Abstract: A system includes a first lidar sensor and a second lidar sensor, where each lidar sensor includes a scanner configured to direct a set of pulses of light along a scan pattern and a receiver configured to detect scattered light from the set of light pulses. The scan patterns are at least partially overlapped in an overlap region. The system further includes an enclosure, where the first lidar sensor and the second lidar sensor are contained within the enclosure. Each scanner includes one or more mirrors, and each mirror is driven by a scan mechanism.

Abstract: A method for detecting boundaries of lanes on a road is presented. The method comprises receiving, by one or more processors from an imaging system, a set of pixels associated with lane markings. The method further includes partitioning, by the one or more processors, the set of pixels into a plurality of groups. Each of the plurality of groups is associated with one or more control points. The method further includes generating, by the one or more processors, a spline that traverses the control points of the plurality of groups. The spline traversing the control points describes a boundary of a lane.

Abstract: To generate a machine learning model for controlling autonomous vehicles, training sensor data is obtained from sensors associated with one or more vehicles, the sensor data indicative of physical conditions of an environment in which the one or more vehicles operate, and a machine learning (ML) model is trained using the training sensor data. The ML model generates parameters of the environment in response to input sensor data. A controller in an autonomous vehicle receives sensor data from one or more sensors operating in the autonomous vehicle, applies the received sensor data to the ML model to obtain parameters of an environment in which the autonomous vehicle operates, provides the generated parameters to a motion planner component to generate decisions for controlling the autonomous vehicle, and causes the autonomous vehicle to maneuver in accordance with the generated decisions.

Abstract: A machine vision system comprises a camera configured to generate one or more images of a field of regard of the camera, a lidar system, and a processor. The lidar system includes a laser configured to emit light, where the emitted light is directed toward a region within the field of regard of the camera and a receiver configured to detect light returned from the emitted light. The processor is configured to receive an indication of a location based on the returned light and determine, based on the one or more images generated by the camera, whether the indication of the location is associated with a spurious return.

Abstract: A lidar system includes one or more light sources configured to generate a first beam of light and a second beam of light, a scanner configured to scan the first and second beams of light across a field of regard of the lidar system, and a receiver configured to detect the first beam of light and the second beam of light scattered by one or more remote targets. The scanner includes a rotatable polygon mirror that includes multiple reflective surfaces angularly offset from one another along a periphery of the polygon mirror, the reflective surfaces configured to reflect the first and second beams of light to produce a series of scan lines as the polygon mirror rotates. The scanner also includes a pivotable scan mirror configured to (i) reflect the first and second beams of light and (ii) pivot to distribute the scan lines across the field of regard.

Abstract: A lidar system for scanning a field of regard is described having first and second light beams and first and second detectors. The light beams pass through a lateral beam shifting device prior to being directed to a beam scanner. The lateral beam shifting device reduces the overall size of the emitted and returned light beams thus reducing the size of scanner components. Lateral beam shifting devices may be a single rhomboid prism, a pair of rhomboid prisms, a pair of mirrors, or a single mirror or prism.

Abstract: A method for tracking a lane on a road is presented. The method comprises receiving, by one or more processors from an imaging system, a set of pixels associated with lane markings. The method further includes generating, by the one or more processors, a predicted spline comprising (i) a first spline and (ii) a predicted extension of the first spline in a direction in which the imaging system is moving. The first spline describes a boundary of a lane and is generated based on the set of pixels. The predicted extension of the first spline is generated based at least in part on a curvature of at least a portion of the first spline.

Abstract: A scanner for a lidar system is configured to direct emitted light to scan a field of regard of the lidar system in accordance with a scan pattern. The scanner includes a mirror and an actuator assembly. The mirror includes a reflective surface and a rear surface and is pivotable along a mirror axle. The actuator assembly is disposed along the rear surface of the mirror and is configured to exert a torque on the mirror to cause the mirror to pivot about the mirror axle.

Abstract: In one embodiment, a lidar system includes a light source configured to emit multiple optical signals directed into a field of regard of the lidar system. The optical signals include a first optical signal and a second optical signal, where the second optical signal is emitted a particular time interval after the first optical signal is emitted. The lidar system also includes a receiver configured to detect a received optical signal that includes a portion of the emitted first or second optical signal that is scattered by a target located a distance from the lidar system. The received optical signal is detected after the second optical signal is emitted. The receiver includes a first detector configured to detect a first portion of the received optical signal and a second detector configured to detect a second portion of the received optical signal.

Abstract: Automated training dataset generators that generate feature training datasets for use in real-world autonomous driving applications based on virtual environments are disclosed herein. The feature training datasets may be associated with training a machine learning model to control real-world autonomous vehicles. In some embodiments, an occupancy grid generator is used to generate an occupancy grid indicative of an environment of an autonomous vehicle from an imaging scene that depicts the environment. The occupancy grid is used to control the vehicle as the vehicle moves through the environment. In further embodiments, a sensor parameter optimizer may determine parameter settings for use by real-world sensors in autonomous driving applications.

Abstract: In one embodiment, a lidar system includes a light source configured to emit (i) local-oscillator light and (ii) pulses of light, where each emitted pulse of light is coherent with a corresponding portion of the local-oscillator light. The light source includes a seed laser configured to produce seed light and the local-oscillator light. The light source also includes a pulsed optical amplifier configured to amplify temporal portions of the seed light to produce the emitted pulses of light, where each amplified temporal portion of the seed light corresponds to one of the emitted pulses of light. The lidar system also includes a receiver configured to detect the local-oscillator light and a received pulse of light, the received pulse of light including light from one of the emitted pulses of light that is scattered by a target located a distance from the lidar system.

