Google Inc.

Waymo LLC

X Development LLC

Jonathan Baldwin Dowdall

Jiajun Zhu

David Ian Ferguson

Dmitri A Dolgov

David Harrison Silver

David Ian Franklin Ferguson

Pierre-Yves Droz

Luke Wachter

Dorel Ionut Iordache

Lo Po Tsui

Peter Morton

Nafees Ahmed

A light detection and ranging device associated with an autonomous vehicle scans through a scanning zone while emitting light pulses and receives reflected signals corresponding to the light pulses. The reflected signals indicate a three-dimensional point map of the distribution of reflective points in the scanning zone. A hyperspectral sensor images a region of the scanning zone corresponding to a reflective feature indicated by the three-dimensional point map. The output from the hyperspectral sensor includes spectral information characterizing a spectral distribution of radiation received from the reflective feature. The spectral characteristics of the reflective feature allow for distinguishing solid objects from non-solid reflective features, and a map of solid objects is provided to inform real time navigation decisions.

Characterizing optically reflective features via hyper-spectral sensor

A vehicle is provided that may distinguish between dynamic obstacles and static obstacles. Given a detector for a class of static obstacles or objects, the vehicle may receive sensor data indicative of an environment of the vehicle. When a possible object is detected in a single frame, a location of the object and a time of observation of the object may be compared to previous observations. Based on the object being observed a threshold number of times, in substantially the same location, and within some window of time, the vehicle may accurately detect the presence of the object and reduce any false detections.

Static obstacle detection

Aspects of the disclosure relate to generating a grid or a visual list to facilitate operator review of labels. The system receives a first set of labels generated by a first labeling source and a second set of labels generated by a second labeling source. The first set of labels and the second set of labels each classify one or more objects perceived in one or more scenes captured by a sensor of a vehicle, such that each of the one or more objects has a corresponding first label and a corresponding second label. The system determines discrepancies between the corresponding first label and the corresponding second label for each of the one or more objects, and generates a grid or a visual list using the determined discrepancies. The system provides the grid or the visual list for display to a human operator.

Perception visualization tool

A vehicle configured to operate in an autonomous mode may engage in an obstacle evaluation technique that includes employing a sensor system to collect data relating to a plurality of obstacles, identifying from the plurality of obstacles an obstacle pair including a first obstacle and a second obstacle, engaging in an evaluation process by comparing the data collected for the first obstacle to the data collected for the second obstacle, and in response to engaging in the evaluation process, making a determination of whether the first obstacle and the second obstacle are two separate obstacles.

Obstacle evaluation technique

An autonomous vehicle configured to avoid pedestrians using hierarchical cylindrical features. An example method involves: (a) receiving, at a computing device, range data corresponding to an environment of a vehicle, and the range data comprises a plurality of data points; (b) detecting, by the computing device, one or more subsets of data points from the plurality of data points that are indicative of an upper-body region of a pedestrian, and the upper-body region may comprise parameters corresponding to one or more of a head and a chest of the pedestrian; and (c) in response to detecting the one or more subsets of data points, determining a position of the pedestrian relative to the vehicle.

Methods and systems for pedestrian avoidance

Methods and systems for estimating vehicle speed are disclosed. A light detecting and ranging (LIDAR) device obtains a set of spatial points indicative of locations of reflective surfaces in an environment of the LIDAR device. A plurality of target points that correspond to a target surface of a target vehicle is identified in the set of spatial points. The plurality of target points includes a first point indicative of a first location on the target surface obtained by the LIDAR device at a first time and a second point indicative of a second location on the target surface obtained by the LIDAR device at a second time. A speed of the target vehicle is estimated based on the first location, the first time, the second location, and the second time.

Methods and systems for estimating vehicle speed

Example methods and systems for detecting reflective markers at long range are provided. An example method includes receiving laser data collected from successive scans of an environment of a vehicle. The method also includes determining a respective size of the one or more objects based on the laser data collected from respective successive scans. The method may further include determining, by a computing device and based at least in part on the respective size of the one or more objects for the respective successive scans, an object that exhibits a change in size as a function of distance from the vehicle. The method may also include determining that the object is representative of a reflective marker. In one example, a computing device may use the detection of one reflective marker to help detect subsequent reflective markers that may be in a similar position.

Methods and systems for detection of reflective markers at long range

Methods and systems for alignment of light detection and ranging (LIDAR) data are described. In some examples, a computing device of a vehicle may be configured to compare a three-dimensional (3D) point cloud to a reference 3D point cloud to detect obstacles on a road. However, in examples, the 3D point cloud and the reference 3D point cloud may be misaligned. To align the 3D point cloud with the reference 3D point cloud, the computing device may be configured to determine a planar feature in the 3D point cloud of the road and a corresponding planar feature in the reference 3D point cloud. Further, the computing device may be configured to determine, based on comparison of the planar feature to the corresponding planar feature, a transform. The computing device may be configured to apply the transform to align the 3D point cloud with the reference 3D point cloud.

Growing community of inventors

Oakland, CA, United States of America

Jonathan Baldwin Dowdall