Abstract: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.

Abstract: A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.

Abstract: Training and/or utilizing a hierarchical reinforcement learning (HRL) model for robotic control. The HRL model can include at least a higher-level policy model and a lower-level policy model. Some implementations relate to technique(s) that enable more efficient off-policy training to be utilized in training of the higher-level policy model and/or the lower-level policy model. Some of those implementations utilize off-policy correction, which re-labels higher-level actions of experience data, generated in the past utilizing a previously trained version of the HRL model, with modified higher-level actions. The modified higher-level actions are then utilized to off-policy train the higher-level policy model. This can enable effective off-policy training despite the lower-level policy model being a different version at training time (relative to the version when the experience data was collected).

Abstract: Techniques are disclosed that enable training a meta-learning model, for use in causing a robot to perform a task, using imitation learning as well as reinforcement learning. Some implementations relate to training the meta-learning model using imitation learning based on one or more human guided demonstrations of the task. Additional or alternative implementations relate to training the meta-learning model using reinforcement learning based on trials of the robot attempting to perform the task. Further implementations relate to using the trained meta-learning model to few shot (or one shot) learn a new task based on a human guided demonstration of the new task.

Abstract: Techniques are disclosed that enable training a plurality of policy networks, each policy network corresponding to a disparate robotic training task, using a mobile robot in a real world workspace. Various implementations include selecting a training task based on comparing a pose of the mobile robot to at least one parameter of a real world training workspace. For example, the training task can be selected based on the position of a landmark, within the workspace, relative to the pose. For instance, the training task can be selected such that the selected training task moves the mobile robot towards the landmark.

Abstract: Training and/or utilizing a hierarchical reinforcement learning (HRL) model for robotic control. The HRL model can include at least a higher-level policy model and a lower-level policy model. Some implementations relate to technique(s) that enable more efficient off-policy training to be utilized in training of the higher-level policy model and/or the lower-level policy model. Some of those implementations utilize off-policy correction, which re-labels higher-level actions of experience data, generated in the past utilizing a previously trained version of the HRL model, with modified higher-level actions. The modified higher-level actions are then utilized to off-policy train the higher-level policy model. This can enable effective off-policy training despite the lower-level policy model being a different version at training time (relative to the version when the experience data was collected).

Abstract: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

Abstract: Implementations disclosed herein relate to mitigating the reality gap through training a simulation-to-real machine learning model (“Sim2Real” model) using a vision-based robot task machine learning model. The vision-based robot task machine learning model can be, for example, a reinforcement learning (“RL”) neural network model (RL-network), such as an RL-network that represents a Q-function.

Abstract: Implementations utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

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 utilize deep reinforcement learning to train a policy neural network that parameterizes a policy for determining a robotic action based on a current state. Some of those implementations collect experience data from multiple robots that operate simultaneously. Each robot generates instances of experience data during iterative performance of episodes that are each explorations of performing a task, and that are each guided based on the policy network and the current policy parameters for the policy network during the episode. The collected experience data is generated during the episodes and is used to train the policy network by iteratively updating policy parameters of the policy network based on a batch of collected experience data. Further, prior to performance of each of a plurality of episodes performed by the robots, the current updated policy parameters can be provided (or retrieved) for utilization in performance of the episode.

Abstract: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.

Abstract: A method includes determining a first state associated with a particular task, and determining, by a task policy model, a latent space representation of the first state. The task policy model may have been trained to define, for each respective state of a plurality of possible states associated with the particular task, a corresponding latent space representation of the respective state. The method also includes determining, by a primitive policy model and based on the first state and the latent space representation of the first state, an action to take as part of the particular task. The primitive policy model may have been trained to define a space of primitive policies for the plurality of possible states associated with the particular task and a plurality of possible latent space representations. The method further includes executing the action to reach a second state associated with the particular task.

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: Implementations described herein relate to training and refining robotic control policies using imitation learning techniques. A robotic control policy can be initially trained based on human demonstrations of various robotic tasks. Further, the robotic control policy can be refined based on human interventions while a robot is performing a robotic task. In some implementations, the robotic control policy may determine whether the robot will fail in performance of the robotic task, and prompt a human to intervene in performance of the robotic task. In additional or alternative implementations, a representation of the sequence of actions can be visually rendered for presentation to the human can proactively intervene in performance of the robotic task.

Abstract: Deep machine learning methods and apparatus related to semantic robotic grasping are provided. Some implementations relate to training a training a grasp neural network, a semantic neural network, and a joint neural network of a semantic grasping model. In some of those implementations, the joint network is a deep neural network and can be trained based on both: grasp losses generated based on grasp predictions generated over a grasp neural network, and semantic losses generated based on semantic predictions generated over the semantic neural network. Some implementations are directed to utilization of the trained semantic grasping model to servo, or control, a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).

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: Deep machine learning methods and apparatus related to manipulation of an object by an end effector of a robot. Some implementations relate to training a deep neural network to predict a measure that candidate motion data for an end effector of a robot will result in a successful grasp of one or more objects by the end effector. Some implementations are directed to utilization of the trained deep neural network to servo a grasping end effector of a robot to achieve a successful grasp of an object by the grasping end effector. For example, the trained deep neural network may be utilized in the iterative updating of motion control commands for one or more actuators of a robot that control the pose of a grasping end effector of the robot, and to determine when to generate grasping control commands to effectuate an attempted grasp by the grasping end effector.

Abstract: A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.