Abstract: In one embodiment, a lidar system includes a light source configured to emit local-oscillator light and pulses of light, where each emitted pulse of light is (i) coherent with a corresponding portion of the local-oscillator light and (ii) includes a spectral signature of one or more different spectral signatures. The lidar system also includes a receiver configured to detect the local-oscillator light and a received pulse of light, the received pulse of light including light from one of the emitted pulses of light scattered by a target located a distance from the lidar system, the one of the emitted pulses of light including a particular spectral signature of the one or more spectral signatures. The local-oscillator light and the received pulse of light are coherently mixed together at the receiver. The receiver includes one or more detectors and a frequency-detection circuit.

Abstract: A lidar system identifies anomalous optical pulses received by the lidar system. The lidar system includes a light source configured to output a plurality of transmitted pulses of light, each transmitted pulse of light having one or more representative characteristics, a scanner configured to direct the plurality of transmitted pulses of light to a plurality of locations within a field of regard, and a receiver configured to detect a plurality of received pulses of light from the field of regard. The lidar system is configured to identify an anomalous pulse amongst the plurality of received pulses of light based on its having at least one characteristic that does not correspond to the one or more representative characteristics of the plurality of transmitted pulses of light.

Abstract: In one embodiment, a lidar system includes a light source configured to emit a pulse of light and a scanner configured to direct the emitted pulse of light into a field of regard of the lidar system. The lidar system also includes a receiver configured to receive a portion of the emitted pulse of light scattered by a target located a distance from the lidar system. The receiver includes a digital micromirror device (DMD) that includes a two-dimensional array of electrically addressable micromirrors, where a portion of the micromirrors are configured to be set to an active-on state to direct the received pulse of light to a detector array. The detector array includes a two-dimensional array of detector elements, where the detector array is configured to detect the received pulse of light and produce an electrical signal corresponding to the received pulse of light.

Abstract: A computer-implemented method of determining relative velocity between a vehicle and an object. The method includes receiving sensor data generated by one or more sensors of the vehicle. The one or more sensors are configured to sense an environment through which the vehicle is moving by following a scan pattern comprising component scan lines. The method includes obtaining, by one or more processors, a point cloud frame based on the sensor data and representative of the environment and identifying, by the one or more processors, a point cloud object within the point cloud frame. The method further includes determining, by the one or more processors, that the point cloud object is skewed relative to an expected configuration of the point cloud object, and determining, by the one or more processors, a relative velocity of the point cloud object by analyzing the skew of the object.

Abstract: In one embodiment, a lidar system includes a light source configured to emit an optical signal that is directed into a field of regard (FOR) of the lidar system. The lidar system also includes a receiver configured to: receive a portion of the emitted optical signal scattered by a target located in the FOR a distance from the lidar system; and produce an electrical signal corresponding to the received optical signal, where the electrical signal is related to a preliminary value of an optical characteristic of the received optical signal. The lidar system further includes a processor coupled to the receiver and configured to: determine the distance to the target; receive a humidity value; and determine a corrected value of the optical characteristic of the received optical signal based at least in part on the electrical signal produced by the receiver, the distance to the target, and the humidity value.

Abstract: In one embodiment, a lidar system includes a light source configured to emit multiple optical signals directed into a field of regard of the lidar system. The optical signals include: a first optical signal; a second optical signal emitted a first time period ?1 after the first optical signal; and a third optical signal emitted a second time period ?2 after the second optical signal, where ?2 is different from ?1. The lidar system also includes a receiver configured to detect a first input optical signal and a second input optical signal. The first and second input optical signals each include light from one of the emitted optical signals that is scattered by a target located a distance from the lidar system.

Abstract: In one embodiment, a lidar system includes a light source configured to emit pulses of light and a scanner configured to scan at least a portion of the emitted pulses of light along an interlaced scan pattern. The scanner includes a first scanning mirror configured to scan the portion of the emitted pulses of light substantially parallel to a first scan axis to produce multiple scan lines of the interlaced scan pattern, where each scan line is oriented substantially parallel to the first scan axis. The scanner also includes a second scanning mirror configured to distribute the scan lines along a second scan axis that is substantially orthogonal to the first scan axis, where the scan lines are distributed in an interlaced manner.

Abstract: In one embodiment, a lidar system includes a light source configured to emit pulses of light and a scanner configured to scan at least a portion of the emitted pulses of light across a field of regard. The field of regard contains all or part of a target located a distance from the lidar system that is less than or equal to a maximum range of the lidar system, and one or more of the emitted pulses of light are scattered by the target. The lidar system also includes a receiver configured to detect at least a portion of the pulses of light scattered by the target. The lidar system further includes a processor configured to determine the distance from the lidar system to the target based at least in part on a round-trip time of flight for an emitted pulse of light.

Abstract: To compensate for the uneven distribution of data points around the periphery of a vehicle in a lidar system, a light source transmits light pulses at a variable pulse rate according to the orientation of the light pulses with respect to the lidar system. A controller may communicate with a scanner in the lidar system that provides the orientations of the light pulses to the controller. The controller may then provide a control signal to the light source adjusting the pulse rate based on the orientations of the light pulses. For example, the pulse rate may be slower near the front of the lidar system and faster near the periphery. In another example, the pulse rate may be faster near the front of the lidar system and slower near the periphery.