Abstract: Provided are a system and methods for a unified framework and tooling for lane boundary annotation, which include obtaining sensor data along a trajectory corresponding to locations of a base map. Features are extracted from the sensor data. The features are input into a trained neural network that outputs overlapping rich feature maps comprising polylines. The overlapping rich feature maps are aggregated according to an aggregation function to obtain raster image. Vectorization is applied to the raster images to extract roadway geometry represented by globally consistent polylines.

Abstract: Provided are methods for. Some methods described include: receiving, with at least one processor, a point cloud from a pose graph; receiving, with the at least one processor, an image from a driving log of a vehicle, the image corresponding to the point cloud from the pose graph; obtaining, with the at least one processor, image pixel labels for the image; projecting, with the at least one processor, the point cloud in a point cloud coordinate system to an image coordinate system based on the image pixel labels; generating, with the at least one processor, a six-dimensional colored point cloud by combining the point cloud and color information from the image; and transforming, with the at least one processor, the six-dimensional colored point cloud into five-dimensional map tiles to form a colored map layer. Systems and computer program products are also provided.

Abstract: Provided are methods, systems, and computer program products for generating an output map indicating a likelihood of individual elements of an image as corresponding to particular road elements, such as lane dividers, road dividers, and road boundaries. An example method may include applying a machine learning architecture to the image, which architecture includes a convolutional neural network and a sub-network capturing global context from feature maps generated by the convolutional neural network.

Abstract: A continuous (multi-)analyte sensor device is provided, comprising a (multi-)analyte sensor operably coupled to a signal transducer, the (multi-)analyte sensor comprising at least one membrane, the least one membrane comprising a least one first transducing element, and at least one of a mediator and/or a regenerative cofactor.

Abstract: A method for determining a trajectory of a vehicle within a physical space based at least on an aligned point cloud may include generating a fused feature map by concatenating a first feature map corresponding to a source point cloud and a second feature map corresponding to a target point cloud. A machine learning model may be applied to determine, based at least on the fused feature map, a relative transform aligning the target point cloud to the source point cloud. An aligned target point cloud may be generated by transforming the target point cloud in accordance with the relative transform. Furthermore, a trajectory of a vehicle within the physical space may be determined based on at least the first relative transform. Related systems and computer program products are also provided.

Abstract: A method for determining a trajectory of a vehicle within a physical space based at least on an aligned point cloud may include generating a fused feature map by concatenating a first feature map corresponding to a source point cloud and a second feature map corresponding to a target point cloud. A machine learning model may be applied to determine, based at least on the fused feature map, a relative transform aligning the target point cloud to the source point cloud. An aligned target point cloud may be generated by transforming the target point cloud in accordance with the relative transform. Furthermore, a trajectory of a vehicle within the physical space may be determined based on at least the first relative transform. Related systems and computer program products are also provided.

Abstract: The present application relates to a floating module, a floating platform assembled by multiple floating platforms, and an off-shore system assembled by multiple floating platforms for harvesting green energies in a large body of water. The floating module comprises an external frame having a plurality of side tubes for providing buoyance to the floating module; and an internal frame coupled to the external frame. In addition, the floating module has a mooring mechanism for fixing the floating module in position at sea or ocean. Methods of making the floating module and assembling the floating platform and the offshore system are also disclosed.

Abstract: A method of signaling enhancement for an always-on PDU session is provided. A User Equipment (UE) transmits a Non-Access Stratum (NAS) request message to a mobile communication network. The NAS request message includes an Always-on PDU Session Requested (APSR) Information Element (IE). The UE receives a NAS response message including an Always-on PDU Session Indication (APSI) IE from the mobile communication network. The APSI IE includes a time length indicator. In response to the APSI IE indicating that the always-on PDU session is not allowed, the UE starts a timer based on the time length indicator and retransmits the NAS request message to the mobile communication network when the timer expires.

Abstract: A communication method of a network entity for a network equipment includes the steps of: receiving a request message of entering a mobile initiated connection only (MICO) mode from a user equipment (UE); determining a time length of a delay timer of the MICO mode according to the request message; and paging the UE when the delay timer of the MICO expires.

Abstract: A configuration system (80) arranged to configure an aircraft in a single-pilot mode and a two-pilot mode, comprising: acquisition means (84) and authentication means (83) arranged to acquire and authenticate a configuration order that defines the selected mode and controls the configuration system (80) to configure the aircraft in the selected mode; first activation means (85) arranged to activate equipment dedicated to piloting by a single-pilot on board when the aircraft is configured in single-pilot mode, and to deactivate dedicated equipment when the aircraft is configured in two-pilot mode; verification means (87) arranged to, when the aircraft is configured in the single-pilot mode, verify that single-pilot flight conditions are met and inform the sole pilot on board and a ground station of the results of these checks.

Abstract: The present invention relates to a composition for prevention or treatment of Alzheimer's disease comprising Lactobacillus sakei Probio-65, and more particularly, it relates to a composition for the prevention or treatment of Alzheimer's disease containing Lactobacillus sakei Probio-65 which may alleviate Alzheimer's disease through changes in the profile of intestinal microorganisms and intestinal metabolome composition without side effects.

