One or more computational strategies is used to reduce the complexity of handling detected point clusters appearing at a portal of a monitored workcell. If the other side of the portal is a second, adjacent workcell, the monitoring system for a first workcell predicts when a human in that workcell may pass through the portal to a second workcell and alerts the monitoring system for the second workcell. The prediction may be based on absolute proximity of a human to the portal or movement toward it. Other strategies are employed if the workcells overlap, or if the portal leads to an unmonitored space.

An electronic distance meter comprises a coupler located between a laser source and a target and adapted to divert a portion of measurement light emitted by the laser source into a calibration portion connected to a photodetector and comprising an attenuator between said coupler and said photodetector for varying the luminance value of the light passing through the calibration portion, said calibration portion having a known length and said processor being configured to perform distance measurements through the calibration portion at a variety of luminance values achieved by said attenuator to derive calibration values from said distance measurements and said known length, said processor being further configured to use said calibration values for determining a target distance based on a return pulse signal.

Provided are a LIDAR signal processing apparatus and a LIDAR signal processing method. The LIDAR signal processing apparatus comprises: an inherent history pulse wave applying unit for applying a first pulse wave combination to a laser diode, the first pulse wave combination having an inherent history which includes a combination of an inherent pulse period and an inherent pulse variation value; a received history detecting unit for detecting a received signal period and a received signal variation value of a reflected wave received by a photodiode; an inherent pulse wave discriminating unit for deciding whether or not the received signal period and the received signal variation value coincide with the inherent history; and an effective data processing unit for measuring a distance using effective data when the received signal period and the received signal variation value coincide with the inherent history.

A multiple-pulses-in-air (MPiA) laser scanning system, wherein the MPiA problem is addressed in that an MPiA assignment of return pulses to send pulses of a laser scanner is based on range tracking and range probing at intermittent points in time. Each range probing comprises a time-of-flight arrangement which is constructed to be free of the MPiA problem. The invention further relates to an MPiA laser scanning system, wherein an MPiA ambiguity within a time series of return pulses, is converted into 3D point cloud space, which provides additional information from the spatial neighborhood of the points in question to enable MPiA disambiguation.

A light detection and ranging (LiDAR) apparatus capable of extracting speed information and distance information of objects in front thereof is provided. The LiDAR apparatus includes: a continuous wave light source configured to generate continuous wave light; a beam steering device configured to emit the continuous wave light to an object for a first time and stop emitting the continuous wave light to the object for a second time; a receiver configured to receive the continuous wave light that is reflected from the object to form a reception signal; and a signal processor configured to obtain distance information and speed information about the object based on the reception signal.

The present disclosure provides a point cloud denoising method based on deep learning for an aircraft part, in which different degrees of Gaussian noise are added based on a theoretical data model of the aircraft part, a heightmap for each point in the theoretical data model is generated, and a deep learning training set is constructed. A deep learning network is trained based on the constructed deep learning training set, to obtain a deep learning network model. A real aircraft part is scanned via a laser scanner to obtain measured point cloud data. The normal information of the measured point cloud is predicted based on the trained deep learning network model. Based on the predicted normal information, a position of each point in the measured point cloud data is further updated, thereby completing denoising of the measured point cloud data.

According to one or more embodiments, operations may comprise obtaining a first point cloud. The operations also comprise performing segmentation of the first point cloud, the segmentation generating one or more clusters of points of the point cloud. The operations also comprise determining, for each respective cluster of the plurality of clusters, a respective geometric feature of a corresponding object that corresponds to the respective cluster. The operations also comprise obtaining a second point cloud. The operations also comprise assigning a plurality of weights that comprises assigning a respective weight to each respective cluster based on the respective geometric feature that corresponds to the respective cluster. The operations also comprise obtaining a second point cloud and aligning the first point cloud with the second point cloud based on the plurality of weights.

Simulated degraded sensor data may be generated for use in training a model. For instance, first sensor data collected by a sensor of a perception system of an autonomous vehicle may be received and converted into the simulated degraded sensor data for a particular degrading condition, such as a weather-related degrading condition. Then, the simulated degraded sensor data may be used to train a model for evaluating performance of the perception system to detect objects external to the autonomous vehicle under one or more conditions.

The present disclosure relates to vehicle positioning methods, apparatus, controllers, intelligent vehicles, and systems. One example vehicle positioning method includes obtaining a first relative pose between a first vehicle and a help providing object, obtaining a global pose of the help providing object, and calculating a global pose of the first vehicle based on the first relative pose and the global pose.

Disclosed are a control method of a mobile robot, a mobile robot, and a storage medium. The method includes: when distance information obtained by a laser radar has an effective distance change, predicting an inclination angle of a forward road section relative to a current road surface where the mobile robot is currently located; determining a slope of the forward road section based on the inclination angle and a pitch angle; controlling movement of the mobile robot based on the slope and a result of comparison between the slope and a slope threshold preset by the mobile robot; and marking the forward road section as a slope area on a slope map, where the slope map is used to control, based on the slope area when the mobile robot passes by the slope area, the mobile robot to send climbing warning information.