Abstract: Methods, apparatus, systems, and computer-readable media are provided that relate to using one or more vision sensors to capture images of a loaded pallet in association with application of stretch wrap to the loaded pallet by an automated pallet wrapping machine. The images are used to generate an image-based identifier for the loaded pallet that is then used for pallet identification by mobile robots and/or other automated agents in a warehouse or other environment. In some implementations, the images are captured by the vision sensor when the pallet is in the wrapping area of the automated pallet wrapping machine and while the vision sensor and/or the pallet are rotating. In some implementations, the image-based identifier may be assigned to pallet attributes and/or a de-palletizing scheme of the loaded pallet.

Abstract: Methods, apparatus, systems, and computer-readable media are provided that relate to using one or more vision sensors to capture images of a loaded pallet in association with application of stretch wrap to the loaded pallet by an automated pallet wrapping machine. The images are used to generate an image-based identifier for the loaded pallet that is then used for pallet identification by mobile robots and/or other automated agents in a warehouse or other environment. In some implementations, the images are captured by the vision sensor when the pallet is in the wrapping area of the automated pallet wrapping machine and while the vision sensor and/or the pallet are rotating. In some implementations, the image-based identifier may be assigned to pallet attributes and/or a de-palletizing scheme of the loaded pallet.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for spatiotemporal reservations for robots. In various implementations, a sequence of spatial regions of an environment, and a sequence of respective time intervals that are reserved for a robot to operate within the sequence of spatial regions, may be reserved for the robot. A default path through the sequence of spatial regions may be identified. During traversal of the default path, it may be determined that the default path will be unpassable by the robot through a given spatial region during a given time interval reserved for the robot to operate within the given spatial region. Thus, an alternative path through the given spatial region that is traversable by the robot during the given time interval may be identified. The robot may then be traversed along the alternative path through the given spatial region within the given time interval.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for generating and using a spatio-temporal model that defines pose values for a plurality of objects in an environment and corresponding times associated with the pose values. Some implementations relate to using observations for one or more robots in an environment to generate a spatio-temporal model that defines pose values and corresponding times for multiple objects in the environment. In some of those implementations, the model is generated based on uncertainty measures associated with the pose values. Some implementations relate to utilizing a generated spatio-temporal model to determine the pose for each of one or more objects an environment at a target time. The pose for an object at a target time is determined based on one or more pose values for the object selected based on a corresponding measurement time, uncertainty measure, and/or source associated with the pose values.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for spatiotemporal reservations for robots. In various implementations, a sequence of spatial regions of an environment, and a sequence of respective time intervals that are reserved for a robot to operate within the sequence of spatial regions, may be reserved for the robot. A default path through the sequence of spatial regions may be identified. During traversal of the default path, it may be determined that the default path will be unpassable by the robot through a given spatial region during a given time interval reserved for the robot to operate within the given spatial region. Thus, an alternative path through the given spatial region that is traversable by the robot during the given time interval may be identified. The robot may then be traversed along the alternative path through the given spatial region within the given time interval.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for generating and using a spatio-temporal model that defines pose values for a plurality of objects in an environment and corresponding times associated with the pose values. Some implementations relate to using observations for one or more robots in an environment to generate a spatio-temporal model that defines pose values and corresponding times for multiple objects in the environment. In some of those implementations, the model is generated based on uncertainty measures associated with the pose values. Some implementations relate to utilizing a generated spatio-temporal model to determine the pose for each of one or more objects an environment at a target time. The pose for an object at a target time is determined based on one or more pose values for the object selected based on a corresponding measurement time, uncertainty measure, and/or source associated with the pose values.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for selectively deploying robots to performing mapping based on added cost. In various implementations, a measure of interest in mapping an area of an environment may be determined. A cost associated with a robot performing a task may also be determined. Then, an added cost associated with the robot mapping the area of the environment while performing the task may be determined. The robot may be selectively deployed to map the area while performing the task in response to a determination that the measure of interest justifies the added cost.

Abstract: Systems and methods are provided for generating maps with semantic labels. A computing device can determine a first map that includes features located at first positions and semantic labels located at semantic positions, and determine a second map that includes at least some of the features located at second positions. The computing device can identify a first region with fixed features located at first positions and corresponding equivalent second positions. The computing device can identify a second region with moved features located at first positions and corresponding non-equivalent second positions. The computing device can determine one or more transformations between first positions and second positions. The computing device can assign the semantic labels to the second map at second semantic positions, where the second semantic positions are the same in the first region, and where the second semantic positions in the second region are based on the transformation(s).

Abstract: Systems and methods are provided for generating maps with semantic labels. A computing device can determine a first map that includes features located at first positions and semantic labels located at semantic positions, and determine a second map that includes at least some of the features located at second positions. The computing device can identify a first region with fixed features located at first positions and corresponding equivalent second positions. The computing device can identify a second region with moved features located at first positions and corresponding non-equivalent second positions. The computing device can determine one or more transformations between first positions and second positions. The computing device can assign the semantic labels to the second map at second semantic positions, where the second semantic positions are the same in the first region, and where the second semantic positions in the second region are based on the transformation(s).