Abstract: A battery assisting apparatus and a related device. The battery assisting apparatus includes a piezoelectric transformer group which includes N piezoelectric transformers and a drive circuit group which includes N drive circuits. Respective output ends of the N drive circuits are connected to respective input ends of the N piezoelectric transformers in a one-to-one correspondence, and respective output ends of the N piezoelectric transformers are connected to N battery cells in a battery string. M drive circuits in the N drive circuits are configured to respectively output first pulse signals to M piezoelectric transformers in the N piezoelectric transformers. Each of the M piezoelectric transformers is configured to receive the first pulse signal, and output, driven by the first pulse signal, electric energy to a battery cell corresponding to each piezoelectric transformer for charging, so that voltages of the N battery cells are consistent.

Abstract: An apparatus includes an analyte sensor, a memory, and a processor. The processor monitors, using the analyte sensor, an analyte of a patient during a time period to obtain measured analyte data for the analyte and monitors other measured sensor data indicative of a physiological state of the patient during the time period. The processor also determines, based on the physiological state of the patient during the time period, expected analyte data for the analyte and determines a correction factor based on the expected analyte data and the measured analyte data. The correction factor is indicative of an error in calibration of the analyte sensor. The processor also determines whether recalibration of the analyte sensor is possible. If recalibration is possible, the processor recalibrates the analyte sensor based on the correction factor, and if recalibration is not possible, the processor recommends, to the patient, to replace the analyte sensor.

Abstract: Provided are methods for enhanced semantic labeling in mapping with a semantic labeling system, which can include receiving, from a LiDAR sensor of a vehicle, LiDAR point cloud information including at least one raw point feature for a point, receiving, from a camera of the vehicle, image data associated with an image captured using the camera, generating at least one rich point feature for the point based on the image data, predicting, using a LiDAR segmentation neural network and based on the at least one raw point feature and the at least one rich point feature, a point-level semantic label for the point, and providing the point-level semantic label to a mapping engine to generate a map based on the point-level semantic label Systems and computer program products are also provided.

Abstract: An automated optical double-sided inspection apparatus includes a first image-capturing portion, a second image-capturing portion, a platform, a first light-blocking portion, a second light-blocking portion, and a processing portion. The platform carries an external object. When the processing portion operates in a first capturing mode, the second light-blocking portion blocks visible light from passing therethrough, while the first light-blocking portion allows visible light to pass therethrough, so that the first image-capturing portion shoots a first side of the external object through the first light-blocking portion to obtain a first image.

Abstract: An intelligent Forcipomyia taiwana monitoring and management system comprises: a catching mechanism grabbing a to-be-identified target; a database storing a datum comprising pictures of a flying insect category; a model training module using the pictures to establish a training model; an image capture module shooting an image including the target; an identifying module selecting a first segmented region including the target by using YOLO detection framework technology, extracting a first identification feature from the target, and inputting the feature into the training model for deep learning to identify a flying insect category to which the target belongs and produce an identification result; a counting module recording a number of the target into the database; and a predictive tracking module obtaining a marked object based on the result marked with the target identified in the image, and using a Monte-Carlo category algorithm to track and predict the object.

Abstract: A leather defect detection system comprises a worktable, a conveying mechanism, an image capture module, a model training computing device and an embedded computing device, the worktable is used to place a to-be-detected leather; the conveying mechanism is movably disposed on the worktable; the image capture module is disposed on the conveying mechanism, when the conveying mechanism is actuated, relative positions of the image capture module and the to-be-detected leather change synchronously to capture a plurality of to-be-detected images respectively; the model training computing device uses a plurality of historical leather images captured by the image capture module to perform calculation to establish a defect identification model, and the defect identification model is transcoded into the embedded computing device, so that the embedded computing device is capable of directly using the transcoded defect identification model to perform defect identification on the to-be-detected images.

Abstract: Embodiments are disclosed for ground plane estimation (GPE) using a LiDAR semantic network. In an embodiment, a method comprises: obtaining a point cloud from a depth sensor of a vehicle operating in an environment; encoding the point cloud; estimating, using a deep learning network with the encoded point cloud as input, a ground plane in the environment; planning a path through the environment based on a drivable area of the estimated ground plane; and operating the vehicle, the vehicle along the path. The deep learning network includes a two-dimensional (2D) convolutional backbone, a detection head for detecting objects and a GPE head for estimating the ground plane. In an embodiment, point pillars are used to encode the point cloud.

Abstract: Provided are methods for unsupervised domain adaptation for LiDAR segmentation via enhanced pseudo-labelling techniques, which can include training a machine learning model to perform a segmentation task for a source domain using a first sample set. Some methods also include generating a second sample set by applying the trained model to one or more unannotated samples associated with a target domain, and annotating the one or more unannotated samples with one or more pseudo-labels corresponding to an output of the trained machine learning model. Some methods also include generating a third sample set that includes at least one sample formed by concatenating a first sample from the first sample set and a second sample from the second sample set with target inputs. Some methods also include updating the trained machine learning model to perform the segmentation task for the target domain. Systems and computer program products are also provided.

Abstract: Provided are methods, systems, and computer program products for machine-learning based point cloud alignment classification. An example method may include: obtaining at least two light detection and ranging (LiDAR) point clouds; processing the at least two LiDAR point clouds using at least one classifier network; obtaining at least one output dataset from the at least one classifier network; determining that the at least two LiDAR point clouds are misaligned based on the at least one output dataset; and performing a first action based on the determining that the at least two LiDAR point clouds are misaligned.