Abstract: Methods for performing a calibration process for outward-facing cameras on devices such as head-mounted display devices are disclosed. Extrinsic parameters of the camera are first estimated using inputs to the calibration process such as information from an inertial measurement unit and points of interest within images captured by the camera that are tracked with time. Then, extrinsic and intrinsic parameters are concurrently determined in an optimization problem such that updated values of said parameters may be stored and used by applications that run on the device and make use of the camera. The calibration process may be extended to concurrently calibrate multiple cameras based, at least in part, on information from the inertial measurement unit that is local to the camera.

Abstract: Disclosed are techniques for employing deep learning to analyze radar signals. In an aspect, an on-board computer of a host vehicle receives, from a radar sensor of the vehicle, a plurality of radar frames, executes a neural network on a subset of the plurality of radar frames, and detects one or more objects in the subset of the plurality of radar frames based on execution of the neural network on the subset of the plurality of radar frames. Further, techniques for transforming polar coordinates to Cartesian coordinates in a neural network are disclosed. In an aspect, a neural network receives a plurality of radar frames in polar coordinate space, a polar-to-Cartesian transformation layer of the neural network transforms the plurality of radar frames to Cartesian coordinate space, and the neural network outputs the plurality of radar frames in the Cartesian coordinate space.

Abstract: Disclosed are techniques for fusing camera and radar frames to perform object detection in one or more spatial domains. In an aspect, an on-board computer of a host vehicle receives, from a camera sensor of the host vehicle, a plurality of camera frames, receives, from a radar sensor of the host vehicle, a plurality of radar frames, performs a camera feature extraction process on a first camera frame of the plurality of camera frames to generate a first camera feature map, performs a radar feature extraction process on a first radar frame of the plurality of radar frames to generate a first radar feature map, converts the first camera feature map and/or the first radar feature map to a common spatial domain, and concatenates the first radar feature map and the first camera feature map to generate a first concatenated feature map in the common spatial domain.

Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.

Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.

Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.

Abstract: Methods of processing vehicle sensor information for object detection may include capturing generating a feature map based on captured sensor information, associating with each pixel of the feature map a prior box having a set of two or more width priors and a set of two or more height priors, determining a confidence value of each height prior and each width prior, outputting an indication of a detected object based on a highest confidence height prior and a highest confidence width prior, and performing a vehicle operation based on the output indication of a detected object. Embodiments may include determining for each pixel of the feature map one or more prior boxes having a center value, a size value, and a set of orientation priors, determining a confidence value for each orientation prior, and outputting an indication of the orientation of a detected object based on the highest confidence orientation.

Abstract: A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.

Abstract: A method performed by an apparatus is described. The method includes receiving a first set of object data corresponding to a first journey. The method also includes receiving a second set of object data corresponding to a second journey. The method further includes determining a similarity metric between the first set of object data and the second set of object data. The similarity metric indicates a distance between the first set of object data and the second set of object data for at least one object. The method additionally includes clustering the first set of object data and the second set of object data for the at least one object based on the similarity metric to produce at least one object cluster. The method also includes producing map data based on the at least one object cluster.

Abstract: Techniques and devices are described for wireless communication. A base station may determine a parameter associated with a transmission such as hybrid automatic repeat request (HARQ) feedback, a signal-to-noise ratio, or a determination regarding whether the transmission was successfully decoded. The base station may then determine a contention window adjustment value based on the parameter. The base station may then apply weighting factor (e.g., based on the time of the transmission, a number of devices being served, aspects of the transmission parameter, etc.) to the contention window adjustment value may adjust a contention window size for a second transmission based on the weighted contention window adjustment value (and, in some cases, other weighted adjustments based on other transmissions). The base station may then perform a clear channel assessment (CCA) based on the contention window size.

Abstract: Disclosed are techniques for employing deep learning to analyze radar signals. In an aspect, an on-board computer of a host vehicle receives, from a radar sensor of the vehicle, a plurality of radar frames, executes a neural network on a subset of the plurality of radar frames, and detects one or more objects in the subset of the plurality of radar frames based on execution of the neural network on the subset of the plurality of radar frames. Further, techniques for transforming polar coordinates to Cartesian coordinates in a neural network are disclosed. In an aspect, a neural network receives a plurality of radar frames in polar coordinate space, a polar-to-Cartesian transformation layer of the neural network transforms the plurality of radar frames to Cartesian coordinate space, and the neural network outputs the plurality of radar frames in the Cartesian coordinate space.

