Using cleaning protocols to monitor defects associated with Light Detection and Ranging (LIDAR) equipment

Abstract

To monitor defects associated with devices.SOLUTION: Example embodiments relate to using cleaning protocols to monitor defects associated with light detection and ranging (lidar) devices. An example embodiment includes a method. The method includes applying, using a cleaning device, a cleaning protocol to one or more optical components of a light detection and ranging (lidar) device. The method also includes emitting one or more light signals from a light emitter of the lidar device. Additionally, the method includes detecting, by a light detector of the lidar device, reflection of the one or more light signals. Further, the method includes determining, by a controller of the lidar device based on the detected reflection of the one or more light signals, that one or more defects are present within the one or more optical components or within the cleaning device.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] background Unless otherwise stated herein, the statements in this section are not prior art to the claims of this application and should not be admitted to be prior art by inclusion in this section. [Background technology]

[0002] Light detection and ranging (lidar) devices can estimate distances to objects in a surrounding environment by emitting light pulses into the surrounding environment and determining the respective time-of-flight of each light pulse. The time-of-flight of each light pulse can be used to estimate distances to reflecting objects in the surrounding environment and / or to create a three-dimensional point cloud indicative of reflecting objects in the surrounding environment. Additionally, cameras can be used to capture images of one or more objects in the surrounding environment. Such images can be used in object detection and avoidance methods (e.g., in vehicles operating in autonomous or semi-autonomous modes). However, imperfections along one or more optical paths of the lidar device and / or camera can lead to erroneous detections (e.g., erroneous point clouds, or blurry and / or unclear images). Summary of the Invention

[0003] Exemplary embodiments relate to techniques that include monitoring defects associated with a lidar device using cleaning protocols. These techniques may involve using a cleaning device to apply the cleaning protocol. For example, the cleaning protocol may include spraying a cleaning solution onto one or more components associated with the lidar device (e.g., one or more optical components, such as an optical window, a lens, a hydrophobic coating, or a mirror). As the cleaning protocol progresses, for example, when the cleaning solution begins to dry or is otherwise removed (e.g., by wiping the one or more optical components using a wiper of the cleaning device or by applying pressurized air onto the one or more optical components using a pressurized air source of the cleaning device), the light emitters of the lidar device may emit optical signals. These optical signals may be reflected (e.g., from the one or more optical components or from one or more defects on or in the one or more optical components) and subsequently detected by the optical detectors of the lidar device. By analyzing these detected optical signals, a computing device (e.g., a controller of the lidar device) may determine whether one or more defects exist within one or more optical components and / or within the cleaning device, and may further determine one or more qualities of the optical components (e.g., optical quality and hydrophobicity quality) based on the identified defects.

[0004] In a first aspect, a method is provided. The method includes applying a cleaning protocol to one or more optical components of the lidar device using a cleaning device of the lidar device. The method also includes emitting one or more optical signals from a light emitter of the lidar device. The method further includes detecting reflections of the one or more optical signals by a light detector of the lidar device. The method further includes determining, by a controller of the lidar device, that one or more defects exist in the one or more optical components or in the cleaning device based on the detected reflections of the one or more optical signals.

[0005] In a second aspect, a system is provided. The system includes a lidar device. The lidar device includes one or more optical components. The lidar device also includes a light emitter configured to emit one or more optical signals. Further, the lidar device includes a light detector configured to detect reflections of the one or more optical signals. The system also includes a cleaning device configured to apply a cleaning protocol to the one or more optical components. Further, the system includes a controller configured to determine, based on the detected reflections of the one or more optical signals, that one or more defects exist in the one or more optical components or in the cleaning device.

[0006] In a third aspect, a computing device is provided. The computing device is configured to receive data corresponding to reflections of one or more optical signals detected by a lidar device. The one or more optical signals are emitted by light emitters of the lidar device in response to a cleaning device of the lidar device applying a cleaning protocol to one or more optical components of the lidar device. The computing device is also configured to determine, based on the received data, that one or more defects exist in the one or more optical components or in the cleaning device.

[0007] These and other aspects, advantages, and alternatives will become apparent to those skilled in the art from a reading of the following detailed description, where appropriate with reference to the accompanying drawings. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a functional block diagram illustrating a vehicle, in accordance with an exemplary embodiment.

[0009] [Figure 2A] FIG. 2A is an illustrative diagram of a vehicle's physical configuration, according to an exemplary embodiment.

[0010] [Figure 2B] FIG. 2B is an illustrative diagram of a vehicle's physical configuration, according to an exemplary embodiment.

[0011] [Figure 2C] FIG. 2C is an illustrative diagram of a vehicle's physical configuration, in accordance with an exemplary embodiment.

[0012] [Figure 2D] FIG. 2D is an illustrative diagram of a vehicle's physical configuration in accordance with an exemplary embodiment.

[0013] [Figure 2E] FIG. 2E is an illustrative diagram of a vehicle's physical configuration, in accordance with an exemplary embodiment.

[0014] [Figure 2F] FIG. 2F is an illustrative diagram of a vehicle's physical configuration, according to an exemplary embodiment.

[0015] [Figure 2G] FIG. 2G is an illustrative diagram of a vehicle's physical configuration in accordance with an exemplary embodiment.

[0016] [Figure 2H] FIG. 2H is an illustrative diagram of a vehicle's physical configuration, in accordance with an exemplary embodiment.

[0017] [Figure 2I] FIG. 2I is an illustrative diagram of a vehicle's physical configuration, in accordance with an exemplary embodiment.

[0018] [Figure 2J] FIG. 2J is an illustrative diagram of the fields of view of various sensors in accordance with an illustrative embodiment.

[0019] [Figure 2K] FIG. 2K is an illustrative diagram of beam steering relative to a sensor in accordance with an example embodiment.

[0020] [Figure 3] FIG. 3 is a conceptual, illustrative diagram of wireless communication between various computing systems associated with an autonomous or semi-autonomous vehicle, in accordance with an example embodiment.

[0021] [Figure 4A] FIG. 4A is a block diagram of a system including a lidar device, in accordance with an exemplary embodiment.

[0022] [Figure 4B] FIG. 4B is a block diagram of a lidar device, in accordance with an exemplary embodiment.

[0023] [Figure 5] FIG. 5 is an illustrative diagram of a lidar device and associated hydrophobic coating, in accordance with an example embodiment.

[0024] [Figure 6A] FIG. 6A is an illustrative diagram of object detection in accordance with an example embodiment.

[0025] [Figure 6B] FIG. 6B is an illustrative diagram of crosstalk detection according to an example embodiment.

[0026] [Figure 6C]FIG. 6C is an illustrative diagram of cross-feedback detection in accordance with an example embodiment.

[0027] [Figure 6D] FIG. 6D is an illustrative diagram of occlusion detection in accordance with an example embodiment.

[0028] [Figure 7A] FIG. 7A is an illustrative diagram of a system having a cleaning device applying a cleaning protocol, according to an example embodiment.

[0029] [Figure 7B] FIG. 7B is an illustrative diagram of a system having a cleaning device applying a cleaning protocol, according to an example embodiment.

[0030] [Figure 8A] FIG. 8A is an illustrative diagram of a plot of the intensity of a detected reflected light signal and a fitted function associated with the plot of the intensity of the detected reflected light signal in accordance with an exemplary embodiment.

[0031] [Figure 8B] FIG. 8B is a scatter plot of metrics determined for a fleet of systems in accordance with an illustrative embodiment.

[0032] [Figure 9] FIG. 9 is a flowchart illustration of a method according to an example embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0033] Exemplary methods and systems are contemplated herein. Any illustrative embodiment or example feature described herein should not necessarily be construed as preferred or advantageous over other embodiments or features. Moreover, the illustrative embodiments described herein are not meant to be limiting. It will be readily understood that certain aspects of the disclosed systems and methods can be arranged and combined in a wide variety of different configurations, all of which are contemplated herein. Additionally, the specific arrangements shown in the figures should not be considered limiting. It should be understood that other embodiments can include more or fewer of each element shown in a given figure. Additionally, some of the illustrated elements can be combined or omitted. Still further, exemplary embodiments may include elements not illustrated in the figures.

[0034] The lidar devices described herein may include one or more light emitters and one or more detectors used to detect light emitted by the one or more light emitters and reflected by one or more objects in the environment surrounding the lidar device. By way of example, the surrounding environment may include an interior or exterior environment, such as the inside or outside of a building. Additionally or alternatively, the surrounding environment may include the interior of a vehicle. Still further, the surrounding environment may include the surroundings around and / or on a road. Examples of objects in the surrounding environment include, but are not limited to, other vehicles, traffic signs, pedestrians, bicyclists, road surfaces, buildings, terrain, etc. Additionally, the one or more light emitters may emit light into the local environment of the lidar itself. For example, light emitted from the one or more light emitters may interact with the housing of the lidar and / or surfaces or structures coupled to the lidar. In some cases, the lidar may be mounted on a vehicle, in which case the one or more light emitters may be configured to emit light that interacts with objects in the vicinity of the vehicle. The light emitters may include fiber optic amplifiers, laser diodes, light-emitting diodes (LEDs), among other possibilities.

[0035] Lidar devices and / or cameras can be used to sense the surrounding environment. For example, a lidar device can be used to generate a point cloud associated with the environment surrounding the autonomous vehicle, which can be used by the autonomous vehicle for object detection and avoidance. Such lidar devices and / or cameras can include one or more optical components. For example, the lidar devices and / or cameras can include optical windows, mirrors, lenses, etc.

[0036] In some cases, the captured image or generated point cloud may be adversely affected as a result of one or more defects on or in the optical components within the camera or lidar device (e.g., as a result of contamination of the aperture and / or degradation of the aperture over time). For example, scratches, cracks, dirt, deformations, bubbles, impurities, deterioration, discoloration, imperfect transparency, distortions, water droplets, stains, dust, mud, leaves, rain, snow, sleet, hail, ice, etc., can direct light emitted from the lidar light emitter to unintended / incorrect areas of the image sensor / photodetector, prevent the light from the lidar light emitter from even reaching the image sensor / photodetector, result in undesirable crosstalk or internal reflections, or alter the light emitted from the lidar light emitter (e.g., change its polarization or wavelength) before it reaches the image sensor / photodetector. Such defects can result in improper object identification and distance detection. In autonomous vehicle applications, improper object identification and distance detection can lead to vehicle slowdowns or collisions. Thus, many lidar devices / cameras (e.g., lidar devices / cameras mounted on autonomous vehicles) may also include cleaning devices (e.g., wipers, cleaning nozzles / sprayers, and air compressors configured to apply pressurized air) that can be used to clean components of the lidar device / camera. For example, the lidar device may include a cleaning sprayer used to deposit a cleaning solution on an exterior window of the lidar device, and / or a wiper used to remove the cleaning solution from the exterior window after it has been deposited.

[0037] The exemplary embodiments described herein provide techniques for identifying the presence of one or more defects. Furthermore, the exemplary embodiments enable debris detection without additional detection components (e.g., additional optics, emitters, and sensors). For example, to detect the presence and / or monitor the condition of debris (e.g., condensation, snow, and rain) on one or more components (e.g., the degradation state of a hydrophobic coating on a surface on an exterior window) over time, one or more cleaning components may be used to apply moisture to the one or more components. For example, a sprayer may be used to apply water or a cleaning solution to the hydrophobic coating on the surface of an exterior window. Optical signals reflected from the water / cleaning solution and / or internal components of the lidar device (e.g., cross-feedback signals, cross-talk signals, and signals interacting with objects external to the lidar device) may then be analyzed to determine the health (e.g., amount of degradation) of the hydrophobic coating. For example, one or more optical signals emitted by the light emitter that are reflected (or partially reflected) from the water / cleaning solution and then detected by the optical detector are compared to calibration measurements (e.g., made when the lidar device is on the manufacturing line or being assembled) to determine the current state of the hydrophobic coating (e.g., how droplets bead on the surface of the hydrophobic coating and / or how quickly they shed from the hydrophobic coating). In some embodiments, detection of the optical signals can occur while one or more additional cleaning techniques are performed (e.g., while one or more applications of pressurized air, i.e., air puffs, are occurring).

