Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.

Abstract: A system for imaging at least one of a trailer or other conveyance that is connected to a tractor and an environment proximate the tractor, wherein the trailer or other conveyance has two opposed lateral sides, the system comprising a plurality of sensors mounted to the tractor, wherein the sensors together have an active sensing area that encompasses at least the two opposed lateral sides of the trailer or other conveyance.

Abstract: Techniques for safe non-conservative planning include: obtaining a risk budget constraining a plan for an autonomous vehicle to satisfy an objective; based at least on the risk budget and the objective, planning a trajectory of the autonomous vehicle toward the objective, at least by: (a) determining a risk cost associated with an initial planned action of the trajectory, (b) based at least on the risk cost, determining whether the trajectory is feasible or infeasible within the risk budget, and (c) responsive to determining that the trajectory is feasible within the risk budget, executing the initial planned action; decreasing the risk budget by the risk cost, to obtain a remaining risk budget; obtaining state data corresponding to a state of the autonomous vehicle after executing the initial planned action; and based at least on the state data, the remaining risk budget, and the objective, planning another trajectory toward the objective.

Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.

Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.

Abstract: Techniques for safe non-conservative planning include: obtaining a risk budget constraining a plan for an autonomous vehicle to satisfy an objective; based at least on the risk budget and the objective, planning a trajectory of the autonomous vehicle toward the objective, at least by: (a) determining a risk cost associated with an initial planned action of the trajectory, (b) based at least on the risk cost, determining whether the trajectory is feasible or infeasible within the risk budget, and (c) responsive to determining that the trajectory is feasible within the risk budget, executing the initial planned action; decreasing the risk budget by the risk cost, to obtain a remaining risk budget; obtaining state data corresponding to a state of the autonomous vehicle after executing the initial planned action; and based at least on the state data, the remaining risk budget, and the objective, planning another trajectory toward the objective.

Abstract: Techniques for latent belief space planning include: during execution of an autonomous agent configured to control operation of a physical mechanism, obtaining a current observation of a physical environment; based at least on the current observation of the physical environment, generating a trajectory tree that represents possible trajectories in a belief space, wherein nodes of the trajectory tree represent values of a continuous observation, a continuous state, and a continuous control, each node being associated with one of multiple timesteps along the plurality of possible trajectories, and wherein branches from inner nodes to child nodes correspond to possible outcomes and observations of a multi-modal latent state; determining a current value of the continuous control associated with a current node; and applying the current value of the continuous control to operation of the physical mechanism.

Abstract: A method of instance segmentation in an image and a system for instance segmentation of images. The method includes identifying, with a processor, a starting pixel associated with an object in an image, the image having a plurality of rows of pixels, the starting pixel located in a row of the plurality of rows; identifying, with the processor, at least one pixel located in an adjacent row to the row in which the starting pixel is located, the at least one pixel being part of the same object as the starting pixel; iterating the previous two identification steps using the at least one identified adjacent row pixel as a start pixel for the next iteration; and connecting, with the processor, the at least one identified adjacent row pixels to form polylines representing the object.

Abstract: Laser-enhanced visual simultaneous localization and mapping (SLAM) is disclosed. A laser line is generated, the laser line being incident on an object and/or environment. While the laser line is incident on the object, one or more images of the object with the laser line incident on the object are captured. The camera is localized based on one or more characteristics of the laser line incident on the object. In some examples, improved feature localization provided by the laser line provides more accurate camera localization, which, in turn, improves the accuracy of the stitched mesh of the object/environment. As such, the examples of the disclosure provide for improved camera localization and improved three-dimensional mapping.