amplification band of the gain medium and inside the wavelength range of the optical components; and directing the guide laser beam through the optical component set to thereby align one or more optical components of the optical component set.

Abstract: An EUV light source device is described herein which may comprise a laser beam travelling along a beam path, at least a portion of the beam path aligned along a linear axis; a material for interaction with the laser beam at an irradiation site to create an EUV light emitting plasma; a first reflector having a focal point, the first reflector positioned with the focal point on the linear axis, the first reflector receiving laser light along the beam path; and a second reflector receiving laser light reflected by the first reflector and directing the laser light toward the irradiation site.

Abstract: A method for producing extreme ultraviolet light includes producing a target material at a target location; supplying pump energy to a gain medium of at least one optical amplifier that has an amplification band to produce an amplified light beam; propagating the amplified light beam through the gain medium using one or more optical components of a set of optical components; delivering the amplified light beam to the target location using one or more optical components of the optical component set; producing with a guide laser a guide laser beam that has a wavelength outside of the amplification band of the gain medium and inside the wavelength range of the optical components; and directing the guide laser beam through the optical component set to thereby align one or more optical components of the optical component set.

Abstract: An EUV light source device is described herein which may comprise a laser beam travelling along a beam path, at least a portion of the beam path aligned along a linear axis; a material for interaction with the laser beam at an irradiation site to create an EUV light emitting plasma; a first reflector having a focal point, the first reflector positioned with the focal point on the linear axis, the first reflector receiving laser light along the beam path; and a second reflector receiving laser light reflected by the first reflector and directing the laser light toward the irradiation site.