[0038] Analyzing the reflected light signal may include monitoring the intensity of the reflected light signal over time. For example, when a cleaning solution is sprayed onto the optical window of the lidar device, the light signal emitted toward the optical window may be substantially reflected back toward the detector of the lidar device. This may result in a relatively high intensity detected light signal with a short transit time (e.g., due to reflection from droplets of cleaning solution on the window). Conversely, as the cleaning solution evaporates / migrates from the optical window (e.g., due to the application of pressurized air by the cleaning device), the intensity of the detected light signal within a short time window (e.g., corresponding to a short transit time) may decrease (e.g., because fewer droplets of cleaning solution are present on the optical window). In various embodiments, this decrease may be observed in data corresponding to all or only a subset of the photodetectors of the lidar device. However, by monitoring this decrease over time (e.g., by plotting the detected reflected intensity against time), a trend can be observed. The trend may be fitted to one or more curves / functions. For example, the controller of the lidar device may fit the trend to an exponential decay function. Such fitted exponential decay functions may have one or more figures of merit. For example, the initial / peak values ​​and time constant associated with the exponential decay may be used as figures of merit. These figures of merit can be tracked over time and / or compared to one or more calibration measurements to determine the state of the lidar device (e.g., the health of the optical window and the health of the cleaning device itself). For example, if the initial value of the exponential decay function is too low compared to the calibration measurements, it may be an indication that the sprayer of the cleaning device is not providing enough liquid to the surface of the optical component (e.g., the cleaning solution in the cleaning device needs to be refilled). Alternatively, if the time constant is too high compared to the calibration measurements, it may be an indication that the associated hydrophobic coating has degraded (e.g., resulting in a decrease in hydrophobicity). Other types of fitted functions and / or other figures of merit are possible and are contemplated herein.

[0039] In some embodiments, analysis of the detected signals (e.g., comparison with calibration measurements) may take additional factors into account when determining the condition of the hydrophobic coating. For example, if a sprayer is applying water / cleaning solution to the hydrophobic coating, but there is additional rain / snow in the surrounding environment (e.g., as determined by an auxiliary sensor such as a radar device), the series of detected optical signals may be artificially modified (e.g., an offset may be applied to the intensity of the series of detected optical signals) to simulate a series of signals in the absence of rain / snow, and then that simulated series of signals may be compared to the calibration measurements. Alternatively, there may be a bank of calibration measurements taken under various environmental conditions to which run-time measurements can be compared (e.g., based on the environmental conditions when the run-time measurements were taken) to determine the condition of the hydrophobic coating.

[0040] To monitor the condition / health of the lidar device's components, these cleaning techniques may be performed (and the corresponding optical signals analyzed) at regular intervals. For example, the lidar device may perform a cleaning protocol and learn characteristics of the reflected optical signal once a month, once a week, once a day, once an hour, once every 15 minutes, once a minute, etc. Additionally or alternatively, the cleaning techniques may be performed (and the corresponding optical signals analyzed) in response to a trigger event. For example, a user (e.g., a lidar in an autonomous vehicle) may send one or more signals to the lidar device (e.g., via a vehicle user interface or using a mobile application on a mobile device) to request cleaning or to indicate that a component reliability analysis should be performed. Upon receiving such a signal, the lidar device may initiate a cleaning protocol. Other triggering events are possible and contemplated herein (e.g., a weather event, a communication from an off-board computing device such as a fleet management device, a determination by the controller of the lidar device that one or more objects detected in the surrounding environment have been improperly identified, a determination made by the lidar controller that one or more detected optical signals, such as detected cross-feedback signals or detected crosstalk signals, exceed a given intensity threshold).

[0041] Furthermore, upon determining using the techniques described herein that one or more defects exist within one or more components associated with the lidar device (e.g., degradation of one or more optical components, one or more defects present within one or more optical components, and debris on one or more optical components), appropriate corrective action may be initiated. For example, additional cleaning protocols may be implemented (e.g., longer cleaning protocols or escalated cleaning protocols, such as cleaning protocols using more concentrated solutions or enhanced pressurized airflow). Alternatively, one or more optical components associated with the one or more defects may be repaired or replaced. In yet other embodiments, data captured via one or more optical components associated with the one or more defects may be flagged for potential review and / or flagged as potentially unreliable. In still other embodiments, post-processing may be performed on data captured via one or more optical components to account for the effect of defects present within the one or more optical components. For example, if a defect results in a decrease in apparent range to objects in the surrounding environment, an offset to the range may be applied to correct the data. Similarly, if a defect results in a decrease in the apparent intensity of an optical signal reflected by objects in the surrounding environment, an offset to the intensity may be applied to correct the data.

[0042] The following description and accompanying drawings highlight features of various exemplary embodiments. The embodiments provided are by way of example and are not intended to be limiting. Accordingly, dimensions of the drawings are not necessarily to scale.

[0043] Exemplary systems within the scope of the present disclosure will now be described in more detail. The exemplary system may be implemented in or take the form of an automobile. Additionally, the exemplary system may also be implemented in or take the form of a variety of vehicles, such as cars, trucks (e.g., pickup trucks, vans, tractors, and tractor-trailers), motorcycles, buses, airplanes, helicopters, drones, lawn mowers, bulldozers, boats, submarines, all-terrain vehicles, snowmobiles, aircraft, recreational vehicles, amusement park vehicles, farm equipment or vehicles, construction machinery or vehicles, warehouse equipment or vehicles, factory equipment or vehicles, trams, golf carts, trains, trolleys, walkway transport vehicles, robotic devices, etc. Other vehicles are possible as well. Furthermore, in some embodiments, the exemplary system may not include a vehicle.

[0044] Referring now to the figures, FIG. 1 is a functional block diagram illustrating an example vehicle 100 that may be configured to operate fully or partially in an autonomous mode. More specifically, vehicle 100 may operate in the autonomous mode without human interaction through receiving control instructions from a computing system. As part of its operation in the autonomous mode, vehicle 100 may use sensors to detect and possibly identify objects in the surrounding environment to enable safe navigation. Additionally, example vehicle 100 may operate in a partially autonomous (i.e., semi-autonomous) mode in which some functions of vehicle 100 are controlled by a human driver of vehicle 100 and some functions of vehicle 100 are controlled by a computing system. For example, vehicle 100 may also include subsystems that enable the driver to control the operation of vehicle 100, such as steering, acceleration, and braking, while the computing system performs assistance functions, such as lane departure warning / lane keeping assist or adaptive cruise control, based on other objects (e.g., vehicles) in the surrounding environment.

[0045] As described herein, in a partially autonomous driving mode, the vehicle assists with one or more driving operations (e.g., steering, braking, and / or accelerating to perform lane centering, adaptive cruise control, advanced driver assistance systems (ADAS), and emergency braking), but the human driver is expected to maintain situational awareness of the vehicle's surroundings and supervise the assisted driving operations. Here, the vehicle may perform all driving tasks in certain situations, but the human driver is expected to be responsible for assuming control as needed.

[0046] For simplicity and brevity, various systems and methods are described below in conjunction with autonomous vehicles; however, these or similar systems and methods may be used in various driver assistance systems that fall short of a fully autonomous driving system (i.e., a partially autonomous driving system). In the United States, the Society of Automotive Engineers (SAE) defines different levels of automated driving behavior to indicate how much or how little control the vehicle has over the driving; however, different organizations in the United States or other countries may classify the levels differently. More specifically, the disclosed systems and methods may be used in SAE Level 2 driver assistance systems, which implement steering, braking, acceleration, lane centering, adaptive cruise control, and other driver assistance functions. The disclosed systems and methods may be used in SAE Level 3 driver assistance systems, which are capable of autonomous driving under limited (e.g., highway) conditions. Similarly, the disclosed systems and methods may be used in vehicles using SAE Level 4 automated driving systems, which operate autonomously under most normal driving conditions and require only occasional attention from a human operator. In all such systems, accurate lane estimation is performed automatically without driver input or control (e.g., while the vehicle is moving), resulting in improved reliability of vehicle positioning and navigation, and overall safety of autonomous, semi-autonomous, and other driver assistance systems. As noted above, in addition to the manner in which the SAE classifies levels of autonomous driving operation, other organizations in the United States or other countries may classify levels of autonomous driving operation differently. Without limitation, the systems and methods disclosed herein may be used with driver assistance systems defined by these other organizations' levels of autonomous driving operation.

[0047] 1 , vehicle 100 may include various subsystems, such as propulsion system 102, sensor system 104, control system 106, one or more peripheral devices 108, power source 110, computer system 112 (which may also be referred to as a computing system) having data storage 114, and user interface 116. In other examples, vehicle 100 may include more or fewer subsystems, each of which may include multiple elements. The subsystems and components of vehicle 100 may be interconnected in various ways. Additionally, the functionality of vehicle 100 described herein may be divided into additional functional or physical components or combined into fewer functional or physical components within an embodiment. For example, control system 106 and computer system 112 may be combined into a single system that operates vehicle 100 according to various operations.

[0048] Propulsion system 102 may include one or more components operable to provide powered motion for vehicle 100 and may include, among other possible components, an engine / motor 118, an energy source 119, a transmission 120, and wheels / tires 121. For example, engine / motor 118 may be configured to convert energy source 119 into mechanical energy and may correspond to one or a combination of an internal combustion engine, an electric motor, a steam engine, or a Stirling engine, among other possible options. For example, in some embodiments, propulsion system 102 may include multiple types of engines and / or motors, such as gasoline engines and electric motors.

[0049] Energy source 119 represents an energy source that may fully or partially power one or more systems (e.g., engine / motor 118) of vehicle 100. For example, energy source 119 may correspond to gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and / or other power sources. In some embodiments, energy source 119 may include a combination of a fuel tank, batteries, a capacitor, and / or a flywheel.

[0050] The transmission 120 may transfer mechanical power from the engine / motor 118 to the wheels / tires 121 and / or other possible systems of the vehicle 100. As such, the transmission 120 may include, among other possible components, a gearbox, a clutch, a differential, and a drive shaft. The drive shaft may include an axle that connects to one or more wheels / tires 121.

[0051] The wheels / tires 121 of the vehicle 100 may have a variety of configurations within the exemplary embodiment. For example, the vehicle 100 may exist in the form of a unicycle, a bicycle / motorcycle, a tricycle, or four wheels of a car / truck, among other possible configurations. Thus, the wheels / tires 121 may be connected to the vehicle 100 in a variety of ways and may exist in different materials, such as metal and rubber.

[0052] The sensor system 104 may include various types of sensors, such as a global positioning system (GPS) 122, an inertial measurement unit (IMU) 124, radar 126, lidar 128, a camera 130, a steering sensor 123, and a throttle / brake sensor 125, among other possible sensors. In some embodiments, the sensor system 104 may also include sensors configured to monitor internal systems of the vehicle 100 (e.g., an O monitor, a fuel gauge, engine oil temperature, and brake wear).

[0053] The GPS 122 may include a transceiver operable to provide information regarding the position of the vehicle 100 relative to the Earth. The IMU 124 may be configured to use one or more accelerometers and / or gyroscopes to sense changes in the position and orientation of the vehicle 100 based on inertial acceleration. For example, the IMU 124 may detect the pitch and yaw of the vehicle 100 while the vehicle 100 is stationary or moving.

[0054] Radar 126 may represent one or more systems configured to sense objects in the environment surrounding vehicle 100 using radio signals, including the object's speed and orientation. Thus, radar 126 may include an antenna configured to transmit and receive radio signals. In some embodiments, radar 126 may correspond to an attachable radar configured to obtain measurements of the environment surrounding vehicle 100.

[0055] The LIDAR 128 may include one or more laser sources, a laser scanner, and one or more detectors, among other system components, and may operate in a coherent mode (e.g., using heterodyne detection, etc.) or an incoherent detection mode (i.e., time-of-flight mode). In some embodiments, the one or more detectors of the LIDAR 128 may include one or more photodetectors, which may be particularly sensitive detectors (e.g., avalanche photodiodes). In some examples, such photodetectors may be capable of detecting single photons (e.g., single-photon avalanche diodes (SPADs)). Furthermore, such photodetectors may be arranged in an array (e.g., as with silicon photomultipliers (SiPMs)) (e.g., through serial electrical connections). In some examples, the one or more photodetectors are devices operating in Geiger mode, and the LIDAR includes subcomponents designed for such Geiger mode operation.

[0056] Camera 130 may include one or more devices (e.g., a still camera, a video camera, a thermal imaging camera, a stereo camera, and a night vision camera) configured to capture images of the environment surrounding vehicle 100.

[0057] Steering sensor 123 may sense the steering angle of vehicle 100, which may include measuring the angle of the steering wheel or measuring an electrical signal representative of the angle of the steering wheel. In some embodiments, steering sensor 123 may measure the angle of the wheels of vehicle 100, such as detecting the angle of the wheels relative to the forward axle of vehicle 100. Steering sensor 123 may also be configured to measure a combination (or subset) of the steering wheel angle, the electrical signal representative of the steering wheel angle, and the angle of the wheels of vehicle 100.

[0058] The throttle / brake sensor 125 may detect either the throttle position or the brake position of the vehicle 100. For example, the throttle / brake sensor 125 may measure the angle of both the accelerator pedal (throttle) and the brake pedal, or may measure an electrical signal representative of, for example, the accelerator pedal (throttle) angle and / or the brake pedal angle. The throttle / brake sensor 125 may also measure the angle of a throttle body of the vehicle 100, which may include part of the physical mechanism that provides modulation of the energy source 119 to the engine / motor 118 (e.g., a butterfly valve and a carburetor). Additionally, the throttle / brake sensor 125 may measure the pressure of one or more brake pads on a rotor of the vehicle 100, or a combination (or subset) of the accelerator pedal (throttle) and the brake pedal angle, an electrical signal representative of the accelerator pedal (throttle) and the brake pedal angle, the throttle body angle, and the pressure applied by at least one brake pad to a rotor of the vehicle 100. In other embodiments, the throttle / brake sensor 125 may be configured to measure pressure applied to a vehicle pedal, such as a throttle or brake pedal.