Abstract: Various aspects related to techniques for harmonization between common reference signal (CRS) and demodulation reference signal (DM-RS) based transmission modes (TMs) in unlicensed spectrum are described. In one aspect, a downlink/uplink (DL/UL) subframe configuration may be signaled for each subframe. Information provided by the DL/UL subframe configuration may indicate whether the respective downlink subframe is a single-frequency network (MBSFN) subframe (associated with DM-RS-based TM) or a non-MBSFN subframe (associated with CRS-based TM). In another aspect, periodic as well as aperiodic channel state information (CSI) reporting requests may be supported. In yet another aspect, discontinued reception (DRX) wake ups for unlicensed carriers may be explicitly or implicitly indicated to a user equipment (UE) via a carrier in a licensed spectrum.

Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.

Abstract: Methods and apparatus for wireless communication are described. A method may include receiving at a user equipment (UE) a number of allocated interlaces for an uplink transmission over a shared spectrum, each of which may include a plurality of non-contiguous resource blocks (RB) of the shared spectrum. In some cases, the number of allocated interlaces is unsupported by joint interlace precoding hardware of the UE and the allocated interlaces may be partitioned into subsets of interlaces which may be a size supported by the joint interlace precoding hardware. Reference signals may be generated for the RBs of the allocated interlaces according to a reference signal sequence based on an ordering of the RBs for the allocated interlaces within the shared spectrum.

Abstract: Disclosed are techniques for fusing camera and radar frames to perform object detection in one or more spatial domains. In an aspect, an on-board computer of a host vehicle receives, from a camera sensor of the host vehicle, a plurality of camera frames, receives, from a radar sensor of the host vehicle, a plurality of radar frames, performs a camera feature extraction process on a first camera frame of the plurality of camera frames to generate a first camera feature map, performs a radar feature extraction process on a first radar frame of the plurality of radar frames to generate a first radar feature map, converts the first camera feature map and/or the first radar feature map to a common spatial domain, and concatenates the first radar feature map and the first camera feature map to generate a first concatenated feature map in the common spatial domain.

Abstract: Methods of processing vehicle sensor information for object detection may include capturing generating a feature map based on captured sensor information, associating with each pixel of the feature map a prior box having a set of two or more width priors and a set of two or more height priors, determining a confidence value of each height prior and each width prior, outputting an indication of a detected object based on a highest confidence height prior and a highest confidence width prior, and performing a vehicle operation based on the output indication of a detected object. Embodiments may include determining for each pixel of the feature map one or more prior boxes having a center value, a size value, and a set of orientation priors, determining a confidence value for each orientation prior, and outputting an indication of the orientation of a detected object based on the highest confidence orientation.

Abstract: A method performed by an apparatus is described. The method includes receiving a set of image frames including at least one object. The method also includes receiving a camera position for each image frame. The method further includes associating the at least one object between image frames based on one or more object points and the received camera position for each image frame to produce two-dimensional (2D) object location data. The method additionally includes estimating three-dimensional (3D) pose data of the at least one object based on the 2D object location data. The method also includes refining the 3D pose data based on a shape constraint.

Abstract: Methods, apparatuses, systems, and devices are described for wireless communication. In one method, a control format indicator value for a frame may be received over a physical carrier in a shared spectrum. Based on the control format indicator value, a number of subframes of the frame to be used by a base station for downlink transmissions over the physical carrier may be determined. The control format indicator value may indicate an end of transmission, if data is to be transmitted during the frame, a number of subframes to be used for transmission, or whether the current subframe is the final subframe used for transmission. In some cases, a user equipment (UE) may use the control format indicator value to determine a sleep schedule. Further, ACK/NACK transmissions by a UE may be scheduled based on the control format indicator value.

Abstract: The present disclosure, for example, relates to one or more techniques for scaling the bandwidth of a carrier. Available sub-channels of an unlicensed radio frequency spectrum band may be determined, and the available sub-channels may be included in the carrier. The available sub-channels may be adjacent or non-adjacent sub-channels. The bandwidth of the carrier may be determined according to which sub-channels are included in the carrier. In this way, the bandwidth of the carrier may be scaled according to the available sub-channels in the unlicensed radio frequency spectrum band.

Abstract: Methods and apparatus for wireless communication are described. A method may include receiving at a user equipment (UE) a number of allocated interlaces for an uplink transmission over a shared spectrum, each of which may include a plurality of non-contiguous resource blocks (RB) of the shared spectrum. In some cases, the number of allocated interlaces is unsupported by joint interlace precoding hardware of the UE and the allocated interlaces may be partitioned into subsets of interlaces which may be a size supported by the joint interlace precoding hardware. Reference signals may be generated for the RBs of the allocated interlaces according to a reference signal sequence based on an ordering of the RBs for the allocated interlaces within the shared spectrum.