Abstract: Path extraction for a vehicle on a guideway, the vehicle having two or more sensors. Two or more sensor inputs are received from two or more sensors including at least one active 3D sensor input from at least one active 3D sensor and at least one passive 2D sensor input from at least one passive 2D sensor. At least one active 3D sensor path is extracted based on the at least one active 3D sensor input and at least one passive 2D sensor path based on the at least one passive 2D sensor input. At least one 3D sensor ground surface model is generated based on the at least one passive 2D sensor path. At least one passive 3D path is generated based on the at least one passive 2D sensor path and the at least one 3D sensor ground surface model. The at least one passive 3D path and the at least one active 3D sensor path are fused to produce a consolidated 3D path. In a path extraction pipeline, at least one supervision check is performed for providing integrity to the consolidated 3D path.

Abstract: In a system and method for searching, browsing, and visualizing items, a first image containing an item is received to be stored in an account associated with a user. The first image is processed using a processor to extract an image of the item from the first image. The image of the item is layered over a stream of video frames received from the client device to form a superimposed image. The superimposed image is caused to be displayed on the client device.

Abstract: A method of determining a traversed branch for a vehicle on a constrained path, the method includes: receiving map-related information; receiving speed information; performing two or more different detection methods from among: inertial detection; magnetometer detection; texture detection; 3D detection; or velocity field detection; and arbitrating among the result of the two or more different detection methods to determine which branch was traversed.

Abstract: Embodiments of a method of locating a guideway mounted vehicle are disclosed. In one embodiment, a communication signal is transmitted to a wayside communication device. A range estimation is obtained based on the communication signal. A radar signal is transmitted to at least one reflector. An accuracy of the range estimation is increased based on the radar signal.

Abstract: A method of determining a position of a train (localization) includes initializing a train position with no a priori position information (e.g., at power up), i.e., cold localization, and determining a train position within a known coarse region, i.e., warm localization. On-board sensors are used to detect landmark objects in a localization region of the guideway, based on distinct features of the landmark objects. Detectors detect object features and the object features are fused. Landmark objects are tracked over time in a unified local reference frame such that a sliding window of landmark objects is maintained as a local map. Object features of landmark objects in the local map are compared to a reference map in order to uniquely identify a corresponding constellation of landmark objects in the reference map.

Abstract: In various example embodiments, a system and method for dynamically generating virtual marketplace platforms are presented. The system receives a set of facility data, a set of selections for a set of user interaction objects, and a set of object placement selections. The set of user interaction objects includes a first subset and a second subset. The system generates a virtual facility comprising the facility data and the set of user interaction objects distributed based on the object placement selections. The system receives user data for a user interacting with the virtual facility and one or more objects of the first and second subset of user interaction objects, dynamically arranges the second subset of user interaction objects into a second arrangement and causes presentation of the virtual facility and the set of user interaction objects to the user.

Abstract: A method of detecting a way-side object includes receiving data frames from sensors mounted on a vehicle. Position data corresponding to the position of the vehicle is received. Object-of-interest data is retrieved from a database. The sensor data frames and the object-of-interest data are processed to determine a region-of-interest in the sensor data frame. A portion of the sensor data frames corresponding to the region of interest is processed using machine-learned object detection to identify a first object-of-interest. The portion of the sensor data frames corresponding to the region of interest is processed using computer vision methods to detect features of the expected object-of-interest and identifying the detected object-of-interest as explained when the features of the expected object-of-interest are detected. Explained object-of-interest data corresponding to the explained detected object-of-interest is output to a navigation system of the vehicle.

Abstract: In various example embodiments, a system and method for smart recurrent orders are presented. An inventory indicator corresponding to an inventory level of a first item may be received. An order schedule for the first item may be identified. An adjustment to the order schedule based on the inventory indicator may be determined. The adjustment to the order schedule for the first item may be facilitated.

Abstract: A method of semantic object detection in an image dataset includes extracting semantic links relevant to the image dataset. Objects are detected in the image dataset and confidence scores are assigned to the detected objects. The semantic object detection compares the detected objects with the semantic links and augments the confidence scores based on the semantic links between the detected objects.

Abstract: A rinse ring system for use on a toilet. The rinse ring is a dual channel rinse ring, which allows the toilet to be flushed with either potable water from a fresh water system or with grey water from a grey water source. Other flush fluids are possible for use. The dual channel rinse ring provides separation between entry points for potable water rinse and the grey water rinse, preventing the possibility of contamination of the potable water source with grey water.

