Abstract: A vehicle including a plurality of first motorized tiles and a vehicle elevator is disclosed. The plurality of first motorized tiles may be disposed in a vehicle interior portion. The plurality of first motorized tiles may be configured to move and secure a first bin of a first size and a second bin of a second size. The vehicle elevator may include a second motorized tile and a set of third motorized tiles. The second motorized tile may be configured to receive the second bin from the plurality of first motorized tiles and secure the second bin. The second motorized tile may be of a third size. Further, each third motorized tile may be configured to receive the first bin from the plurality of first motorized tiles and secure the first bin. Each third motorized tile may be of a fourth size.

Abstract: A vehicle including a transceiver, a control unit and a processor is disclosed. The transceiver may be configured to receive inventory information from a server. The inventory information may include a plurality of delivery addresses associated with a plurality of packages disposed in the vehicle. The control unit may be configured to determine vehicle information. The processor may be configured to determine that a predefined condition may be met based on the inventory information and the vehicle information. The processor may further generate a geofence for each delivery address based on the vehicle information, responsive to determining that the predefined condition may be met. Furthermore, the processor may determine that the vehicle may have entered the geofence based on the vehicle information. The processor may perform a predefined action responsive to determining that the vehicle may have entered the geofence.

Abstract: A method includes generating a workspace model having one or more digital robots, one or more digital sensors, and a digital transport system. The method includes simulating, for a task of the one or more digital robots, a sensor operation of the one or more digital sensors within the workspace model based on sensor characteristics of the one or more digital sensors. The method includes identifying, for the task of the one or more digital robots, an undetectable area within the workspace model based on the simulated sensor operation. The method includes selectively positioning, by a transport system, a set of sensors from among the one or more sensors based on the undetectable areas associated with the task.

Abstract: A vehicle for package delivery is provided. The vehicle includes one or more processors; a tile floor system connected to the one or more processors, the tile floor system comprising a plurality of tiles with actuators that individually move containers thereon, and in a first arrangement a first tile is associated with a first container; at least one imaging device; and a memory. The processors determine an identifier for a package, receive first image data associated with the package from the imaging device, determine a first association of the package with the first container based on the first image data, determine a first delivery route that includes a first stop associated with the identifier for the package, and rearrange the containers by the tile floor system into a second arrangement based on the first delivery route prior to the first stop of the first delivery route.

Abstract: A system for detecting a road surface includes a processor programmed to identify, in a vehicle sensor field of view, environment features including a sky, a road surface, a road shoulder, based on map data and data received from the one or more vehicle sensors, upon determining a low confidence in identifying an area of the field of view to be a road surface or sky, to receive a polarimetric image, and to determine, based on the received polarimetric image, whether the identified area is a mirage phenomenon, a wet road surface, or the sky. The low confidence is determined upon determining that a road surface has a vanishing edge, a road lane marker is missing, or an anomalous object is present.

Abstract: A method includes generating a workspace model having one or more digital robots, one or more digital sensors, and a digital transport system. The method includes simulating, for a task of the one or more digital robots, a sensor operation of the one or more digital sensors within the workspace model based on sensor characteristics of the one or more digital sensors. The method includes identifying, for the task of the one or more digital robots, an undetectable area within the workspace model based on the simulated sensor operation. The method includes selectively positioning, by a transport system, a set of sensors from among the one or more sensors based on the undetectable areas associated with the task.

Abstract: Disclosed is an end-to-end delivery system that uses standard containers designed for autonomous vehicle (AV) goods delivery, a purpose-built AV cargo management system, a purpose-built robot to load and unload packages, and software to coordinate the various tasks involved. The standard containers may include a hardware locking interface for locking to a carrying robot. The cargo management system may include a programmable conveyor system installed on each floor of a multi-floor cargo space within the AV. For example, the floor may include a roller surface to allow omnidirectional routing of packages. An elevator shaft may be used for receiving and off-loading containers. The software may identify a target container anywhere within the multi-floor cargo space, and determine how to rearrange the containers within a grid in the AV so that the target container may be moved to the elevator shaft for unloading.

Abstract: Building infrastructure and robot coordination methods and systems are disclosed herein. An example method can include preregistering an autonomous vehicle with a building controller of a building to inform the building controller of arrival of the autonomous vehicle and a delivery request for a package, the delivery request specifying a recipient of the package, the recipient having a location in the building. The method can include determining completion of a validation routine with the autonomous vehicle, assigning a task management plan to the autonomous vehicle, the task management plan determining how the autonomous vehicle navigates through the building to deliver the package to the location, and tracking the autonomous vehicle through the building.

Abstract: A method for controlling a human driven vehicle (HDV) includes identifying HDV indicia of a fiducial marker disposed on the HDV based on localization data obtained from the plurality of localization sensors, determining a pose of the HDV based on the localization data, where the pose of the HDV includes a location and an orientation of the HDV, and defining a bounding region of the HDV based on the HDV indicia and the pose of the HDV. The method includes determining a location-based characteristic of the one or more autonomous devices, where the location-based characteristic includes a location of the one or more autonomous devices, a trajectory of the one or more autonomous devices, or a combination thereof, selectively generating a notification based on the location-based characteristic and the bounding region, and broadcasting the notification to the HDV in response to generating the notification.