[0059] The control system 106 may include components configured to assist in navigating the vehicle 100, such as a steering unit 132, a throttle 134, a braking unit 136, a sensor fusion algorithm 138, a computer vision system 140, a navigation / pathfinding system 142, and an obstacle avoidance system 144. More specifically, the steering unit 132 may be operable to adjust the heading of the vehicle 100, and the throttle 134 may control the operating speed of the engine / motor 118 to control the acceleration of the vehicle 100. The braking unit 136 may decelerate the vehicle 100, which may involve slowing the wheels / tires 121 using friction. In some embodiments, the braking unit 136 may convert the kinetic energy of the wheels / tires 121 into electrical current for subsequent use by one or more systems of the vehicle 100.

[0060] The sensor fusion algorithm 138 may include a Kalman filter, a Bayesian network, or other algorithm capable of processing data from the sensor system 104. In some embodiments, the sensor fusion algorithm 138 may provide an assessment based on the incoming sensor data, such as an assessment of individual objects and / or features, an assessment of a particular situation, and / or an assessment of possible effects within a given situation.

[0061] Computer vision system 140 may include hardware and software (e.g., a general-purpose processor such as a central processing unit (CPU), a special-purpose processor such as a graphics processing unit (GPU) or a tensor processing unit (TPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), volatile memory, non-volatile memory, or one or more machine learning models) operable to process and analyze images to determine moving objects (e.g., other vehicles, pedestrians, bicyclists, or animals) and non-moving objects (e.g., traffic signals, roadway boundaries, speed bumps, or potholes). Thus, computer vision system 140 may employ object recognition, structure-from-motion (SFM), video tracking, and other algorithms used in computer vision, for example, to recognize objects, map the environment, track objects, estimate object speed, etc.

[0062] Navigation / routing system 142 may determine a driving path for vehicle 100, which may involve dynamically adjusting navigation during operation. Thus, navigation / routing system 142 may use data from sensor fusion algorithms 138, GPS 122, and maps, among other sources, to navigate vehicle 100. Obstacle avoidance system 144 may evaluate potential obstacles based on sensor data and cause systems of vehicle 100 to avoid or otherwise navigate the potential obstacles.

[0063] 1 , vehicle 100 may also include peripherals 108, such as a wireless communication system 146, a touchscreen 148, an internal microphone 150, and / or a speaker 152. Peripherals 108 may provide controls or other elements for a user to interact with a user interface 116. For example, touchscreen 148 may provide information to a user of vehicle 100. User interface 116 may also accept input from a user via touchscreen 148. Peripherals 108 may also enable vehicle 100 to communicate with devices, such as devices in other vehicles.

[0064] The wireless communication system 146 may communicate with one or more devices directly or wirelessly via a communication network. For example, the wireless communication system 146 may use 3G cellular communications such as Code Division Multiple Access (CDMA), Evolution Data Optimized (EVDO), Global System for Mobile Communications (GSM) / General Packet Radio Service (GPRS), or 4G Worldwide Interoperability for Microwave Access (WiMAX) or Long Term Evolution (LTE), or 5G. Alternatively, the wireless communication system 146 may communicate with a wireless local area network (WLAN) using Wi-Fi or other possible connections. The wireless communication system 146 may also communicate directly with devices using, for example, an infrared link, Bluetooth, or ZigBee. Other wireless protocols, such as various vehicle communication systems, are possible within the context of this disclosure. For example, the wireless communication system 146 may include one or more dedicated short-range communication (DSRC) devices, which may include public and / or private data communications between vehicles and / or roadside gas stations.

[0065] Vehicle 100 may include a power source 110 for powering its components. Power source 110, in some embodiments, may include a rechargeable lithium-ion or lead-acid battery. For example, power source 110 may include one or more batteries configured to provide power. Vehicle 100 may also use other types of power sources. In an exemplary embodiment, power source 110 and energy source 119 may be integrated into a single energy source.

[0066] Vehicle 100 may also include a computer system 112 for performing operations such as those described therein. Accordingly, computer system 112 may include at least one processor 113 (which may include at least one microprocessor) operable to execute instructions 115 stored in a non-transitory computer-readable medium, such as data storage 114. In some embodiments, computer system 112 may represent multiple computing devices that may function to control individual components or subsystems of vehicle 100 in a distributed manner.

[0067] In some embodiments, data storage 114 may include instructions 115 (e.g., program logic) executable by processor 113 for performing various functions of vehicle 100, including those described above in connection with Figure 1. Data storage 114 may also include additional instructions, including instructions for transmitting data to, receiving data from, interacting with, and / or controlling one or more of propulsion system 102, sensor system 104, control system 106, and peripherals 108.

[0068] In addition to instructions 115, data storage 114 may store data such as road maps, route information, etc., among other information. Such information may be used by vehicle 100 and computer system 112 during operation of vehicle 100 in autonomous, semi-autonomous, and / or manual modes.

[0069] Vehicle 100 may include a user interface 116 for providing information to or receiving input from a user of vehicle 100. User interface 116 may control or allow control of the layout of content and / or interactive images that may be displayed on touchscreen 148. Additionally, user interface 116 may include one or more input / output devices in the set of peripherals 108, such as wireless communication system 146, touchscreen 148, microphone 150, and speaker 152.

[0070] Computer system 112 may control functions of vehicle 100 based on inputs received from various subsystems (e.g., propulsion system 102, sensor system 104, or control system 106) and from user interface 116. For example, computer system 112 may utilize inputs from sensor system 104 to estimate outputs generated by propulsion system 102 and control system 106. Depending on the embodiment, computer system 112 may be operable to monitor many aspects of vehicle 100 and its subsystems. In some embodiments, computer system 112 may disable some or all functions of vehicle 100 based on signals received from sensor system 104.

[0071] Components of vehicle 100 may be configured to function in an interconnected manner with other components within or outside their respective systems. For example, in an exemplary embodiment, camera 130 may capture multiple images that may represent information about the state of the environment surrounding vehicle 100 operating in an autonomous or semi-autonomous mode. The state of the environment may include parameters of the road on which the vehicle is operating. For example, computer vision system 140 may be capable of recognizing slopes (gradients) or other features based on multiple images of the road. Additionally, the combination of GPS 122 and features recognized by computer vision system 140 may be used along with map data stored in data storage 114 to determine specific road parameters. Furthermore, radar 126 and / or lidar 128, and / or some other environmental mapping, range, and / or positioning sensor system may also provide information about the vehicle's surroundings.

[0072] In other words, a combination of various sensors (which may be referred to as input indicator sensors and output indicator sensors) and computer system 112 may interact to provide an indication of the inputs or the vehicle's surroundings that are provided to control the vehicle.

[0073] In some embodiments, computer system 112 may make decisions regarding various objects based on data provided by systems other than a wireless system. For example, vehicle 100 may have laser or other optical sensors configured to sense objects within the vehicle's field of view. Computer system 112 may use output from the various sensors to determine information about objects within the vehicle's field of view and may determine distance and direction information to the various objects. Computer system 112 may also determine whether an object is desirable or undesirable based on output from the various sensors.

[0074] 1 depicts various components of vehicle 100 (i.e., wireless communication system 146, computer system 112, data storage 114, and user interface 116) as being integrated into vehicle 100, one or more of these components may be separately mounted or associated with vehicle 100. For example, data storage 114 may exist partially or completely separate from vehicle 100. Thus, vehicle 100 may be provided in the form of device elements that may be located separately or together. The device elements that make up vehicle 100 may be communicatively coupled together in a wired and / or wireless manner.

[0075] 2A-2E show an example vehicle 200 (e.g., a fully autonomous or semi-autonomous vehicle) that may include some or all of the functionality described in connection with vehicle 100 with reference to FIG. 1. Vehicle 200 is illustrated in FIGS. 2A-2E as a van with side mirrors for illustrative purposes, but the present disclosure is not so limited. For example, vehicle 200 may represent a truck, a passenger car, a semi-trailer truck, a motorcycle, a golf cart, an off-road vehicle, an agricultural vehicle, or any other vehicle described elsewhere herein (e.g., a bus, a boat, an airplane, a helicopter, a drone, a lawn mower, a bulldozer, a submarine, an all-terrain vehicle, a snowmobile, an aircraft, a recreational vehicle, an amusement park vehicle, farm equipment, construction machinery or vehicles, warehouse equipment or vehicles, factory equipment or vehicles, a tram, a train, a trolley, a walkway transport vehicle, and a robotic device).

[0076] Exemplary vehicle 200 may include one or more sensor systems 202, 204, 206, 208, 210, 212, 214, and 218. In some embodiments, sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may represent one or more optical systems (e.g., cameras), one or more lidars, one or more radars, one or more inertial sensors, one or more humidity sensors, one or more acoustic sensors (e.g., microphones and sonar devices), or one or more other sensors configured to sense information about the environment surrounding vehicle 200. In other words, any sensor system now known or hereafter created may be coupled to vehicle 200 and / or utilized in conjunction with various operations of vehicle 200. As an example, lidar may be utilized for autonomous driving or other types of navigation, planning, perception, and / or mapping operations of vehicle 200. Additionally, sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may represent a combination of sensors described herein (e.g., one or more lidars and radars, one or more lidars and cameras, one or more cameras and radars, one or more lidars, cameras, and radars).

[0077] 2A-E are intended as non-limiting examples of the locations, numbers, and types of such sensor systems in an autonomous or semi-autonomous vehicle. Alternative numbers, locations, types, and configurations of such sensors are possible (e.g., to accommodate vehicle size, shape, aerodynamics, fuel economy, aesthetics, or other requirements to reduce cost or suit a particular environment or application). For example, sensor systems (e.g., 202 and 204) may be disposed in various other locations on the vehicle (e.g., at location 216) and may have fields of view corresponding to the interior and / or surrounding environment of vehicle 200.

[0078] Sensor system 202 may include one or more sensors mounted on top of vehicle 200 and configured to detect information about the environment surrounding vehicle 200 and output an indication of the information. For example, sensor system 202 may include any combination of cameras, radar, lidar, inertial sensors, humidity sensors, and acoustic sensors (e.g., microphones and sonar devices). Sensor system 202 may include one or more movable mounts that may be operable to adjust the orientation of one or more sensors in sensor system 202. In one embodiment, the movable mount may include a rotating platform that can scan the sensors to obtain information from each direction around vehicle 200. In another embodiment, the movable mount of sensor system 202 may be movable in a scanning manner within a specific angular and / or azimuth and / or elevation angle range. Sensor system 202 may be mounted on the roof of a vehicle, although other mounting locations are also possible.

[0079] Additionally, the sensors of sensor system 202 may be distributed at various locations and need not be co-located at a single location. Further, each sensor of sensor system 202 may be configured to be moved or scanned independently of the other sensors of sensor system 202. Additionally or alternatively, multiple sensors may be mounted at one or more of sensor locations 202, 204, 206, 208, 210, 212, 214, and / or 218. For example, there may be two lidar devices mounted at a sensor location, and / or there may be one lidar device and one radar mounted at a sensor location.

[0080] One or more of sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may include one or more lidar sensors. For example, a lidar sensor may include multiple light emitter devices arranged over a range of angles relative to a given plane (e.g., the x-y plane). For example, one or more of sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may be configured to rotate or pivot about an axis perpendicular to the given plane (e.g., the z-axis) to illuminate the environment surrounding vehicle 200 with light pulses. Based on detecting various aspects of the reflected light pulses (e.g., the elapsed time of flight, polarization, and intensity), information about the surrounding environment may be determined.

[0081] In an exemplary embodiment, sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may be configured to provide respective point cloud information that may be associated with physical objects within the surrounding environment of vehicle 200. While vehicle 200 and sensor systems 202, 204, 206, 208, 210, 212, 214, and 218 are illustrated as including particular features, it will be understood that other types of sensor systems are contemplated within the scope of the present disclosure. Additionally, exemplary vehicle 200 may include any of the components described in connection with vehicle 100 of FIG. 1 .

