Abstract: Disclosed herein are system, method, and computer program product embodiments for automated autonomous vehicle pose validation. An embodiment operates by generating a range image from a point cloud solution comprising a pose estimate for an autonomous vehicle. The embodiment queries the range image for predicted ranges and predicted class labels corresponding to lidar beams projected into the range image. The embodiment generates a vector of features from the range image. The embodiment compares a plurality of values to the vector of features using a binary classifier. The embodiment validates the autonomous vehicle pose based on the comparison of the plurality of values to the vector of features using the binary classifier.

Abstract: Disclosed herein are system and method embodiments to implement a validation of an SfM map. An embodiment operates by receiving a motion-generated map corresponding to a digital image, generating a first depth map, wherein the first depth map comprises depth information for one or more triangulated points located within the motion generated image. The embodiment further receives a light detection and ranging (lidar) generated point cloud including at least a portion of the one or more triangulated points, splats the lidar point cloud proximate to the portion of the one or more triangulated points and generates a second depth map for the portion and identifies an incorrect triangulated point, of the one or more triangulated points, based on comparing the first depth information to the second depth information. The incorrect triangulated points may be removed from the SfM map or marked with a low degree of confidence.

Abstract: Disclosed herein are system, method, and computer program product embodiments for automated autonomous vehicle pose validation. An embodiment operates by generating a range image from a point cloud solution comprising a pose estimate for an autonomous vehicle. The embodiment queries the range image for predicted ranges and predicted class labels corresponding to lidar beams projected into the range image. The embodiment generates a vector of features from the range image. The embodiment compares a plurality of values to the vector of features using a binary classifier.

Abstract: Disclosed herein are system, method, and computer program product embodiments for automated autonomous vehicle pose validation. An embodiment operates by generating a range image from a point cloud solution comprising a pose estimate for an autonomous vehicle. The embodiment queries the range image for predicted ranges and predicted class labels corresponding to lidar beams projected into the range image. The embodiment generates a vector of features from the range image. The embodiment compares a plurality of values to the vector of features using a binary classifier. The embodiment validates the autonomous vehicle pose based on the comparison of the plurality of values to the vector of features using the binary classifier.

Abstract: Disclosed herein are system, method, and computer program product embodiments for automated autonomous vehicle pose validation. An embodiment operates by generating a range image from a point cloud solution comprising a pose estimate for an autonomous vehicle. The embodiment queries the range image for predicted ranges and predicted class labels corresponding to lidar beams projected into the range image. The embodiment generates a vector of features from the range image. The embodiment compares a plurality of values to the vector of features using a binary classifier.

Abstract: An automated bootstrap process implemented as a simple state machine generates an initial pose for an autonomous vehicle, without reliance on human intervention. To trigger initiation of the bootstrap process automatically, the autonomous vehicle remains stationary. A GPS-derived position estimate, combined with lidar sweep data and HD map reference point cloud data, can be used to generate a pose using an iterative closest point algorithm. The bootstrap solution can then be automatically validated by a machine learning-based binary classifier trained with appropriate features. Full automation of the bootstrap process may facilitate launching a fleet service of autonomous vehicles.

Abstract: Disclosed herein are system and method embodiments to implement a validation of an SfM map. An embodiment operates by receiving a motion-generated map corresponding to a digital image, generating a first depth map, wherein the first depth map comprises depth information for one or more triangulated points located within the motion generated image. The embodiment further receives a light detection and ranging (lidar) generated point cloud including at least a portion of the one or more triangulated points, splats the lidar point cloud proximate to the portion of the one or more triangulated points and generates a second depth map for the portion and identifies an incorrect triangulated point, of the one or more triangulated points, based on comparing the first depth information to the second depth information. The incorrect triangulated points may be removed from the SfM map or marked with a low degree of confidence.

Abstract: A method of communicating with one or more RFID sensor tags within a predetermined area. The method comprises: providing an RFID sensor tag interrogation apparatus comprising an RF transceiver configured to enable control of a transmitted RF power level; setting the transmitted RF power level to provide an RF signal detectable by RFID sensor tags located within a corresponding region of the predetermined area; transmitting, by the RFID sensor tag interrogation apparatus, an RFID sensor tag interrogation signal; and receiving, by the RFID sensor tag interrogation apparatus, one or more responses transmitted by the RFID sensor tags located within the predetermined area. In some embodiments the transmitted RF power level is adjusted to increase or decrease the size of the corresponding region of the predetermined area, based upon responses received from RFID sensor tags located within the region.

Abstract: An RFID sensor tag includes a processor, a power source, an RF transceiver, one or more sensors accessible to the processor via a sensor interface, and at least one memory device. In one example, the tag is configured to operate in a low power-consumption state, a medium power-consumption state in which sensor measurements are performed, and a high power-consumption state used when engaged in RF communications. In another example, power consumption and memory usage are reduced by configuring the tag to record sensor data only upon satisfaction of a predetermined condition. In a further example, the tag is configured to respond to an RF interrogation signal only when the signal includes an instruction in accordance with a predetermined communications protocol. In another example, the tag is configured, upon interrogation, to confirm whether new recorded sensor data is available, to minimise transmission in the event that no new data is available.

