Waymo LLC

Google Inc.

Ian James Mahon

Nathaniel Fairfield

David Ian Ferguson

Jiajun Zhu

Dmitri A Dolgov

Christopher Paul Urmson

Congcong Li

Dirk Haehnel

Ruichi Yu

Sachithra Madhawa Hemachandra

Mingcheng Chen

Christian Lauterbach

Sachithra Hemachandra

The technology relates to tracking objects in an environment around an autonomous vehicle. A computing system of the autonomous vehicle determines accurate motion characteristics of objects detected in its environment despite various sensor measurement limitations. By correcting motion distortion for fast moving objects and accounting for discrepancies in sensor data gathering, motion characteristics may be determined for the detected objects with enhanced accuracy. Multiple sets of correspondences are determined for clusters from multiple sensor spins, enabling better alignment using a surface matching algorithm even when clusters have fewer data points. Efficiency is also enhanced by selecting hypotheses based on confidence levels. These techniques provide for identifying the types of objects for which a yaw rate can be accurately determined. Object classification can also be improved by accumulating associated clusters corresponding to a detected object. In addition, under- or over-segmentation can be mitigated with such techniques.

Onboard cluster tracking system

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for associating a new measurement of an object surrounding a vehicle with a maintained track. One of the methods includes receiving an object track for a particular object, receiving a new measurement characterizing a new object at a new time step, and determining whether the new object is the same as the particular object, comprising: generating a representation of the new object at the new and preceding time steps; generating a representation of the particular object at the new and preceding time steps; processing a first network input comprising the representations using a first neural network to generate an embedding of the first network input; and processing the embedding of the first network input using a second neural network to generate a predicted likelihood that the new object and the particular object are the same.

Geo-motion and appearance aware data association

A system and method is provided for identifying an object along a road, where the object may be represented by a bounding box, and projecting a set of obstacle points within the bounding box corresponding to the identified object. In one aspect, a two-dimensional plane oriented perpendicular to a direction of the movement of the vehicle may be identified. In another aspect, the areas of the plane that may be occupied based on the set of obstacle points may be determined to generate a contour of the identified object. Thereafter, the height profiles of the identified object and the vehicle may be determined and identified, respectively. Based on the height profiles, a minimum clearance may be determined.

Using obstacle clearance to measure precise lateral gap

Using obstacle clearance to measure precise lateral

Methods and systems for construction zone object detection are described. A computing device may be configured to receive, from a LIDAR, a 3D point cloud of a road on which a vehicle is travelling. The 3D point cloud may comprise points corresponding to light reflected from objects on the road. Also, the computing device may be configured to determine sets of points in the 3D point cloud representing an area within a threshold distance from a surface of the road. Further, the computing device may be configured to identify construction zone objects in the sets of points. Further, the computing device may be configured to determine a likelihood of existence of a construction zone, based on the identification. Based on the likelihood, the computing device may be configured to modify a control strategy of the vehicle; and control the vehicle based on the modified control strategy.

Construction zone object detection using light detection and ranging

Aspects of the disclosure relate generally to notifying a pedestrian of the intent of a self-driving vehicle. For example, the vehicle may include sensors which detect an object such as a pedestrian attempting or about to cross the roadway in front of the vehicle. The vehicle's computer may then determine the correct way to respond to the pedestrian. For example, the computer may determine that the vehicle should stop or slow down, yield, or stop if it is safe to do so. The vehicle may then provide a notification to the pedestrian of what the vehicle is going to or is currently doing. For example, the vehicle may include a physical signaling device, an electronic sign or lights, a speaker for providing audible notifications, etc.

Pedestrian notifications

Growing community of inventors

Berkeley, CA, United States of America

Ian James Mahon