[0082] In an exemplary configuration, one or more radars may be located on vehicle 200. Similar to radar 126 described above, the one or more radars may include an antenna configured to transmit and receive radio waves (e.g., electromagnetic waves having frequencies between 30 Hz and 300 GHz). Such radio waves may be used to determine the distance and / or speed of one or more objects in the vehicle 200's surrounding environment. For example, one or more sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may include one or more radars. In some examples, one or more radars may be located near the rear of vehicle 200 (e.g., sensor systems 208 and 210) to actively scan the environment near the rear of vehicle 200 for the presence of radio wave-reflecting objects. Similarly, one or more radars may be located near the front of vehicle 200 (e.g., sensor systems 212 and 214) to actively scan the environment near the front of vehicle 200. The radar may be positioned in a location suitable for illuminating an area including the forward path of vehicle 200, for example, without being obstructed by other features of vehicle 200. For example, the radar may be embedded in and / or mounted on or near the front bumper, front headlights, cowl, and / or hood, etc. Furthermore, one or more additional radars may be positioned to actively scan the sides and / or rear of vehicle 200 for the presence of radio wave reflective objects, such as by including such devices on or near the rear bumper, side panels, rocker panels, and / or undercarriage, etc.

[0083] Vehicle 200 may include one or more cameras. For example, one or more sensor systems 202, 204, 206, 208, 210, 212, 214, and / or 218 may include one or more cameras. The cameras may be light-sensitive devices, such as still cameras, video cameras, thermal imaging cameras, stereo cameras, night-vision cameras, etc., configured to capture multiple images of the environment surrounding vehicle 200. To this end, the cameras may be configured to detect visible light and, additionally or alternatively, may be configured to detect light from other parts of the spectrum, such as infrared or ultraviolet light. The cameras may be two-dimensional detectors and, optionally, may have a sensitivity range in three-dimensional space. In some embodiments, the cameras may include range detectors configured to generate two-dimensional images indicating, for example, the distance from the camera to points in the surrounding environment. To this end, the cameras may use one or more range-sensing techniques. For example, the camera can provide range information by using structured light techniques, in which the vehicle 200 illuminates objects in the surrounding environment with a predetermined light pattern, such as a grid or checkerboard pattern, and uses the camera to detect reflections of the predetermined light pattern from the surrounding environment. Based on distortions in the reflected light pattern, the vehicle 200 can determine the distance to a point on the object. The predetermined light pattern may include infrared light or other wavelengths of radiation suitable for such measurements. In some examples, the camera may be mounted inside the windshield of the vehicle 200. Specifically, the camera may be positioned to capture images from a forward-looking perspective relative to the orientation of the vehicle 200. Other mounting locations and viewing angles for the camera, whether interior or exterior of the vehicle 200, may be used. The camera may also have associated optics operable to provide an adjustable field of view. Furthermore, the camera may be mounted to the vehicle 200 using a movable mount to change the pointing angle of the camera, such as via a pan / tilt mechanism.

[0084] Vehicle 200 may also include one or more acoustic sensors used to sense the vehicle's surrounding environment (e.g., one or more of sensor systems 202, 204, 206, 208, 210, 212, 214, 216, 218 may include one or more acoustic sensors). Acoustic sensors may include microphones (e.g., piezoelectric microphones, condenser microphones, ribbon microphones, and microelectromechanical systems (MEMS) microphones) used to sense acoustic waves (i.e., pressure differentials) in the fluid (e.g., air) of the environment surrounding vehicle 200. Such acoustic sensors may be used to identify sounds in the surrounding environment (e.g., sirens, human speech, animal sounds, and alarms) upon which a control strategy for vehicle 200 may be based. For example, if an acoustic sensor detects a siren (e.g., a mobile siren and / or a fire engine siren), vehicle 200 may slow down and / or navigate to the curb of the road.

[0085] Although not shown in FIGS. 2A-2E, vehicle 200 may include a wireless communication system (e.g., similar to and / or in addition to wireless communication system 146 of FIG. 1). The wireless communication system may include a wireless transmitter and a wireless receiver that may be configured to communicate with devices external or internal to vehicle 200. Specifically, the wireless communication system may include a transceiver configured to communicate with other vehicles and / or computing devices, for example, in a vehicle communication system or roadside gas station. Examples of such vehicle communication systems include DSRC, radio frequency identification (RFID), and other communication standards proposed for intelligent transport systems.

[0086] Vehicle 200 may include one or more other components in addition to or instead of those shown. The additional components may include electrical or mechanical functions.

[0087] A control system of vehicle 200 may be configured to control vehicle 200 according to a control strategy from among a plurality of possible control strategies. The control system may be configured to receive information from sensors (on or off vehicle 200) coupled to vehicle 200, modify the control strategy (and associated driving behavior) based on the information, and control vehicle 200 according to the modified control strategy. The control system may be further configured to monitor the information received from the sensors and continuously evaluate driving conditions, and may be configured to modify the control strategy and driving behavior based on changing driving conditions. For example, the path taken by the vehicle from one destination to another may be modified based on driving conditions. Additionally or alternatively, speed, acceleration, turn angle, following distance (i.e., the distance to the vehicle ahead of the current vehicle), lane selection, etc. may all be modified in response to changing driving conditions.

[0088] As noted above, in some embodiments, vehicle 200 may take the form of a van, although alternative forms are also possible and contemplated herein. Accordingly, FIGS. 2F-2I illustrate an embodiment in which vehicle 250 takes the form of a semi-truck. For example, FIG. 2F illustrates a front view of vehicle 250, and FIG. 2G illustrates an isometric view of vehicle 250. In an embodiment in which vehicle 250 is a semi-truck, vehicle 250 may include tractor portion 260 and trailer portion 270 (illustrated in FIG. 2G). FIGS. 2H and 2I provide side and top views, respectively, of tractor portion 260. Similar to vehicle 200 illustrated above, vehicle 250 illustrated in FIGS. 2F-2I may also include various sensor systems (e.g., similar to sensor systems 202, 206, 208, 210, 212, 214 shown and described with reference to FIGS. 2A-2E). In some embodiments, vehicle 200 of FIGS. 2A-2E may include only a single copy of some sensor systems (e.g., sensor system 204), while vehicle 250 illustrated in FIGS. 2F-2I may include multiple copies of its sensor systems (e.g., sensor systems 204A and 204B, as illustrated).

[0089] While the figures and general description may refer to a given vehicle form (e.g., semi-truck vehicle 250 or van vehicle 200), it is understood that the embodiments described herein may be equally applicable in various vehicle contexts (e.g., with modifications adopted to account for the vehicle form factor). For example, sensors and / or other components described or illustrated as being part of van vehicle 200 may also be used in semi-truck vehicle 250 (e.g., for navigation and / or obstacle detection and avoidance).

[0090] FIG. 2J illustrates various sensor fields of view (e.g., associated with vehicle 250, described above). As described above, vehicle 250 may contain multiple sensors / sensor units. The various sensor locations may correspond, for example, to the sensor locations disclosed in FIGS. 2F-2I. However, in some cases, sensors may have other locations. To simplify the drawing, sensor location reference numbers are omitted from FIG. 2J. For each sensor unit of vehicle 250, FIG. 2J illustrates a representative field of view (e.g., fields of view labeled as 252A, 252B, 252C, 252D, 254A, 254B, 256, 258A, 258B, and 258C). The sensor field of view may include an angular region (e.g., an azimuth region and / or an elevation region) in which the sensor may detect objects.

[0091] FIG. 2K illustrates beam steering for a sensor of a vehicle (e.g., vehicle 250 shown and described with reference to FIGS. 2F-2J) according to an exemplary embodiment. In various embodiments, the sensor unit of vehicle 250 may be radar, lidar, sonar, or the like. Additionally, in some embodiments, during sensor operation, the sensor may be scanned within the sensor's field of view. Various different scan angles for the exemplary sensor are shown as regions 272, each indicating the angular region in which the sensor is operating. The sensor may periodically or repeatedly change the region in which it is operating. In some embodiments, multiple sensors may be used by vehicle 250 to measure region 272. Additionally, other regions may be included in other examples. For example, one or more sensors may measure aspects of trailer 270 of vehicle 250 and / or the region ahead of vehicle 250.

[0092] At some angles, the sensor's operating area 275 may include the rear wheels 276A, 276B of the trailer 270. Thus, the sensor may measure the rear wheels 276A and / or 276B during operation. For example, the rear wheels 276A, 276B may reflect lidar or radar signals transmitted by the sensor. The sensor may receive signals reflected from the rear wheels 276A, 276B. Thus, the data collected by the sensor may include data from reflections from the wheels.

[0093] In some cases, such as when the sensor is a radar, reflections from the rear wheels 276A, 276B may appear as noise in the received radar signal. As a result, the radar may operate with an enhanced signal-to-noise ratio in cases where the rear wheels 276A, 276B direct the radar signal away from the sensor.

[0094] 3 is a conceptual, illustrative diagram of wireless communication between various computing systems associated with an autonomous or semi-autonomous vehicle, according to an example embodiment. In particular, wireless communication may occur between a remote computing system 302 and the vehicle 200 over a network 304. Wireless communication may also occur between a server computing system 306 and the remote computing system 302, and between the server computing system 306 and the vehicle 200.

[0095] Vehicle 200 can correspond to various types of vehicles capable of transporting passengers or objects between locations and can take the form of any one or more of the vehicles discussed above. In some cases, vehicle 200 can operate in an autonomous or semi-autonomous mode that enables a control system to safely navigate vehicle 200 between destinations using sensor measurements. When operating in an autonomous or semi-autonomous mode, vehicle 200 can navigate with or without a passenger. As a result, vehicle 200 can pick up and drop off passengers between desired destinations.

[0096] Remote computing system 302 may represent any type of device associated with remote assistance technologies, including but not limited to those described herein. In examples, remote computing system 302 may represent any type of device configured to (i) receive information related to vehicle 200, (ii) provide an interface through which a human operator can then observe the information and enter a response related to the information, and (iii) transmit the response to vehicle 200 or to another device. Remote computing system 302 may take various forms, such as a workstation, a desktop computer, a laptop, a tablet, a mobile phone (e.g., a smartphone), and / or a server. In some examples, remote computing system 302 may include multiple computing devices operating together in a network configuration.

[0097] The remote computing system 302 may include one or more subsystems and components similar to or identical to those of the vehicle 200. At a minimum, the remote computing system 302 may include a processor configured to perform various operations described herein. In some embodiments, the remote computing system 302 may also include a user interface including input / output devices such as a touchscreen and a speaker. Other examples are possible as well.

[0098] Network 304 represents an infrastructure that enables wireless communication between remote computing system 302 and vehicle 200. Network 304 also enables wireless communication between server computing system 306 and remote computing system 302, and between server computing system 306 and vehicle 200.

[0099] The location of remote computing system 302 can vary within the examples. For example, remote computing system 302 can be at a location remote from vehicle 200 with wireless communication over network 304. In another example, remote computing system 302 can correspond to a computing device within vehicle 200 that is separate from vehicle 200 but that allows a human operator to interact with passengers or the driver of vehicle 200. In some examples, remote computing system 302 can be a computing device with a touchscreen that can be operated by a passenger of vehicle 200.

[0100] In some embodiments, the operations described herein performed by remote computing system 302 may additionally or alternatively be performed by vehicle 200 (i.e., by any system or subsystem of vehicle 200). In other words, vehicle 200 may be configured to provide remote assistance mechanisms with which a driver or passengers of the vehicle can interact.

[0101] Server computing system 306 may be configured to wirelessly communicate with remote computing system 302 and vehicle 200 over network 304 (or, in some cases, directly with remote computing system 302 and / or vehicle 200). Server computing system 306 may represent any computing device configured to receive, store, determine, and / or transmit information related to vehicle 200 and its remote assistance. As such, server computing system 306 may be configured to perform any operation or portion of such operation described herein as being performed by remote computing system 302 and / or vehicle 200. Some embodiments of wireless communication related to remote assistance may utilize server computing system 306, while other embodiments may not.

[0102] The server computing system 306 may include one or more subsystems and components similar to or identical to the subsystems and components of the remote computing system 302 and / or the vehicle 200, such as a processor configured to perform the various operations described herein, and a wireless communication interface for receiving information from and providing information to the remote computing system 302 and the vehicle 200.

[0103] The various systems described above may perform various operations, and these operations and associated features will now be described.

[0104] In keeping with the above discussion, computing systems (e.g., remote computing system 302, server computing system 306, and a computing system local to vehicle 200) may operate to capture images of the autonomous or semi-autonomous vehicle's surrounding environment using cameras. Generally, at least one computing system may analyze the images and, if possible, control the autonomous or semi-autonomous vehicle.

[0105] In some embodiments, to facilitate autonomous or semi-autonomous operation, a vehicle (e.g., vehicle 200) may receive data representing objects in the environment surrounding the vehicle (also referred to herein as "environmental data") in various manners. A sensor system of the vehicle may provide the environmental data representing objects in the surrounding environment. For example, the vehicle may have various sensors including cameras, radar, lidar, microphones, radio units, and other sensors. Each of these sensors may communicate environmental data to a processor within the vehicle regarding the information each respective sensor receives.

[0106] In one example, the camera may be configured to capture still images and / or video. In some embodiments, the vehicle may have two or more cameras positioned at different orientations. Also, in some embodiments, the camera may be capable of moving to capture images and / or video in different directions. The camera may be configured to store captured images and video in memory for later processing by the vehicle's processing system. The captured images and / or video may be environmental data. Additionally, the camera may include an image sensor as described herein.

