Zoox, Inc.

Mehran Ferdowsi

Subasingha Shaminda Subasingha

Turhan Karadeniz

Robert Nicholas Moor

Harrison Thomas Waschura

Joseph Patrick Warga

Silas Kogure Wilkinson

Yongzhe Chen

Samuel Holladay

Ryan McMichael

Sreevatsan Bhaskaran

Adam Pollack

Holly Ho

Denis Nikitin

Minh Nguyen

Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. The sensor may generate first image data at a first configuration and second image data at a second configuration. An estimated depth of an object may be determined from the first image data, and an actual depth of the object may be determined from the second image data, based on the estimated depth. In examples, the first and second configurations have different modulation frequencies such that a nominal maximum depth in the first configuration is greater than the nominal maximum depth in the second configuration.

Determining depth using multiple modulation frequencies

Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. Sensor data generated by the time-of-flight sensor can include returns associated with highly reflective objects that cause glare. In some examples, a depth of a sensed surface is determined from the sensor data and additional pixels at the same depth are identified. The subset of pixels at the depth are filtered by comparing a measured intensity value to a threshold intensity value for the depth. Other threshold intensity values can be applied to subsets of pixels at different depths.

Depth dependent pixel filtering

Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. The sensor may generate first image data at a first configuration and second image data at a second configuration. A disambiguated depth of a surface may be determined from the first image data and the second image data. If the disambiguated depth is greater than a nominal maximum depth of the sensor in the first configuration, an intensity of the surface may be determined from the first image data. If the intensity meets or exceeds a threshold intensity, the surface may be determined to be beyond the nominal maximum depth. If the intensity is less than the threshold intensity, an actual depth of the surface may be determined form the second image data as a distance less than the nominal maximum depth.

Determining pixels beyond nominal maximum sensor depth

Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. Sensor data generated by the time-of-flight sensor can include saturated pixels, e.g., due to over-exposure, sensing highly-reflective objects, and/or excessive ambient light. In some examples, parameters associated with power of a time-of-flight sensor can be altered based on characteristics of the saturated pixels, as well as information about non-saturated pixels neighboring the saturated pixels. For example, the neighboring pixels may provide information about whether saturation is due to ambient light, e.g., sunlight, or due to emitted light from the sensor.

Active power control using neighboring pixels

A machine-learned (ML) model for detecting that depth data (e.g., lidar data, radar data) comprises a false positive attributable to particulate matter, such as dust, steam, smoke, rain, etc. The ML model may be trained based at least in part on simulated depth data generated by a fluid dynamics model and/or by collecting depth data during operation of a device (e.g., an autonomous vehicle. In some examples, an autonomous vehicle may identify depth data that may be associated with particulate matter based at least in part on an outlier region in a thermal image. For example, the outlier region may be associated with steam.

Identifying and/or removing false positive detections from LIDAR sensor output

Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. Sensor data generated by the time-of-flight sensor can return unreliable pixels, e.g., in the case of over- or under-exposure. In some examples, parameters associated with power of a time-of-flight sensor can be altered based on a number of unreliable pixels in measured data and/or based on intensity values of the measured data. For example, unreliable pixels can be determined using phase frame information captured at a receiver of the sensor.

Active power control of sensors

A LIDAR system that identifies, from a channel output, a false positive return and/or suppressing a corresponding false positive detection caused, in some cases, a strong reflection by a highly reflective surface that caused light to leak from a first channel to a second channel. The LIDAR system described herein may identify, as a false return, a return detected in the second channel that has an intensity that is much less than a return in the first channel and indicates a distance that is the same or very close to a distance indicated the return in the first channel. Based at least in part on identifying a return as a false return, the LIDAR system may suppress a false detection associated with the false return by modifying a detection threshold.

Identifying and/or removing ghost detections from lidar sensor output

Techniques for facilitating a robust clock synchronization across a computer network that presumes network jitter exists are discussed herein. A first device and a second device transceive a plurality of sets of time-synchronization messages to synchronize a synchronization clock of the second device to a first clock of the first device. The second device calculates a smoothing of time delay data of a plurality of sets. The time delay data is associated with a transmission duration of time-synchronization messages of the sets of the plurality. The second device sets a synchronization clock based on a time at the first device and the smoothed time delay data.

Robust clock synchronization over computer network

Particulate matter, such as dust, steam, smoke, rain, etc. may cause one or more sensor types to generate false positive detections. In particular, various depth measurements may be impeded by particulate matter. Identifying a false return and/or removing a false detection based at least in part on a sensor output may comprise determining a similarity of a portion of a return signal to an emitted light pulse or an expected return signal, determining a variance of the signal portion over time, determining a difference between a power spectrum of the return relative to an expected power spectrum, and/or determining that a duration associated with the signal portion meets or exceeds a threshold duration.

Identifying and/or removing false positive detections from lidar sensor output

Techniques associated with generating or tuning parameters associated with long wave infrared sensor data to improve object detection associated with the captured images are discussed herein. The system may determine a region of interest associated with the sensor data and adjust or tune the parameters to improve detection(s) within the region of interest. Additionally, the system may adjust the parameters based on map data and/or environmental conditions, such as weather and temperature.

System for tuning parameters of a thermal sensor to improve object detection

System for tuning parameters of a thermal sensor based on a region of interest

Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. Sensor data generated by the time-of-flight sensor can include noise. In some examples, the sensor data is filtered by comparing a measured intensity value to a threshold intensity value. The threshold intensity value can be determined on a per-pixel basis using depth information and/or intensity information for a corresponding image frame.

Reducing noise in sensor data

A vehicle can include various components such as sensors and computing devices, as well as a network to couple the sensors and computing devices. A capability status can indicate an error with a computing device, available computational resources of a computing device, and/or an available bandwidth among others. Sensor data can be manipulated, based on the capability status, into various formats and/or sent to various destinations.

Growing community of inventors

San Mateo, CA, United States of America

Mehran Ferdowsi