Abstract: A method (300) of managing energy consumption associated with premises includes firstly generating (302) and storing an initial energy profile (304) of the premises. The profile (304) includes information characterizing the premises, such as occupancy patterns, function of the premises, geographical location, installed appliances (108), and so forth. An expected energy usage (308) associated with the premises is computed over a predetermined time period based upon the information in the initial energy profile (304). Actual energy usage (312) associated with the premises is then recorded over the predetermined time period and the energy profile (304) is adaptively updated based upon the recorded energy usage (312). The energy profile (304) and the actual energy usage (312) are used to manage energy consumption associated with the premises. An installable system (100) and apparatus (102) for implementing the method at premises are also provided.

Abstract: A method (300) of managing energy consumption associated with premises includes firstly generating (302) and storing an initial energy profile (304) of the premises. The profile (304) includes information characterising the premises, such as occupancy patterns, function of the premises, geographical location, installed appliances (108), and so forth. An expected energy usage (308) associated with the premises is computed over a predetermined time period based upon the information in the initial energy profile (304). Actual energy usage (312) associated with the premises is then recorded over the predetermined time period and the energy profile (304) is adaptively updated based upon the recorded energy usage (312). The energy profile (304) and the actual energy usage (312) are used to manage energy consumption associated with the premises. An installable system (100) and apparatus (102) for implementing the method at premises are also provided.

Abstract: A method for processing an information sequence with an iterative decoder is provided. The information sequence is divided into a current window and at least one additional window. The current window of the information sequence is selected. At least one metric value for a current recursion of the current window is computed based on metric values from the additional window of the information sequence, wherein the additional window is a past iteration. Systems and programs for processing an information sequence are also provided.

Abstract: System (100) for generating syndrome (222) usable in decoder (130) includes reducer (340) and converter (330). Reducer (340) employs information to generate representation (342). Converter (330) generates, with employment of representation (342), syndrome (222).

Abstract: A method of processing an information sequence with a decoder is provided. A window within the information sequence is selected. A training period is calculated for the window. At least one recursion of the window is initialized based on the calculated training period. Systems and programs for processing the information sequence are also provided.

Abstract: A processor includes a first vector processing unit including a first register file and first vector arithmetic logic unit; a second vector processing unit including a second register file and second vector arithmetic logic unit wherein the first register file has a first plurality of cross connections to the second vector arithmetic logic unit; wherein the second register file as a second plurality of cross connections to the first vector arithmetic logic unit.

Abstract: A method for inspecting a semiconductor wafer using an SEM having a nominal focal plane and operable for guiding a beam. The SEM having a stage movable in each of an X-, Y-, and Z-direction, including moving the SEM stage in the XY-direction to a first location for inspection, optically sensing the location of the top surface of an area in relation to the focal plane of the stage, adjusting the position of the stage in the Z-direction so that the top surface of the area is substantially at the focal plane, inspecting the areas, and moving the stage in the XY-direction to the next location such that the next area is under the SEM beam for inspection. The Z-stage using a non-contact optical sensor to provide feedback to drive a plurality of piezoelectric actuator to move the wafer to the focal plane.

Abstract: A squished trellis encoder encodes blocks of information with unequal error correction. A multiplexing switch partitions the information block into a first portion and a second portion. A first trellis encoder encodes the first portion. A second trellis encoder encodes the second portion. An initial state information generator maps the states of the first trellis encoder to the second trellis encoder to establish initial conditions for the states of the second trellis encoder. A delay delays the second portion from processing by the second trellis encoder until the initial state information generator has mapped the states. An associated decoder can use the novel squished approach or other alternative approaches.

Abstract: The log-add kernel operation is represented as a summation of an average and a correction factor composed of a constant and a term based on a difference between the input arguments. In a described embodiment, the correction factor is approximated using the reduction of the correction factor into a Taylor series expansion, which may be defined around the difference between the input arguments as approximately zero. The approach may be further optimized to provide the Taylor series expansion as being modified to compute the correction factor with simple additions, multiplications, and shift operations. If the input arguments are close to each other, the new computed representation may be used, and if the arguments are further apart, the max operation is used. The log-add kernel operation also may be extended to more than two arguments, for application, for example, in the kernel operation of the generalized Viterbi decoder with a branch fan-in greater than 2.

Abstract: Controller component (155) of system (100) generates address pattern (902) through employment of one or more parameters (205), to store information (810) at a plurality of parts of storage, for example, one or more instances of banked data memory (140) that are employable with multiprocessing. The one or more parameters (205) are related to the information (810).

Abstract: The invention provides a method for operating a hybrid automatic repeat request communication system wherein it is determined whether a receiver can process a data packet, and a self-decode request associated with the data packet is sent based on the determination.