[0107] In another example, a radar may be configured to transmit electromagnetic signals that are reflected by various objects near the vehicle and then capture the electromagnetic signals that reflect from the objects. The captured reflected electromagnetic signals may enable the radar (or a processing system) to make various determinations about the objects that reflected the electromagnetic signals. For example, the distance and location to the various reflecting objects may be determined. In some embodiments, a vehicle may have two or more radars at different orientations. The radar may be configured to store the captured information in a memory for later processing by the vehicle's processing system. The information captured by the radar may be environmental data.

[0108] In another example, a LIDAR may be configured to transmit an electromagnetic signal (e.g., infrared light, such as from a gas or diode laser, or other possible light source) that is reflected by a target object near the vehicle. The LIDAR may be capable of acquiring the reflected electromagnetic (e.g., infrared light) signal. The captured reflected electromagnetic signal may enable a ranging system (or processing system) to determine the distance to various objects. The LIDAR may also determine the velocity or speed of the target object, which may be stored as environmental data.

[0109] Additionally, in one example, a microphone may be configured to capture audio of the vehicle's surrounding environment. Sounds captured by the microphone may include sounds of emergency vehicle sirens and other vehicles. For example, the microphone may capture the sounds of sirens from an ambulance, a fire engine, and a police vehicle. The processing system may be capable of identifying that the captured audio signal is indicative of an emergency vehicle. In another example, the microphone may capture the sound of an exhaust from another vehicle, such as an exhaust from a motorcycle. The processing system may be capable of identifying that the captured audio signal is indicative of a motorcycle. Data captured by the microphone may form part of the environmental data.

[0110] In yet another example, the radio unit may be configured to transmit electromagnetic signals that may take the form of Bluetooth signals, 802.11 signals, and / or other wireless technology signals. The first electromagnetic radiation signal may be transmitted via one or more antennas located on the radio unit. Furthermore, the first electromagnetic radiation signal may be transmitted in one of many different wireless signal modes. However, in some embodiments, it may be desirable to transmit the first electromagnetic radiation signal in a signal mode that solicits responses from devices located near the autonomous or semi-autonomous vehicle. The processing system may be able to detect nearby devices based on responses transmitted back to the radio unit and use this communicated information as part of the environmental data.

[0111] In some embodiments, the processing system may be able to combine information from various sensors to further determine the vehicle's surroundings. For example, the processing system may combine data from both radar information and captured images to determine whether another vehicle or pedestrian is in front of the autonomous or semi-autonomous vehicle. In other embodiments, other combinations of sensor data may be used by the processing system to make decisions about the surroundings.

[0112] While operating in autonomous mode (or semi-autonomous mode), the vehicle may control its operation with little or no human input. For example, if a human operator inputs an address into the vehicle, the vehicle may be able to drive to the specified destination without further input from the human (e.g., without the human having to steer or touch the brake / accelerator pedals). Additionally, while the vehicle is operating autonomously or semi-autonomously, the sensor system may receive environmental data. The vehicle's processing system may alter control of the vehicle based on the environmental data received from the various sensors. In some embodiments, the vehicle may alter the vehicle's speed in response to the environmental data from the various sensors. The vehicle may alter its speed to avoid obstacles, obey traffic laws, etc. If the processing system in the vehicle identifies an object near the vehicle, the vehicle may be able to alter its speed or otherwise modify its movement.

[0113] If the vehicle detects an object but is not fully confident in its detection, the vehicle can request a human operator (or a more powerful computer) to perform one or more remote assistance tasks, such as (i) verifying whether the object is actually present in the surrounding environment (e.g., is there actually a stop sign or is there actually no stop sign), (ii) verifying whether the vehicle's identification of the object is correct, (iii) correcting the identification if it is incorrect, and / or (iv) providing supplemental instructions (or modifying current instructions) to the autonomous or semi-autonomous vehicle. Remote assistance tasks also include the human operator providing instructions to control the vehicle's operation (e.g., if the human operator determines that the object is a stop sign, commanding the vehicle to stop at the stop sign), although in some scenarios the vehicle itself may control its own operation based on the human operator's feedback related to the object's identification.

[0114] To facilitate this, the vehicle may analyze environmental data representing objects in the surrounding environment to determine at least one object having a detection confidence below a threshold. A processor of the vehicle may be configured to detect various objects in the surrounding environment based on the environmental data from various sensors. For example, in one embodiment, the processor may be configured to detect objects that may be important for the vehicle to recognize. Such objects may include pedestrians, bicyclists, street signs, other vehicles, indicator signals of other vehicles, and various other objects detected in the captured environmental data.

[0115] The detection confidence may indicate the likelihood that a determined object is correctly identified or present in the surrounding environment. For example, the processor may perform object detection of objects in image data in the received environmental data and determine that an object has a detection confidence below a threshold based on the inability to identify at least one object with a detection confidence above a threshold. If the object detection or object recognition results for an object are inconclusive, the detection confidence may be low or below a set threshold.

[0116] The vehicle may detect objects in the surrounding environment in a variety of ways, depending on the source of the environmental data. In some embodiments, the environmental data may be image or video data coming from a camera. In other embodiments, the environmental data may come from a lidar. The vehicle may analyze the captured image or video data to identify objects in the image or video data. Methods and apparatus may be configured to monitor the image and / or video data for the presence of objects in the surrounding environment. In other embodiments, the environmental data may be radar, audio, or other data. The vehicle may be configured to identify objects in the surrounding environment based on radar, audio, or other data.

[0117] In some embodiments, the technique used by the vehicle to detect objects may be based on a set of known data. For example, data related to environmental objects may be stored in a memory located in the vehicle. The vehicle may compare the received data with the stored data to determine the object. In other embodiments, the vehicle may be configured to determine the object based on the context of the data. For example, construction-related street signs may generally have an orange color. Thus, the vehicle may be configured to detect an orange object located near the side of the road as a construction-related street sign. Additionally, as the vehicle's processing system detects objects in the captured data, it may also calculate a confidence score for each object.

[0118] Additionally, the vehicle may also have a confidence threshold. The confidence threshold may vary depending on the type of object detected. For example, the confidence threshold may be lower for an object that may require a quick response action from the vehicle, such as the brake lights of another vehicle. However, in other embodiments, the confidence threshold may be the same for all detected objects. If the confidence associated with a detected object is higher than the confidence threshold, the vehicle may assume that the object was correctly recognized and responsively adjust the vehicle's controls based on that assumption.

[0119] If the confidence associated with the detected object is lower than a confidence threshold, the action taken by the vehicle may vary. In some embodiments, the vehicle may react as if the detected object is present despite the low confidence level. In other embodiments, the vehicle may react as if the detected object is not present.

[0120] Upon detecting an object in the surrounding environment, the vehicle may also calculate a confidence level associated with the particular detected object. The confidence level may be calculated in various ways depending on the embodiment. In one example, upon detecting an object in the surrounding environment, the vehicle may compare environmental data to predetermined data associated with known objects. The closer the match between the environmental data and the predetermined data, the higher the confidence level. In other embodiments, the vehicle may use a mathematical analysis of the environmental data to determine the confidence level associated with the object.

[0121] In response to determining that the object has a detection confidence below a threshold, the vehicle may transmit a request for remote assistance along with an identification of the object to a remote computing system. As discussed above, the remote computing system may take a variety of forms. For example, the remote computing system may be an in-vehicle computing device that is separate from the vehicle, but which may include a touchscreen interface for displaying remote assistance information, through which a human operator may interact with a passenger or driver of the vehicle. Additionally or alternatively, as another example, the remote computing system may be a remote computer terminal or other device located at a location not near the vehicle.

[0122] The request for remote assistance may include environmental data, including objects, such as image data, audio data, etc. The vehicle may transmit the environmental data over a network (e.g., network 304) to a remote computing system, in some embodiments, via a server (e.g., server computing system 306). A human operator of the remote computing system may then use the environmental data as a basis for responding to the request.

[0123] In some embodiments, if an object is detected as having a confidence below a confidence threshold, the object may be given a preliminary identification, and the vehicle may be configured to adjust the vehicle's operation in response to the preliminary identification. Such adjustments in operation may take the form of stopping the vehicle, switching the vehicle to a human-controlled mode, changing the vehicle's performance (e.g., speed and / or direction), among other possible adjustments.

[0124] In other embodiments, if the vehicle detects an object with a confidence level that meets or exceeds a threshold, the vehicle may still act on the detected object (e.g., stop if the object is identified with high confidence as a stop sign), but may be configured to request remote assistance at the same time (or after) the vehicle acts on the detected object.

[0125] 4A is a block diagram of a system according to an example embodiment. In particular, FIG. 4A shows a system 400 including a system controller 402, a lidar device 410, multiple sensors 412, and multiple controllable components 414. The system controller 402 includes a processor 404, a memory 406, and instructions 408 stored on the memory 406 and executable by the processor 404 to implement functions.

[0126] The processor 404 may include one or more processors, such as one or more general-purpose microprocessors (e.g., having a single core or multiple cores) and / or one or more special-purpose microprocessors. The one or more processors may include, for example, one or more central processing units (CPUs), one or more microcontrollers, one or more graphics processing units (GPUs), one or more tensor processing units (TPUs), one or more ASICs, and / or one or more field-programmable gate arrays (FPGAs). Other types of processors, computers, or devices configured to execute software instructions are also contemplated herein.

[0127] The memory 406 may include a computer-readable medium such as a non-transitory computer-readable medium, which may include, without limitation, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile random access memory (e.g., flash memory), solid-state drive (SSD), hard disk drive (HDD), compact disc (CD), digital video disc (DVD), digital tape, read / write (R / W) CD, R / W DVD, etc.

[0128] The lidar device 410, described further below, includes a plurality of light emitters configured to emit light (e.g., in light pulses) and one or more photodetectors configured to detect the light (e.g., reflected portions of the light pulses). The lidar device 410 may generate three-dimensional (3D) point cloud data from the output of the photodetectors and provide the 3D point cloud data to the system controller 402. The system controller 402 may then perform operations on the 3D point cloud data to determine characteristics of the surrounding environment (e.g., relative positions of objects within the surrounding environment, edge detection, object detection, and / or proximity sensing).

[0129] Similarly, system controller 402 may use output from multiple sensors 412 to determine characteristics of system 400 and / or the surrounding environment. For example, sensors 412 may include one or more of a GPS, an IMU, an image capture device (e.g., a camera), a light sensor, a heat sensor, and other sensors that indicate parameters related to system 400 and / or the surrounding environment. Lidar device 410 is depicted as separate from sensors 412, for illustrative purposes, and in some examples may be considered part of or as sensors 412.

[0130] Based on characteristics of the surrounding environment determined by the system controller 402 based on output from the system 400 and / or the lidar device 410 and sensors 412, the system controller 402 may control the controllable components 414 to perform one or more actions. For example, the system 400 may correspond to a vehicle, in which case the controllable components 414 may include the vehicle's braking system, turning system, and / or acceleration system, and the system controller 402 may alter aspects of these controllable components based on characteristics determined from the lidar device 410 and / or sensors 412 (e.g., when the system controller 402 controls the vehicle in an autonomous or semi-autonomous mode). In an example, the lidar device 410 and sensors 412 are also controllable by the system controller 402.

[0131] FIG. 4B is a block diagram of a lidar device, according to an example embodiment. In particular, FIG. 4B shows a lidar device 410 having a controller 416 configured to control multiple light emitters 424 and one or more photodetectors, such as multiple photodetectors 426. The lidar device 410 may further include a firing circuit 428 configured to select and provide power to each light emitter of the multiple light emitters 424 and may include a selector circuit 430 configured to select each photodetector of the multiple photodetectors 426. The controller 416 includes a processor 418, a memory 420, and instructions 422 stored on the memory 420.

[0132] Similar to processor 404, processor 418 may include one or more processors, such as one or more general-purpose microprocessors and / or one or more special-purpose microprocessors. The one or more processors may include, for example, one or more CPUs, one or more microcontrollers, one or more GPUs, one or more TPUs, one or more ASICs, and / or one or more FPGAs. Other types of processors, computers, or devices configured to execute software instructions are also contemplated herein.

[0133] Similar to memory 406, memory 420 may include computer-readable media such as, but not limited to, ROM, PROM, EPROM, EEPROM, non-volatile random access memory (e.g., flash memory), SSD, HDD, CD, DVD, digital tape, R / W CD, R / W DVD, and other non-transitory computer-readable media.

[0134] Instructions 422 are stored on memory 420 and executable by processor 418 to perform functions related to controlling firing circuitry 428 and selector circuitry 430 to generate 3D point cloud data and to process the 3D point cloud data (or perhaps to facilitate processing of the 3D point cloud data by another computing device, such as system controller 402).

