A method for measuring the performance of a classifier for radar, ultrasound or audio spectra. The classifier is configured to map a radar, ultrasound or audio spectrum to a set of classification scores with respect to classes of a given classification. The method includes: providing a set of test radar, ultrasound or audio spectra that form part of, and/or define, a common distribution or manifold; obtaining at least one evaluation spectrum that is a modification of at least one test spectrum with substantially the same semantic content as this at least one test spectrum, and/or does not form part of the common distribution or manifold; mapping, using the classifier, the at least one evaluation spectrum to a set of evaluation classification scores; and determining the performance based on the set of evaluation classification scores, and/or on a further outcome produced by the classifier during the processing of the evaluation spectrum.

Proposed is a noise avoiding method for a space monitoring apparatus using a sound signal and, more specifically, is a technology that allows the space monitoring apparatus, which uses a sound signal to monitor a spatial condition, to avoid noise in a space to be monitored to correctly determine the spatial condition.

The underwater acoustic test system comprises an underwater acoustic transmitting unit, an underwater acoustic parabolic reflector, an underwater acoustic receiving unit, an orientation control system, and a computer measurement and control system. The underwater acoustic transmitting unit comprises an underwater acoustic signal generator and a transmitting transducer. The underwater acoustic parabolic reflector comprises a central main reflecting area and an edge diffraction processing area, wherein the central main reflecting area is configured for reflecting acoustic wave signals, and the edge diffraction processing area is configured for reducing the influence of the underwater acoustic parabolic reflector on a test area. The underwater acoustic receiving unit comprises a receiving transducer and an underwater acoustic signal receiver. The orientation control system comprises a traveling crane and a test turntable.

Proposed is a noise avoiding method for a space monitoring apparatus using a sound signal and, more specifically, is a technology that allows the space monitoring apparatus, which uses a sound signal to monitor a spatial condition, to avoid noise in a space to be monitored to correctly determine the spatial condition.

This document describes techniques, apparatuses, and systems for sensor fusion for object-avoidance detection, including stationary-object height estimation. A sensor fusion system may include a two-stage pipeline. In the first stage, time-series radar data passes through a detection model to produce radar range detections. In the second stage, based on the radar range detections and camera detections, an estimation model detects an over-drivable condition associated with stationary objects in a travel path of a vehicle. By projecting radar range detections onto pixels of an image, a histogram tracker can be used to discern pixel-based dimensions of stationary objects and track them across frames. With depth information, a highly accurate pixel-based width and height estimation can be made, which after applying over-drivability thresholds to these estimations, a vehicle can quickly and safely make over-drivability decisions about objects in a road.

An arithmetic device includes: an input unit to which information pertaining to a detection target that is a target recognized by a sensor is input from the sensor; a processing-unit allocation unit that is configured to allocate a plurality of the targets to any one of a plurality of groups; an association unit that is configured to retrieve a second one of the targets to be associated with a first one of the targets from a part of the plurality of groups included in the plurality of groups; and a state fusion unit that is configured to fuse the first target and the second target that have been associated with each other by the association unit to produce a tracking target that is a target being tracked. The first target is any one of the detection target and the tracking target. The second target is any one of the detection target and the tracking target.

A system and method for USS reading enhancement using a lidar point cloud. This provides noise reduction and enables the generation of a 2D environmental map. More specifically, the present disclosure provides a system and method for generating an enhanced environmental map using USSs, and the map is enhanced using a lidar point cloud. Using the lidar point cloud has advantages because the lidar point cloud is accurate and thus can provide accurate labels for training and the like.

A robotic cleaning appliance includes a housing to which is coupled a surface treatment item and a sensor assembly with first and second transducers and an acoustic interface. The first sonic transducer transmits sonic signals through an acoustic interface and out of a first acoustic opening toward a surface beneath the robotic cleaning appliance. The sonic signals reflect from the surface as corresponding returned signals received by the second sonic transducer via a second acoustic opening port of the acoustic interface. A first plurality of annular rings is defined in the external surface around the first acoustic opening port and a second plurality of annular rings is defined in the external surface around the second acoustic opening port. The pluralities of annular rings attenuate direct path echoes from a subset of the transmitted sonic signals which attempt to travel across the external surface to the second acoustic opening port.

A cleaning robot, comprising: a robot body, a control unit provided in the robot body, and a fixing unit provided at the bottom of a front end of the robot body, the fixing unit comprising a sleeve and an ultrasonic sensor, the ultrasonic sensor being fixed in the sleeve and being electrically connected to the control unit, and the ultrasonic sensor being used for emitting an ultrasonic wave downwards and receiving an echo reflected by different ground forms.

A Doppler device including a transducer and processing circuitry is provided. The transducer transmits underwater ultrasonic wave and receives a reflected wave of the ultrasonic wave. The Doppler device generates a first echo signal from the reflected wave in a first direction making a depression angle θ with a receiving surface of the transducer, generates a second echo signal from the reflected wave in a second direction making the depression angle θ with the receiving surface, the second direction being different from the first direction, and generates a third echo signal in a third direction perpendicular to the receiving surface. The processing circuitry further calculates a first Doppler frequency of the first echo signal, a second Doppler frequency of the second echo signal, and a third Doppler frequency of the third echo signal. The processing circuitry further calculates the depression angle θ from the first, second and third Doppler frequencies.