Abstract: Techniques are disclosed that enable the generation of predicted sequences of terminals using a generator model portion of a prediction model. Various implementations include controlling actuators of a robot based on the predicted sequences of terminals. Additional or alternative implementations include jointly training the generator model portion of the prediction model using a discriminator model portion of the prediction model using, for example, stochastic adversarial based sampling.

Abstract: Training and/or using both a high-level policy model and a low-level policy model for mobile robot navigation. High-level output generated using the high-level policy model at each iteration indicates a corresponding high-level action for robot movement in navigating to the navigation target. The low-level output generated at each iteration is based on the determined corresponding high-level action for that iteration, and is based on observation(s) for that iteration. The low-level policy model is trained to generate low-level output that defines low-level action(s) that define robot movement more granularly than the high-level action—and to generate low-level action(s) that avoid obstacles and/or that are efficient (e.g., distance and/or time efficiency).

Abstract: Training and/or using a machine learning model for performing robotic tasks is disclosed herein. In many implementations, an environment-conditioned action sequence prediction model is used to determine a set of actions as well as a corresponding particular order for the actions for the robot to perform to complete the task. In many implementations, each action in the set of actions has a corresponding action network used to control the robot in performing the action.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: Training and/or using a machine learning model for performing robotic tasks is disclosed herein. In many implementations, an environment-conditioned action sequence prediction model is used to determine a set of actions as well as a corresponding particular order for the actions for the robot to perform to complete the task. In many implementations, each action in the set of actions has a corresponding action network used to control the robot in performing the action.

Abstract: Training and/or using both a high-level policy model and a low-level policy model for mobile robot navigation. High-level output generated using the high-level policy model at each iteration indicates a corresponding high-level action for robot movement in navigating to the navigation target. The low-level output generated at each iteration is based on the determined corresponding high-level action for that iteration, and is based on observation(s) for that iteration. The low-level policy model is trained to generate low-level output that defines low-level action(s) that define robot movement more granularly than the high-level action—and to generate low-level action(s) that avoid obstacles and/or that are efficient (e.g., distance and/or time efficiency).

Abstract: Training and/or utilizing a high-level neural network (NN) model, such as a sequential NN model. The high-level NN model, when trained, can be used to process a sequence of consecutive state data instances (e.g., N most recent, including a current state date instance) to generate a sequence of outputs that indicate a sequence of position deltas. The sequence of position deltas can be used to generate an intermediate target position for navigation and, optionally, an intermediate target orientation that corresponds to the intermediate target position. The intermediate target position and, optionally, the intermediate target orientation, can be provided to a low-level navigation policy, such as an MPC policy, and used by the low-level navigation policy as its goal position (and optionally goal orientation) for a plurality of iterations (e.g., until a new intermediate target position (and optionally new target orientation) is generated using the high-level NN model.

Abstract: Training and/or using a recurrent neural network model for visual servoing of an end effector of a robot. In visual servoing, the model can be utilized to generate, at each of a plurality of time steps, an action prediction that represents a prediction of how the end effector should be moved to cause the end effector to move toward a target object. The model can be viewpoint invariant in that it can be utilized across a variety of robots having vision components at a variety of viewpoints and/or can be utilized for a single robot even when a viewpoint, of a vision component of the robot, is drastically altered. Moreover, the model can be trained based on a large quantity of simulated data that is based on simulator(s) performing simulated episode(s) in view of the model. One or more portions of the model can be further trained based on a relatively smaller quantity of real training data.

Abstract: Implementations process, using a large language model, a free-form natural language (NL) instruction to generate to generate LLM output. Those implementations generate, based on the LLM output and a NL skill description of a robotic skill, a task-grounding measure that reflects a probability of the skill description in the probability distribution of the LLM output. Those implementations further generate, based on the robotic skill and current environmental state data, a world-grounding measure that reflects a probability of the robotic skill being successful based on the current environmental state data. Those implementations further determine, based on both the task-grounding measure and the world-grounding measure, whether to implement the robotic skill.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: Training and/or using a recurrent neural network model for visual servoing of an end effector of a robot. In visual servoing, the model can be utilized to generate, at each of a plurality of time steps, an action prediction that represents a prediction of how the end effector should be moved to cause the end effector to move toward a target object. The model can be viewpoint invariant in that it can be utilized across a variety of robots having vision components at a variety of viewpoints and/or can be utilized for a single robot even when a viewpoint, of a vision component of the robot, is drastically altered. Moreover, the model can be trained based on a large quantity of simulated data that is based on simulator(s) performing simulated episode(s) in view of the model. One or more portions of the model can be further trained based on a relatively smaller quantity of real training data.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: Training and/or using a machine learning model for performing robotic tasks is disclosed herein. In many implementations, an environment-conditioned action sequence prediction model is used to determine a set of actions as well as a corresponding particular order for the actions for the robot to perform to complete the task. In many implementations, each action in the set of actions has a corresponding action network used to control the robot in performing the action.

Abstract: Techniques are disclosed that enable the generation of predicted sequences of terminals using a generator model portion of a prediction model. Various implementations include controlling actuators of a robot based on the predicted sequences of terminals. Additional or alternative implementations include jointly training the generator model portion of the prediction model using a discriminator model portion of the prediction model using, for example, stochastic adversarial based sampling.

Abstract: Training and/or using both a high-level policy model and a low-level policy model for mobile robot navigation. High-level output generated using the high-level policy model at each iteration indicates a corresponding high-level action for robot movement in navigating to the navigation target. The low-level output generated at each iteration is based on the determined corresponding high-level action for that iteration, and is based on observation(s) for that iteration. The low-level policy model is trained to generate low-level output that defines low-level action(s) that define robot movement more granularly than the high-level action—and to generate low-level action(s) that avoid obstacles and/or that are efficient (e.g., distance and/or time efficiency).

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: Training and/or using a recurrent neural network model for visual servoing of an end effector of a robot. In visual servoing, the model can be utilized to generate, at each of a plurality of time steps, an action prediction that represents a prediction of how the end effector should be moved to cause the end effector to move toward a target object. The model can be viewpoint invariant in that it can be utilized across a variety of robots having vision components at a variety of viewpoints and/or can be utilized for a single robot even when a viewpoint, of a vision component of the robot, is drastically altered. Moreover, the model can be trained based on a large quantity of simulated data that is based on simulator(s) performing simulated episode(s) in view of the model. One or more portions of the model can be further trained based on a relatively smaller quantity of real training data.

Abstract: The present disclosure provides systems and methods that enable distance metric learning using proxies. A machine-learned distance model can be trained in a proxy space in which a loss function compares an embedding provided for an anchor data point of a training dataset to a positive proxy and one or more negative proxies, where each of the positive proxy and the one or more negative proxies serve as a proxy for two or more data points included in the training dataset. Thus, each proxy can approximate a number of data points, enabling faster convergence. According to another aspect, the proxies of the proxy space can themselves be learned parameters, such that the proxies and the model are trained jointly. Thus, the present disclosure enables faster convergence (e.g., reduced training time). The present disclosure provides example experiments which demonstrate a new state of the art on several popular training datasets.