[0135] The controller 416 may determine 3D point cloud data by using the light emitters 424 to emit pulses of light. An emission time is established for each light emitter, and the relative location of the emission time is also tracked. Aspects of the lidar device 410's surrounding environment, such as various objects, reflect the pulses of light. For example, if the lidar device 410 is in an environment that includes a road, such objects may include vehicles, signs, pedestrians, road surfaces, construction cones, etc. Some objects may be more reflective than others, so that the intensity of the reflected light may indicate the type of object reflecting the light pulse. Furthermore, object surfaces may be in different positions relative to the lidar device 410 and therefore may take more or less time to reflect a portion of the light pulse back to the lidar device 410. Therefore, the controller 416 may track the detection time when the reflected light pulse is detected by the photodetector and the relative location of the photodetector at the detection time. By measuring the time difference between the emission time and the detection time, the controller 416 can determine how far the light pulse travels before it is received and, therefore, the relative distance of the corresponding object. By tracking the relative positions at emission and detection times, the controller 416 can determine the orientation of the light pulses and reflected light pulses relative to the lidar device 410, and thus the relative orientation of the object. By tracking the intensity of the received light pulses, the controller 416 can determine how reflective the object is. 3D point cloud data determined based on this information can therefore indicate the relative positions of the detected reflected light pulses (e.g., in a coordinate system such as a Cartesian coordinate system) and the intensity of each reflected light pulse.

[0136] The firing circuit 428 is used to select the light emitter for emitting a light pulse. Similarly, the selector circuit 430 is used to sample the output from the photodetector.

[0137] As noted above, various types of defects can adversely affect measurements made by a detection device (such as a lidar device or camera). For example, some detection devices may include one or more optical components (e.g., lenses, mirrors, waveguides, optical coatings, and / or windows), and one or more defects in or on portions of such optical components can cause improper detection of the surrounding environment. For example, an optical window (e.g., the optical element through which a camera or lidar captures images of the surrounding environment) may be adversely affected by one or more scratches, cracks, dirt, deformations, bubbles, impurities (e.g., chemical impurities in the glass or plastic of the optical window), degradation (e.g., degradation of optical properties over time), discoloration, imperfect transparency, or distortions within one or more portions of the optical window (e.g., within the body). Additionally or alternatively, such optical windows may be adversely affected by water droplets, dirt, dust, mud, leaves, rain, snow, sleet, hail, ice, or insect residue (i.e., remains of dead insects) on one or more portions of the optical window (e.g., on one or more portions of the optical window that are in contact with the ambient environment, i.e., on one or more exterior portions of the optical window). As an additional example of a defect, one or more optical components may include optical coatings (e.g., anti-reflective coatings, hydrophobic coatings, polarizing filters, color filters, and neutral density filters), and such optical coatings may degrade over time (e.g., suffer from a decrease in their anti-reflective, hydrophobic, or filtering properties) as a result of exposure of the optical coating to the ambient environment (e.g., due to wind, condensation, insects, precipitation, ambient temperature fluctuations, ambient pressure fluctuations, exposure to ultraviolet light, or dust / dirt accumulation). Additionally, in some embodiments, the defects may include one or more protective layers (e.g., protective films) remaining on the optical component after the optical component should be removed (e.g., before operation). Such protective films may have undesirable or poorly characterized optical properties that may adversely affect detection. It is understood that other types of defects are possible and are contemplated herein.Furthermore, such defects may attenuate the optical signal, obscure the optical signal, block the optical signal, scatter the optical signal, redirect the optical signal, or interfere with optical signals received from the surrounding environment. In view of the above, the term defect is understood to broadly encompass both debris present on the surface of one or more components (e.g., from the external environment or internal to the lidar device) as well as defects within one or more components (e.g., manufacturing defects and degradation).

[0138] FIG. 5 illustrates an exemplary system 500 (e.g., similar to system 400 shown and described with reference to FIG. 4A ). System 500 may include a lidar device 410 (e.g., including a light emitter 424 and a light detector 426). Additionally, as shown, system 500 may include an optical component 502 (e.g., an optical coating, such as a hydrophobic coating) on ​​or within the lidar device 410 (e.g., an optical coating on an optical window of the lidar device 410). As mentioned above, in some embodiments, optical component 502 may suffer from defects (e.g., deterioration and debris) that degrade the performance of the lidar device 410 (e.g., resulting in internal reflection of an optical signal from the light emitter 424 that is detected by the light detector 426, as shown in FIG. 5 ). Such defects may be visible to the naked eye (e.g., leaves) or invisible to the naked eye (e.g., small debris or small cracks, deformations, and changes in refractive index). Furthermore, it is understood that although there may be a single defect external to optical component 502, any number and / or types of defects are possible (eg, on or within optical component 502).

[0139] 5 through internal reflection, defects can interfere with the optical signal emitted by the light emitter (e.g., light emitter 424 of the lidar device 410 shown and illustrated in FIG. 4B) and / or the optical signal being detected by the light detector (e.g., light detector 426 of the lidar device 410 shown and illustrated in FIG. 4B). Thus, as shown in FIG. 5, defects can affect measurements of the surrounding environment using the light emitter 424 / light detector 426.

[0140] It may be desirable to mitigate the adverse effects of the defects. This can be done by detecting the presence of one or more defects and then taking one or more corrective actions (e.g., cleaning the problematic optical component, replacing the problematic optical component, removing all or part of the problematic optical component from use, flagging data acquired by a sensor using the optical component as including the effects of the defect, and performing post-processing on the data acquired by a sensor using the optical component to compensate for the effects of the defect). To detect the presence of one or more defects, techniques described herein can be implemented. Furthermore, such techniques can be implemented using one or more devices or systems described herein.

[0141] In some embodiments, detecting the presence of one or more defects in an optical component (e.g., optical component 502 of FIG. 5) can include sensing one or more types of defect signals. FIGS. 6A-6D illustrate various types of signals that can be detected by a lidar device. By disambiguating the different types of signals that can be detected by a lidar device and analyzing those disambiguated signals, a determination can be made as to what types of defects are present, how many are present, and what types of defects are present.

[0142] FIG. 6A illustrates a system for detecting an object 602 in a surrounding environment (e.g., in the absence of defects). The system may include a lidar device (e.g., the lidar device 410 shown and described with reference to FIGS. 4A-5) and an optical component (e.g., the optical component 502 shown and described with reference to FIG. 5) that may be positioned on one or more components of the lidar device (e.g., an optical window 604 defined within the housing of the lidar device). As illustrated, light emitters 424A, 424B and corresponding photodetectors 426A, 426B may be used by the lidar device to detect an object 602 in the surrounding environment (e.g., similar to the light emitter 424 and photodetector 426 described and illustrated with reference to FIG. 4B). For example, as illustrated by the arrows in FIG. 6A, the first light emitter 424A and the second light emitter 424B may each emit one or more optical signals that are transmitted to the surrounding environment through the optical window 604 and the optical component 502 (e.g., if the optical component 502 is an optical coating). The optical signals may be reflected by objects 602 in the surrounding environment and directed to corresponding first and second photodetectors 426A and 426B (e.g., again through the optical window 604 / optical component 502) to provide information about the surrounding environment (e.g., distance to the object 602 in the surrounding environment based on time of flight). While FIG. 6A shows two light emitters 424A, 424B, two photodetectors 426A, 426B, and optical component 502, it is understood that other numbers and / or arrangements of light emitters, photodetectors, and optical components are possible and contemplated herein. For example, in some embodiments, the system may include an array of light emitters (e.g., more than two light emitters) and a corresponding array of photodetectors (e.g., more than two photodetectors). The array may be arranged such that light emitters and photodetectors in the same channel are adjacent to one another. Additionally or alternatively, some embodiments may include multiple optical components and / or different types / positions of optical components.

[0143] Under certain circumstances (e.g., different from those illustrated in FIG. 6A ), the optical signals detected by the optical detectors 426A, 426B may be emitted by the light emitters 424A, 424B and then reflected by something other than the target object 602 in the surrounding environment. In still other circumstances (e.g., different from those illustrated in FIG. 6A ), the optical signals detected by the optical detectors 426A, 426B may be reflected such that they are directed toward the optical detectors 426A, 426B for which they are not intended. FIGS. 6B and 6C illustrate examples of the aforementioned circumstances. For example, FIG. 6B illustrates an example of crosstalk detection, and FIG. 6C illustrates an example of cross-feedback detection.

[0144] Sometimes, when interacting with certain objects in the surrounding environment, the optical signals emitted by the light emitters 424A, 424B may result in crosstalk. For example, as shown in FIG. 6B, the first light emitter 424A may emit an optical signal into the surrounding environment. Generally, when the emitted optical signal is reflected by a surface with low or moderate reflectivity, a reflected optical signal of low or moderate intensity may be returned to the first detector 426A. However, as shown in FIG. 6B, when the optical signal emitted from the first light emitter 424A into the surrounding environment is reflected by an object with high or very high reflectivity (e.g., a reflectivity above a threshold, which may be part of a road sign, such as a retroreflector 612), the intensity of the reflected signal may be correspondingly higher and / or the reflected signal may occupy a correspondingly larger detectable area when incident on the light detectors 426A, 426B (sometimes referred to as a flowering effect). 6B, a high-intensity reflected optical signal may illuminate multiple photodetectors 426A, 426B rather than just the intended photodetector corresponding to the channel of the emitted signal (e.g., the first photodetector 426A). For example, the high-intensity reflected optical signal may illuminate a second photodetector 426B in addition to the first photodetector 426A. Thus, the second photodetector 426B may detect crosstalk (i.e., detect crosstalk signals arising from the emitted signal of the first light emitter 424A), which means that the second photodetector 426B may be undesirably affected by light from the first channel (e.g., may cause noise or inappropriate detection events based on the detection of the second photodetector 426B).

[0145] Which photodetectors within a lidar device (e.g., which of the photodetectors 426 shown and described with reference to FIG. 4B ) can detect a given reflected signal (e.g., which photodetectors 426 are susceptible to crosstalk) may depend on the strength of the reflected signal (e.g., based on the reflectivity of surfaces in the surrounding environment), the sensitivity of the photodetectors 426, the location of the photodetectors 426 within the lidar device, the orientation of the photodetectors 426 within the lidar device (e.g., the azimuth / yaw and / or elevation / pitch orientations of the photodetectors 426), and the distance to the reflecting object in the surrounding environment. For example, because the reflected optical signal may attenuate / diverge as it propagates through the surrounding environment (e.g., due to dust, smoke, etc. in the surrounding environment), the greater the distance between the lidar device and the reflecting object, the greater the decrease in optical signal strength. As a result, the number of photodetectors 426 within the lidar device that detect crosstalk as a result of optical signals reflected from a highly reflective object may be greater the closer the lidar device is to the highly reflective object.

[0146] Under certain circumstances, the optical signals detected by the optical detectors 426A, 426B may be emitted by the light emitters 424A, 424B and subsequently reflected by objects other than the target object in the surrounding environment. For example, as shown in FIG. 6C , defects 622 may be present (e.g., debris such as mud or condensation, deterioration, and bends / warping present in or on the optical component 502). As illustrated, the defects 622 may reflect the optical signals emitted by the light emitters 424A, 424B, which are intended to survey the surrounding environment, and redirect the optical signals to the optical detectors 426A, 426B. Furthermore, the first light emitter 424A may emit an optical signal intended for the first optical detector 426A when reflected from an object in the surrounding environment (e.g., as shown in FIG. 6A ), and the second light emitter 424B may emit an optical signal intended for the second optical detector 426B when reflected from an object in the surrounding environment (e.g., as shown in FIG. 6A ). However, when such emitted optical signals are reflected from a defect 622, they may be directed to an unintended optical detector. For example, an optical signal emitted by a first light emitter 424A may be directed to and detected by a second optical detector 426B, and an optical signal emitted by the second light emitter 426B may be directed to and detected by the first optical detector 426A (e.g., as illustrated in FIG. 6C ). In some embodiments, such redirected optical signals may be partially diffused or otherwise dispersed after interacting with a defect 622. Because such optical signals are redirected by the defect 622 to an optical detector for which they were not originally intended, such redirected optical signals may be referred to herein as “cross-feedback signals.” In other words, a cross-feedback signal occurs when one or more optical signals emitted from a light emitter in one channel are internally reflected (e.g., from a defect on or within one or more optical components of the system) and redirected, resulting in an optical detector in a different channel (e.g., an adjacent channel) detecting the optical signal.While FIG. 6C shows a “cross-feedback signal” redirected by defect 622, it is understood that a “cross-feedback signal” having a non-zero intensity may be detected even in the absence of a defect. For example, internal reflections from one or more optical components (e.g., lenses and mirrors) of the lidar device may be detected as a cross-feedback signal. It is understood that a “cross-feedback signal” may be detected even in the absence of a defect, but in some embodiments, the intensity of the detected “cross-feedback signal” may be higher in the presence of a defect than in the absence of a defect.

