Faro Technologies, Inc.

Mark Brenner

Oliver Zweigle

Aleksej Frank

Ahmad Ramadneh

Mufassar Waheed

Simon Raab

Rolf Heidemann

Matthias Wolke

Muhammad Umair Tahir

Steffen Kappes

Michael Müller

A method for performing a simultaneous location and mapping of a scanner device in a surrounding environment includes capturing a scan-data of a portion of a map of the surrounding environment. The scan-data comprises a point cloud. Further, at runtime, a user-interface is used to make, a selection of a feature from the scan-data, and a selection of a submap that was previously captured. The submap includes the same feature. The method further includes determining a first scan position as a present position of the scanner device, and determining a second scan position as a position of the scanner device. The method further includes determining a displacement vector for the map based on the first and the second scan positions. Further, a revised first scan position is computed based on the second scan position and the displacement vector. The scan-data is registered using the revised first scan position.

Generating environmental map by aligning captured scans

A mobile three-dimensional (3D) measuring system includes a 3D measuring device, and a support apparatus. The 3D measuring device is coupled to the support apparatus. The support apparatus includes a pole mount that includes a gimbal at the top of the pole mount, wherein the 3D measuring device is attached to the gimbal. The support apparatus further includes a counterweight at the bottom of the pole mount, the counterweight matches a weight of the 3D measuring device.

Support system for mobile coordinate scanner

A system includes a transporter robot with a motion controller that changes the transporter robot's poses during transportation. A scanning device is fixed to the transporter robot. One or more processors are coupled to the transporter robot and the scanning device to generate a map of the surrounding environment. At a timepoint T, when the transporter robot is stationary at a first location, a first pose of the transporter robot is captured. During transporting the scanning device, at a timepoint T, the scanning device captures additional scan-data of a portion of the surrounding environment. In response, the motion controller provides a second pose of the transporter robot at T. A compensation vector and a rotation for the scan-data are determined based on a difference between the first pose and the second pose. A revised scan-data is computed, and the revised scan-data is registered to generate the map.

Capturing environmental scans using automated transporter robot

Techniques are described for converting a 2D map into a 3D mesh. The 2D map of the environment is generated using data captured by a 2D scanner. Further, a set of features is identified from a subset of panoramic images of the environment that are captured by a camera. Further, the panoramic images from the subset are aligned with the 2D map using the features that are extracted. Further, 3D coordinates of the features are determined using 2D coordinates from the 2D map and a third coordinate based on a pose of the camera. The 3D mesh is generated using the 3D coordinates of the features.

Generating textured three-dimensional meshes using two-dimensional scanner and panoramic camera

A method for performing a simultaneous location and mapping of a scanner device includes detecting a set of lines in a point cloud, and identifying a semantic feature based on the set of lines. The method further includes assigning a first scan position of the scanner device in the surrounding environment at the present time tas a landmark, and linking the landmark with the portion of the map. The method further includes determining that the scanner device has moved, at time t, to the scan position that was marked as the landmark based on identifying said semantic feature in another scan-data. In response, a second scan position at time tis determined. Also, a displacement vector is determined for the map based on a difference between the first scan position and the second scan position. Subsequently, a revised second scan position is computed based on the displacement vector.

Capturing environmental scans using landmarks based on semantic features

Aspects of the present disclosure provide a system for measuring an object, the system including a plurality of frame segments. The frame segments are configured to mechanically couple together to form a frame. The plurality of frame segments includes a plurality of measurement device link segments and each of the plurality of measurement device link segments includes a measurement device which together form a plurality of measurement devices having a field of view within or adjacent to the frame. Each of the plurality of measurement devices is operable to measure three-dimensional (3D) coordinates for a plurality of points on the object. The system further includes a computing device to receive data from the plurality of measurement devices via a network established by the plurality of measurement device link segments.

Modular inspection system for measuring an object

A system for generating an automatically segmented and annotated two-dimensional (2D) map of an environment includes processors coupled to a scanner to convert a 2D map from the scanner into a 2D image. Further, a mapping system categorizes a first set of pixels from the image into one of room-inside, room-outside, and noise by applying a trained neural network to the image. The mapping system further categorizes a first subset of pixels from the first set of pixels based on a room type if the first subset of pixels is categorized as room-inside. The mapping system also determines the room type of a second subset of pixels from the first set of pixels based on the first subset of pixels by using a flooding algorithm. The mapping system further annotates a portion of the 2D map to identify the room type based on the pixels corresponding to the portion.

System and method of automatic room segmentation for two-dimensional laser floorplans

A projector projects an uncoded pattern of uncoded spots onto an object, which is imaged by a first camera and a second camera, 3D coordinates of the spots on the object being determined by a processor based on triangulation, the processor further determining correspondence among the projected and imaged spots based at least in part on a nearness of intersection of lines drawn from the projector and image spots through their respective perspective centers.

Growing community of inventors

Asperg, Germany

Mark Brenner