Abstract: In various example embodiments, a system and method for dynamically generating virtual marketplace platforms are presented. The system receives a set of facility data, a set of selections for a set of user interaction objects, and a set of object placement selections. The set of user interaction objects includes a first subset and a second subset. The system generates a virtual facility comprising the facility data and the set of user interaction objects distributed based on the object placement selections. The system receives user data for a user interacting with the virtual facility and one or more objects of the first and second subset of user interaction objects, dynamically arranges the second subset of user interaction objects into a second arrangement and causes presentation of the virtual facility and the set of user interaction objects to the user.

Abstract: A method and system include receiving positioning and motion information from one or more positioning and motion devices on a vehicle on a guideway, based on the positioning and motion information, receiving information from a database on the vehicle, the information comprising track geometry information and infrastructure information corresponding to the guideway, using the track geometry information and positioning and motion information to determine a path of the guideway and a trajectory of the vehicle along the path, receiving data from one or more electromagnetic sensors on the vehicle, and detecting an object by using the trajectory, the infrastructure information, and the information from the one or more electromagnetic sensors.

Abstract: Vacuum toilet flush valves. The disclosure uses a precise positioning of a magnet with respect to a flush valve plate in order to identify absolute alignment accurately.

Abstract: In various example embodiments, a system and method for dynamically generating virtual marketplace platforms are presented. The system receives a set of facility data, a set of selections for a set of user interaction objects, and a set of object placement selections. The set of user interaction objects includes a first subset and a second subset. The system generates a virtual facility comprising the facility data and the set of user interaction objects distributed based on the object placement selections. The system receives user data for a user interacting with the virtual facility and one or more objects of the first and second subset of user interaction objects, dynamically arranges the second subset of user interaction objects into a second arrangement, and causes presentation of the virtual facility and the set of user interaction objects to the user.

Abstract: Path extraction for a vehicle on a guideway, the vehicle having two or more sensors. Two or more sensor inputs are received from two or more sensors including at least one active 3D sensor input from at least one active 3D sensor and at least one passive 2D sensor input from at least one passive 2D sensor. At least one active 3D sensor path is extracted based on the at least one active 3D sensor input and at least one passive 2D sensor path based on the at least one passive 2D sensor input. At least one 3D sensor ground surface model is generated based on the at least one passive 2D sensor path. At least one passive 3D path is generated based on the at least one passive 2D sensor path and the at least one 3D sensor ground surface model. The at least one passive 3D path and the at least one active 3D sensor path are fused to produce a consolidated 3D path. In a path extraction pipeline, at least one supervision check is performed for providing integrity to the consolidated 3D path.

Abstract: Methods and systems for equipping a toilet with hygiene and safety features by controlling and reducing potential escape of liquid waste from the toilet.

Abstract: A fluid recycling unit for use on board an aircraft or other passenger transportation vehicle. The fluid recycling unit captures various types of used fluids, filters or otherwise appropriately treats the fluids, and recycles the fluids for various uses onboard the vehicle.

Abstract: A system for determining a stationary state of a rail vehicle on a track includes a first radar mounted at an end of the rail vehicle and a second radar mounted at another end of the rail vehicle. A speed sensor is mounted on the rail vehicle. A series of fixed reflective track features are found along the track. A processing unit, communicably connected with the speed sensor, the first radar and the second radar receives data from the first radar and the second radar corresponding to the distance to the fixed reflective track features and determines the stationary state or low-speed condition of the rail vehicle and checks the state or condition by comparing it with an output of the speed sensor.

Abstract: A vehicle locator includes an on-board computer and a ground penetrating radar mounted on the vehicle that is communicably connected to the on-board computer. A reflective landmark is located at a known location along the path of the vehicle. The reflective landmark includes reflective elements arranged to encode data. The ground penetrating radar transmits signal energy and detects reflected signal energy reflected by the reflective landmark and communicates encoded data representative of the reflected signal energy to the on-board computer. The on-board computer decodes the encoded data and thereby determines the location of the vehicle.

Abstract: A method of improving robustness of a deep neural network (DNN), the method including: applying a coverage metric to a trained DNN based on a test set to determine test set adequacy; monitoring a performance of the trained DNN; based on the performance, applying new data to the trained DNN; applying a novelty metric to an output of the trained DNN based on the applied new data to identify a subset of the applied new data in response to determining whether new features are generated; and identifying the subset of the applied new data.