[0147] Various techniques may be used to disambiguate a "cross-feedback signal" from other signals. For example, a "cross-feedback signal" may arrive at the detector earlier during a detection cycle than other signals. Thus, based on a timing window associated with a detection event, a detected signal may be labeled as either cross-feedback or non-cross-feedback. In some embodiments, the energization of a photodetector (e.g., the energization of a SiPM used in a photodetector) may be set to detect cross-feedback but not non-cross-feedback. For example, the photodetector may be de-energized after a certain time corresponding to a detection distance beyond which cross-feedback occurs.

[0148] 6C illustrates an example in which a defect 622 external to the optical component 502 and the lidar device reflects / redirects the optical signals emitted by the light emitters 424A, 424B, although it should be understood that other embodiments are possible and contemplated herein. For example, the cross-feedback signal may be detected based on reflections from internal optics (mirrors and lenses) and / or mechanical components (e.g., mounts, actuators, motors) within the system (e.g., within the lidar device associated with the light emitters 424A, 424B and light detectors 426A, 426B).

[0149] Crosstalk and cross-feedback signals (e.g., as shown and described with reference to FIGS. 6B and 6C ) can be useful in identifying the type of defect associated with the system (e.g., a defect associated with the optical component 502). For example, signals detected by the photodetector 426 of a lidar device can be analyzed (e.g., by a computing device such as the system controller 402 or the lidar controller 416 illustrated in FIGS. 4A and 4B ) to determine the presence, absence, location, and / or strength (e.g., intensity waveform) of the crosstalk and / or cross-feedback signals. A determination of the presence, absence, type, and / or location of one or more defects can then be made by comparing the determined presence, absence, location, and / or strength (e.g., intensity waveform) of the crosstalk and / or cross-feedback signals with calibration measurements (e.g., obtained when no defects are known to be present, when a particular type of defect is present, and / or when a defect is present in a known location). In addition to, or instead of, making such determinations using crosstalk and cross-feedback signals (e.g., detected by the photodetector 426 of the LIDAR device), images captured by an image sensor (e.g., a camera) can be used to identify defects.

[0150] As shown in FIG. 6D , image sensor 632 (e.g., a charge-coupled device (CCD)) may be positioned to capture images of optical component 502 (e.g., the entire optical component 502 or a portion of optical component 502 through which an optical signal detectable by photodetectors 426, 426B travels). Additionally or alternatively, image sensor 632 may be configured to capture images of optical window 604 and / or an interior portion of the lidar device. As shown in FIG. 6D , image sensor 632 may be positioned at a focal plane associated with photodetectors 426A, 426B. While not shown in FIG. 6D , it will be appreciated that additional components may be used to assist image sensor 632 in capturing images of optical component 502 or other portions of the system. For example, one or more lenses, photographic flashes, mirrors, apertures, etc. may be used in association with image sensor 632 to capture images.

[0151] Upon capturing an image of the optical component 502 or other portion of the system, the image may be analyzed (e.g., by a computing device) to determine what percentage of the optical component 502 (or other portion of the system), if present, is occluded (e.g., by mud, condensation, cracks, and deformations) by one or more defects 622. Such image analysis may be performed using a machine learning model (e.g., a classifier trained on one or more labeled training images with known occlusion percentages). The determined occlusion percentage may represent an additional metric (in addition to the strength, location, timing, etc. of detected crosstalk and / or cross-feedback signals) used to characterize the presence, absence, location, and / or type of defect 622 associated with the system at the time the image was captured. Similar to the crosstalk and cross-feedback signals described above, the percentage of occlusion and / or location of occlusion captured in the image may be compared (e.g., by a computing device) to one or more calibration images or calibration metrics (e.g., calibrated percentage of occlusion) to determine the presence, absence, location, and / or type of defect present on or within the optical component 502.

[0152] As described above, the crosstalk signal (e.g., detected by the photodetector 426 of the lidar device 410), the cross-feedback signal (e.g., detected by the photodetector 426 of the lidar device 410), and / or the occlusion rate (e.g., determined by a computing device based on images captured by the image sensor 632) may be used to analyze defects associated with a system (e.g., the lidar device 410 and / or associated optical component 502). With this in mind, changes in the crosstalk signal, the cross-feedback signal, and / or the occlusion rate over time can be used to characterize changes in defects over time. Furthermore, however, some types of defects will develop over time based on the behavior of the system. For example, if the optical component 502 has a hydrophobic coating and one or more water droplets are applied to the optical component 502 (e.g., as a result of rain and / or condensation), these water droplets should aggregate and shed from the optical component 502 over time. By monitoring the evolution of the cross-feedback signal, the cross-talk signal, and / or the percentage of occlusion over time, a determination can be made regarding the hydrophobic quality of the hydrophobic coating (e.g., how quickly / completely water aggregates / sheds from the hydrophobic coating). In other words, defects (e.g., resulting in a decrease in hydrophobicity), such as degradation of the hydrophobic coating (e.g., chemical or physical degradation as a result of exposure to the ambient environment), can be monitored over time. Similarly, if one or more defects (e.g., bubbles, cracks, imperfect transparency, and bends) are present in the optical component 502, the occurrence of such defects can be monitored by monitoring the cross-talk signal, the cross-feedback signal, and / or the percentage of occlusion over time. For example, by analyzing the cross-talk signal, the cross-feedback signal, and / or the percentage of occlusion over time, it can be determined whether a crack in the optical component 502 is growing over time. Other types of defect monitoring over time (e.g., for various types of optical components) are also possible and are contemplated herein using the signals and metrics described throughout.

[0153] In view of the above, the techniques described herein may involve intentionally introducing one or more defects into a system (e.g., in or on optical component 502) and then monitoring various metrics (e.g., metrics based on crosstalk signals, cross-feedback signals, and / or captured images) over time to determine the state of the system (e.g., the system's ability to properly handle, remove, address, account for, etc., the defects present in the system). Figures 7A and 7B illustrate one technique for intentionally introducing defects and monitoring the handling of those defects over time. In particular, Figures 7A and 7B illustrate a system 700 including a lidar device (e.g., the lidar device 410 shown and described with reference to Figures 4A and 4B), an optical component (e.g., the optical component 502 shown and described with reference to Figures 5-6D), and a cleaning device. As shown, the cleaning device may include a sprayer 710 and a pressurized air source 720. The cleaning device illustrated in FIGS. 7A and 7B is provided by way of example only, and other cleaning devices are possible and contemplated herein (e.g., a cleaning device including one or more wipers, such as windshield wipers, a heater, such as a defroster, a cooling unit, a fan, a vacuum, and an actuator, such as a motor, a centrifugal unit, a mechanical stage, or a vibrator). Furthermore, in some embodiments, the cleaning device may serve multiple purposes. For example, the cleaning device may include a motor used to rotate one or more components of the lidar device 410 (e.g., to rotate the light emitters 424 and light detectors 426 of the lidar device 410 relative to the surrounding environment). As the motor rotates the lidar device 410, this may enable the light emitters 424 and light detectors 426 to analyze a larger portion of the surrounding environment (e.g., by azimuthally scanning the surrounding environment). Additionally, as the motor turns the lidar device 410, the motor may function to clean the lidar device 410 (e.g., by removing a previously applied cleaning solution or by removing condensation, rain, snow, and debris from the lidar device 410).The system 700 of Figures 7A and 7B can be configured to perform a multi-stage cleaning protocol as illustrated in Figures 7A and 7B.

[0154] 7A illustrates the steps of a cleaning protocol. As shown, the cleaning protocol may include a sprayer 710 that applies a cleaning solution 712 to one or more components of the system 700 (e.g., to the exterior surface of the optical component 502). The cleaning solution 712 may be applied to a portion of the exterior surface of the optical component 502 or to the entire exterior surface of the optical component 502. In some embodiments, the cleaning solution 712 may be applied, for example, through a nozzle of the sprayer 710. The sprayer 710 may also include one or more actuators (e.g., a motor and a stage) configured to direct the sprayer 710 to specific regions of the lidar device 410 and / or the optical component 502. Additionally, the cleaning solution 712 may include various compounds in various concentrations (e.g., deionized water and isopropyl alcohol). Additionally, the cleaning protocol may include a predetermined or selectable number of sprays of cleaning solution 712 being applied (e.g., 1 spray, 2 sprays, 3 sprays, 4 sprays, 5 sprays, 6 sprays, 7 sprays, 8 sprays, 9 sprays, and 10 sprays). If the number of sprays is greater than one, the number of sprays may be distributed (e.g., evenly) over a predefined or selectable period (e.g., 5 seconds, 10 seconds, 20 seconds, 30 seconds, and 1 minute) according to an application frequency (e.g., 0.25 Hz, 0.5 Hz, 0.75 Hz, 1 Hz, 1.5 Hz, 2 Hz, and 2.5 Hz). Still further, the cleaning protocol may be initiated according to a periodic schedule (e.g., once every 30 minutes, once every hour, once every four hours, once every 12 hours, once a day, once every two days, once every four days, once a week, once every two weeks, and once a month). Additionally or alternatively, the cleaning protocol may be initiated in response to a request (e.g., from a user providing instructions via a mobile or browser-based application, from the rider controller 416, and from the system controller 402).Still further, the cleaning protocol may be initiated in response to one or more thresholds being met (e.g., a determination by the lidar controller 416 that the strength or number of detected cross-feedback signals exceeds a predetermined threshold).

[0155] As illustrated by the arrows, the light emitters 424 of the lidar device 410 may emit one or more optical signals while the cleaning solution 712 is being applied to one or more components of the system 700. These optical signals may be reflected by the cleaning solution 712 being applied to the surface of the optical component 502 and then detected by the optical detectors 426 of the lidar device 410. Thus, such detected signals may represent cross-feedback signals (as shown and described above with respect to FIG. 6C ) when they are directed to a photodetector 426 on a different channel than the corresponding light emitter 424 that emitted the optical signal.

[0156] FIG. 7B illustrates another step of the cleaning protocol. As shown, the cleaning protocol may include a pressurized air source 720 applying pressurized air 722 to one or more components of the system 700 (e.g., the exterior surface of the optical component 502). The pressurized air 722 may be applied after application of the cleaning solution 712 (e.g., as shown and described with reference to FIG. 7A). The pressurized air 722 may be applied to a portion of the exterior surface of the optical component 502 (e.g., the portion to which the cleaning solution 712 was applied, if the cleaning solution 712 was applied only to a portion of the optical component 502), or to the entire exterior surface of the optical component 502. The pressurized air source 720 may also include one or more actuators (e.g., a motor and a stage) configured to direct the pressurized air source 720 to specific regions of the lidar device 410 and / or the optical component 502. Further, the cleaning protocol may include a predetermined or selectable number of applications of pressurized air 722 (e.g., 1 burst, 2 bursts, 3 bursts, 4 bursts, 5 bursts, 6 bursts, 7 bursts, 8 bursts, 9 bursts, and 10 bursts). If the number of bursts is greater than 1, the number of bursts may be distributed (e.g., evenly) over a predefined or selectable period of time (e.g., 5 seconds, 10 seconds, 20 seconds, 30 seconds, and 1 minute) according to an application frequency (e.g., 0.25 Hz, 0.5 Hz, 0.75 Hz, 1 Hz, 1.5 Hz, 2 Hz, and 2.5 Hz). Still further, the steps of the cleaning protocol illustrated in FIG. 7B may be initiated in response to the completion of the steps of the cleaning protocol illustrated in FIG. 7A.

[0157] As illustrated by the arrows, the light emitters 424 of the lidar device 410 may emit one or more optical signals while pressurized air 722 is applied to one or more components of the system 700. These optical signals may be reflected by the cleaning solution 712 on the surface of the optical component 502 and then detected by the optical detectors 426 of the lidar device 410. Such detected signals may therefore represent cross-feedback signals (e.g., as shown and described above with respect to FIG. 6C ) when the signals are directed to a photodetector 426 on a different channel than the corresponding light emitter 424 that emitted the optical signal.

[0158] As illustrated by the above description, optical signals can be emitted by the light emitter 424 and detected by the light detector 426 while the cleaning device performs a cleaning protocol. By analyzing the detected optical signals, determinations can be made regarding the presence of a defect, the absence of a defect, the location of a defect, the type of defect, and / or the time evolution of a defect within the system 700 (e.g., on the exterior surface of the optical component 502). Such determinations may be made, for example, by the system controller 402 and / or the lidar controller 416. Furthermore, such determinations can be used to estimate the health of one or more components of the system 700. For example, based on the time evolution of the cleaning solution 712 being removed from the exterior surface of the optical component 502 (e.g., by application of pressurized air 722 during a cleaning protocol), determinations can be made (e.g., by the system controller 402 and / or the lidar controller 416) regarding the hydrophobic quality of the optical component 502 (e.g., when the optical component 502 is or includes a hydrophobic coating). These determined hydrophobic qualities can indicate the level of degradation of the hydrophobic coating over time (e.g., due to exposure to the ambient environment). A lower level of degradation may correspond, for example, to larger droplets of cleaning solution 712 and / or faster shedding of cleaning solution 712 due to the applied pressurized air 722. Other qualities can be analyzed using similar techniques and are also contemplated herein (e.g., optical qualities such as polarization, reflectance, absorbance, transmittance, and refractive index).