Abstract: A method includes identifying a set of intermediate grids of a grid map of the manufacturing environment based on a location of the first AMR and a destination grid of the grid map and appending temporal information to the set of intermediate grids based on a mobility characteristic of the first AMR. The method includes generating a first reservation based on the set of intermediate grids and the temporal information of the set of intermediate grids, determining a state of the first reservation based on priority information associated with the plurality of AMRs and one or more additional reservations associated with the one or more additional AMRs from among the plurality of AMRs, and assigning the first reservation to the first AMR in response to the first reservation being in an available state.

Abstract: A method for controlling a plurality of autonomous mobile robots (AMRs) in a manufacturing environment having an intersection includes obtaining a plurality of routes associated with the plurality of AMRs, velocity information associated with the plurality of AMRs, and priority information associated with the plurality of AMRs, and determining a plurality of arrival times associated with the plurality of AMRs based on the velocity information and the plurality of routes. The method includes generating a plurality of intersection reservations based on the plurality of arrival times and the priority information, where each intersection reservation from among the plurality of intersection reservations corresponds to an AMR from among the plurality of AMRs, and controlling a movement of the plurality of AMRs through the intersection based on the plurality of intersection reservations.

Abstract: A system for detecting a road surface includes a processor programmed to identify, in a vehicle sensor field of view, environment features including a sky, a road surface, a road shoulder, based on map data and data received from the one or more vehicle sensors, upon determining a low confidence in identifying an area of the field of view to be a road surface or sky, to receive a polarimetric image, and to determine, based on the received polarimetric image, whether the identified area is a mirage phenomenon, a wet road surface, or the sky. The low confidence is determined upon determining that a road surface has a vanishing edge, a road lane marker is missing, or an anomalous object is present.

Abstract: Systems and methods for delivering a package to a curbside receptacle are provided. A delivery window of a vehicle may be aligned with a curbside receptacle. A carousel within the vehicle may be moved, e.g., rotated, within the vehicle to align a target compartment with the delivery window. A conveyor arm slidably coupled to the delivery window is then extended and aligned with the target compartment, and a target package within the target compartment is ejected from the target compartment onto the conveyor arm, e.g., via a plunger mechanism. The conveyor arm then transfers the target package to curbside receptacle.

Abstract: This disclosure describes systems, methods, and devices related to automatic annotation. A device may capture data associated with an image comprising an object. The device may acquire input data associated with the object. The device may estimate a plurality of points within a frame of the image, wherein the plurality of point constitute a 3D bounding to around the object. The device may transform the plurality of points to two or more 2D points. The device may construct a bounding box that encapsulates the object using the two or more 2D points. The device may create a segmentation mask of the object using morphological techniques. The device may perform annotation based on the segmentation mask.

Abstract: A method includes generating a workspace model having one or more digital robots, one or more digital sensors, and a digital transport system. The method includes simulating, for a task of the one or more digital robots, a sensor operation of the one or more digital sensors within the workspace model based on sensor characteristics of the one or more digital sensors. The method includes identifying, for the task of the one or more digital robots, an undetectable area within the workspace model based on the simulated sensor operation. The method includes selectively positioning, by a transport system, a set of sensors from among the one or more sensors based on the undetectable areas associated with the task.

Abstract: Disclosed is an end-to-end delivery system that uses standard containers designed for autonomous vehicle (AV) goods delivery, a purpose-built AV cargo management system, a purpose-built robot to load and unload packages, and software to coordinate the various tasks involved. The standard containers may include a hardware locking interface for locking to a carrying robot. The cargo management system may include a programmable conveyor system installed on each floor of a multi-floor cargo space within the AV. For example, the floor may include a roller surface to allow omnidirectional routing of packages. An elevator shaft may be used for receiving and off-loading containers. The software may identify a target container anywhere within the multi-floor cargo space, and determine how to rearrange the containers within a grid in the AV so that the target container may be moved to the elevator shaft for unloading.

Abstract: Systems and methods for delivering a package to a curbside receptacle are provided. A delivery window of a vehicle may be aligned with a curbside receptacle. A carousel within the vehicle may be moved. e.g., rotated, within the vehicle to align a target compartment with the delivery window. A conveyor arm slidably coupled to the delivery window is then extended and aligned with the target compartment, and a target package within the target compartment is ejected from the target compartment onto the conveyor arm, e.g., via a plunger mechanism. The conveyor arm then transfers the target package to curbside receptacle.

Abstract: A first distance d1 between a vehicle at a first location and an object is determined. A best fit line representing the object is determined from a plurality of sensor data. A distance ?d to move to a second location is specified. A predicted second distance dp between the vehicle at the second location and the object is determined based on the first distance d1, the distance ?d, and the best fit line. The vehicle is operated from the first location to the second location based on a center steering wheel angle. A measured second distance d2 between the vehicle at the second location and object is determined. Then the center steering wheel angle is one of (a) maintained based on the predicted second distance dp matching the measured second distance d2, or (b) updated based on the predicted second distance dp being different than the measured second distance d2.

Abstract: A first distance d1 between a vehicle at a first location and an object is determined. A best fit line representing the object is determined from a plurality of sensor data. A distance ?d to move to a second location is specified. A predicted second distance dp between the vehicle at the second location and the object is determined based on the first distance d1, the distance ?d, and the best fit line. The vehicle is operated from the first location to the second location based on a center steering wheel angle. A measured second distance d2 between the vehicle at the second location and object is determined. Then the center steering wheel angle is one of (a) maintained based on the predicted second distance dp matching the measured second distance d2, or (b) updated based on the predicted second distance dp being different than the measured second distance d2.