Abstract: A method of constrained mobility mapping includes receiving from at least one sensor of a robot at least one original set of sensor data and a current set of sensor data. Here, each of the at least one original set of sensor data and the current set of sensor data corresponds to an environment about the robot. The method further includes generating a voxel map including a plurality of voxels based on the at least one original set of sensor data. The plurality of voxels includes at least one ground voxel and at least one obstacle voxel. The method also includes generating a spherical depth map based on the current set of sensor data and determining that a change has occurred to an obstacle represented by the voxel map based on a comparison between the voxel map and the spherical depth map. The method additional includes updating the voxel map to reflect the change to the obstacle.

Abstract: A method of constrained mobility mapping includes receiving from at least one sensor of a robot at least one original set of sensor data and a current set of sensor data. Here, each of the at least one original set of sensor data and the current set of sensor data corresponds to an environment about the robot. The method further includes generating a voxel map including a plurality of voxels based on the at least one original set of sensor data. The plurality of voxels includes at least one ground voxel and at least one obstacle voxel. The method also includes generating a spherical depth map based on the current set of sensor data and determining that a change has occurred to an obstacle represented by the voxel map based on a comparison between the voxel map and the spherical depth map. The method additional includes updating the voxel map to reflect the change to the obstacle.

Abstract: A method of constrained mobility mapping includes receiving from at least one sensor of a robot at least one original set of sensor data and a current set of sensor data. Here, each of the at least one original set of sensor data and the current set of sensor data corresponds to an environment about the robot. The method further includes generating a voxel map including a plurality of voxels based on the at least one original set of sensor data. The plurality of voxels includes at least one ground voxel and at least one obstacle voxel. The method also includes generating a spherical depth map based on the current set of sensor data and determining that a change has occurred to an obstacle represented by the voxel map based on a comparison between the voxel map and the spherical depth map. The method additional includes updating the voxel map to reflect the change to the obstacle.

Abstract: The present disclosure relates to methods and systems for robust robotic task execution. An example method includes obtaining a task-level goal for a robot associated with one or more sub-goals, where accomplishment of the one or more sub-goals accomplishes the task-level goal. Carrying out an operation in pursuance of a given sub-goal may involve controlling at least one actuator of the robot. The method also includes determining one or more parameters indicative of a state of a system that includes the robot and an environment proximate to the robot. The method further includes selecting a particular sub-goal based on at least one of the one or more parameters. Additionally, the method includes selecting at least one controller based on at least one of the one or more parameters and the selected sub-goal. Further, the method includes causing the robot to operate in accordance with the at least one selected controller.

Abstract: The present disclosure relates to methods and systems for improving robotic task selection and execution. An example method includes determining an external environment state based on receiving information indicative of at least one aspect of an environment proximate to a robotic system having at least one actuator. The method also includes optionally determining a goal to be accomplished by a robotic system and determining a plurality of possible tasks each including at least one task involving the at least one actuator that may be carried out by the robotic system in pursuance of the goal. For each possible task group, the method includes determining a respective task group score based on an expected performance capability. The expected performance capability is based, at least in part, on the external environment state. The method includes selecting a task group based on the respective task group scores.

Abstract: Example systems and methods for self-righting a robotic device are provided. An example method may include determining an orientation of a bottom surface of a legged robotic device with respect to a ground surface. The method may also include determining that the robotic device is in an unstable position, based on the determined orientation. The method may also include performing a first action configured to return the robotic device to a stable position. The method may also include performing a first action configured to return the legged robotic device to the stable position. The method may also include performing a second action configured to return the legged robotic device to the stable position, if the legged robotic device is in the unstable position after the first action.

Abstract: Example systems and methods for self-righting a robotic device are provided. An example method may include determining an orientation of a bottom surface of a legged robotic device with respect to a ground surface. The method may also include determining that the robotic device is in an unstable position, based on the determined orientation. The method may also include performing a first action configured to return the robotic device to a stable position. The method may also include performing a first action configured to return the legged robotic device to the stable position. The method may also include performing a second action configured to return the legged robotic device to the stable position, if the legged robotic device is in the unstable position after the first action.

Abstract: Example systems and methods for self-righting a robotic device are provided. An example method may include determining an orientation of a bottom surface of a legged robotic device with respect to a ground surface. The method may also include determining that the robotic device is in an unstable position, based on the determined orientation. The method may also include performing a first action configured to return the robotic device to a stable position. The method may also include performing a first action configured to return the legged robotic device to the stable position. The method may also include performing a second action configured to return the legged robotic device to the stable position, if the legged robotic device is in the unstable position after the first action.