[0159] Exemplary techniques for making determinations about the quality of one or more components of system 700 based on detected optical signals are described in further detail below with reference to Figures 8A and 8B. In some embodiments, such determinations about the quality of one or more components may be made every time a cleaning protocol (e.g., the cleaning protocols illustrated in Figures 7A and 7B) is performed. Alternatively, such determinations about the quality of one or more components may be made only for a subset of cleanings (e.g., every second time a cleaning protocol is performed, every third time a cleaning protocol is performed, and every fourth time a cleaning protocol is performed) and / or only for certain types of cleanings (e.g., only when optical component 502 is cleaned and only when sprayer 710 / pressurized air source 720 is involved in cleaning).

[0160] A cleaning protocol may be initiated for the purpose of cleaning the system 700 (e.g., cleaning debris or other blockages from the exterior surfaces of the optical components 502). However, in some embodiments, a cleaning protocol may be initiated with the sole intention of performing diagnostics on one or more components of the system 700 (e.g., to determine the current state of the optical components 502). Because the cleaning apparatus may include one or more components that can apply defects to the system 700 (e.g., applying cleaning solution 712 to the optical components 502 using a sprayer 710), initiating a cleaning protocol may be a simple, repeatable, and consistent process by which defects can be introduced into the system 700 and monitored. Furthermore, because such a process is repeatable and consistent (e.g., as opposed to defects that arise as a result of precipitation from the ambient environment), results can be compared from one diagnostic test to another (e.g., enabling a process to accurately monitor the health of the components of the system 700 over time). In various embodiments, a cleaning protocol initiated to perform diagnostics on one or more components of system 700 can be a standardized cleaning protocol (e.g., the same cleaning protocol under the same conditions as would be performed to simply clean system 700). Alternatively, a cleaning protocol initiated to perform diagnostics on one or more components of system 700 can be a cleaning protocol that is modified to enhance its diagnostic capabilities (e.g., a cleaning protocol of different intensity or duration than the standard cleaning protocol and a cleaning protocol that uses different cleaning equipment).

[0161] 7A and 7B, the light emitter 424 may emit optical signals that are reflected from one or more defects and detected by one or more optical detectors 426. However, it is understood that some portions of the optical signals emitted by the light emitter 424 may pass through to the surrounding environment unaffected by any present defects (e.g., cleaning solution 712). These optical signals may then be reflected from objects in the surrounding environment and redirected to and detected by corresponding optical detectors 426 of the lidar device 410 (e.g., similar to the process illustrated in FIG. 6A). With this in mind, while some of the optical signals detected by the optical detectors 426 may represent cross-feedback signals (e.g., and thus may be used to perform diagnostics of the optical component 502), other optical signals may still be used to provide information about the surrounding environment (e.g., distances to objects in the surrounding environment based on the time-of-flight of the respective optical signals). In some embodiments, the cross-feedback signal may be disambiguated from the object reflection signal based on time-of-flight (e.g., a signal corresponding to a time-of-flight representing a distance close to a threshold distance, such as 5 cm from the optical component 502, may be determined to represent a cross-feedback signal). Additionally or alternatively, the cross-feedback signal may be disambiguated from the object reflection signal based on empirical data (e.g., a determination may be made during calibration that certain light emitter / light detector channels detect cross-feedback signals when a cleaning protocol is performed, and therefore signals from those channels are considered cross-feedback signals at runtime). Data from those detected signals corresponding to object detection signals may be arranged (e.g., by the system controller 402 and / or the lidar controller 416) into a three-dimensional point cloud (albeit with missing points corresponding to those areas containing defects). In this way, partial detection of the ambient environment may occur (i) during the same emission / detection cycle as diagnostic testing of the system's components and / or (ii) while performing a cleaning protocol using the cleaning device.

[0162] As described above, detected optical signals (e.g., cross-feedback signals) during application of one or more cleaning protocols can be used to determine the quality of one or more components of system 700 (e.g., by tracking the status of one or more defects over time). One method for making such determinations includes tracking the intensity of such cross-feedback signals over time. For example, each time an optical signal is emitted and a corresponding cross-feedback signal is detected, the intensity of the detected cross-feedback signal (e.g., maximum / peak intensity of the intensity waveform corresponding to the optical signal) and a timestamp associated with the detected cross-feedback signal may be recorded (e.g., stored in memory associated with system controller 402 or LIDAR controller 416). The optical detector 426 from which the detected cross-feedback signal is captured over time may be selected based on empirical studies in which the optical detector 426 in the array of optical detectors 426 detects the maximum intensity of cross-feedback and / or the optical detector 426 in the array of optical detectors 426 detects the cross-feedback that most highly correlates with the presence of a defect. By recording a series of timestamps and associated intensities over time (e.g., as additional puffs of pressurized air 722 are applied to optical component 502), a plot of intensity versus time for the detected cross-feedback signal can be made. Figure 8A illustrates such a plot.

[0163] Plot 802 represents the measured intensity (e.g., arbitrary units) of the cross-feedback signal over time (e.g., in seconds). In other embodiments, rather than simply plotting the intensity of one cross-feedback signal corresponding to one photodetector as detected at various times, an average of the cross-feedback intensity can be recorded over a series of time points. For example, any cross-feedback signal detected within a set period (e.g., having lengths of 1 μs, 5 μs, 10 μs, 20 μs, and 50 μs) can be grouped with other cross-feedback signals within that period, and the intensities of the cross-feedback signals over that period can be averaged and stored with an associated timestamp. A plot of these average intensities versus time can then be generated. Such a plot may look similar to FIG. 8A (e.g., including plot 802 representing the average intensity over time in seconds).

[0164] Once a plot 802 of intensity versus time (or average intensity versus time) is generated, the plot 802 may be fitted to a curve (e.g., exponential, quadratic, logarithmic, and linear). For example, as shown in FIG. 8A, the plot 802 may be fitted to a curve 804. Various values ​​from the equation of the fitted curve can be used to evaluate various characteristics of the underlying system. For example, as shown in FIG. 8A, the fitted curve 804 may have an equation of the following form: f(t)=A0e -t / τ +A final where f(t) is the intensity value at time t, and A0+A final is the initial value (i.e., peak value) of curve 804 at time t=0, and A final is the final value of curve 804 as t→∞, and τ is the time constant associated with the exponential decay.

[0165] Curve 804 correlates the time evolution of one or more defects over time, so that the value A 0、 A finalEach of A, A, and τ may provide information that can be used to evaluate the quality of the component in question (e.g., the hydrophobicity of the hydrophobic coating) and / or cleaning device. For example, for a hydrophobic coating under test, A may relate to the ability of the hydrophobic coating to cause water / cleaning solution on the hydrophobic coating to refuse to adhere to the hydrophobic coating, with large droplets forming on the hydrophobic coating, while τ may relate to the ability of the hydrophobic coating to shed from the hydrophobic coating. Additionally or alternatively, if a particular feature is present in the fitted curve 804 (e.g., A+A final is very high), one or more decisions can be made about the cleaning device (e.g., the cleaning device has a clog and is unable to apply an adequate amount of cleaning solution 712 via the sprayer 710). The metrics extracted from the curve 804 can be compared, for example, to the same metrics determined during a calibration measurement. For example, a calibration curve can be generated by fitting a curve to similar measurements of the cross-feedback signal on an optical component (e.g., a hydrophobic coating) whose quality (e.g., hydrophobicity) is well characterized (e.g., a brand new hydrophobic coating whose hydrophobic properties are specified within manufacturing tolerances, or a fully resolved hydrophobic coating whose hydrophobic properties are at their most realistic values). Then, A0+A0 of the calibration curve final The values ​​of τ, τ, and τ may be stored in memory associated with the system controller 402 or the rider controller 416 and / or may be stored in a server memory accessible by the system controller 402 / rider controller 416 (e.g., via the Internet or other data network).

[0166] When performing diagnostic tests, A 0、 A final , and the determined values ​​of τ are used to determine the quality of the optical component 502. 0、 A final , and τ may be compared to one or more calibration values. For example, A 0、 Afinal The determined values ​​of A0, A1, and τ are compared with the values ​​recorded for an ideal optical component (e.g., a brand new optical component). final , and can be compared with the calibrated values ​​of τ. 0、 A final , and one or more of the determined values ​​of τ are greater than or equal to a difference of 1%, 5% or more, 10% or more, 15% or more, 20% or more, and 25% or more relative to an ideal optical component (e.g., a difference of more than 1%, a difference of more than 5%, a difference of more than 10%, a difference of more than 15%, a difference of more than 20%, and a difference of more than 25%). 0、 A final , and τ is greater than a threshold difference from the calibrated value, then it may be determined that one or more qualities of the optical component are deficient (e.g., the hydrophobicity of a hydrophobic coating has deteriorated over time).

[0167] A 0、 A final In addition to, or instead of, simply comparing the determined values ​​of τ and τ to a threshold, alternative metrics can be generated. For example, a single logarithmic metric can be used to determine whether an optical component under test "passes" the test or "fails" the diagnostic test:

number

[0168] The exemplary fit curve 804 shown in FIG. 8A corresponds to an exponential decay function, although it is understood that other types of functions are possible and contemplated herein. For example, a linear or quadratic function could also be used. If a different type of function is used rather than an exponential function, the figure of merit may also be different. For example, if a linear function is used, the slope and y-intercept could be used instead as figures of merit.

[0169] In some embodiments, adverse weather conditions may affect measurements (e.g., detected cross-feedback signals) taken during application of a cleaning protocol. For example, if it is raining, in addition to the cleaning solution 712 being applied to the optical component 502 (e.g., as illustrated in FIG. 7A), rain may be deposited on the optical component 502. Thus, there may be additional imperfections (e.g., additional water droplets) on the optical component 502 when performing cross-feedback measurements. As such, any figure of merit (e.g., A) associated with a fitted curve determined during a rainfall may be misleading. 0、 A final , τ, or pass / fail metric) may be different than when there is no rain. Taking this into account, any decisions made about the underlying optical component 502 based on these figures of merit may be unreliable. Embodiments herein provide several techniques to compensate for this. For example, rather than comparing the strengths of the cross-feedback signals to calibration measurements taken in clear weather conditions, they may instead be compared to calibration measurements taken in the rain (e.g., a brand new hydrophobic coating may be subjected to a calibration test in the rain). Additionally or alternatively, an offset may be applied to the detected strengths of the cross-feedback signals and / or any of the metrics determined based on the detected strengths. For example, each of the cross-feedback strengths detected during rainy conditions may have its detected strength adjusted by a fixed amount (e.g., 5%, 10%, 15%, etc., or 1 arb. unit, 2 arb. unit, and 3 arb. unit). Similarly, A final Alternatively, the value of τ can be adjusted after it is determined to account for rain. For example, the determined τ can be decreased by 5%, 10%, 15%, etc., or by 1 second, 2 seconds, 3 seconds, etc.

[0170] While the examples provided herein are for rain, it is understood that other adverse weather conditions (e.g., snow, wind, cloudy skies, splashes, and heil) may be addressed in a similar manner. Additionally, the type of adverse weather condition present and / or the intensity of such weather conditions (e.g., rainfall / minute and wind speed) may be detected by other sensors associated with system 700 (e.g., radar 126 of vehicle 100 shown and described with reference to FIG. 1 ) or transmitted to lidar device 410 by another device (e.g., from a management server over the internet). The intensity of such weather conditions may be used to determine the degree to which each of the intensities of the cross-feedback signals and / or determined metrics is adjusted (e.g., rainfall / minute at a first level corresponds to a 5% reduction, rainfall / minute at a second level corresponds to a 10% reduction, etc.). The degree to which the adjustment of the intensity of the cross-feedback signals and / or determined metrics depends on the weather condition (e.g., rainfall amount / minutes) may be determined based on previous calibration measurements taken during various weather conditions.

[0171] Techniques are described above for fitting the intensity of the cross-feedback signal to a curve 804 and then making a determination about the quality of the underlying optical component based on a figure of merit (e.g., a time constant) associated with the fitted curve 804. In some embodiments, thresholds for one or more figures of merit may be determined using a machine learning model. For example, a classifier may be trained using labeled training data corresponding to cross-feedback intensity values ​​captured during a calibration experiment in which the quality of the underlying optical component was known. Alternatively, rather than plotting the intensity values ​​and then fitting a curve to the plotted values, a machine learning model (e.g., a classifier) ​​can be trained using labeled training data corresponding to the cross-feedback signal itself (e.g., a full intensity waveform corresponding to the cross-feedback signal intensity variation over time) when the quality of the underlying optical component is known. Then, when performing a diagnostic test, a series of detected cross-feedback signals (e.g., a full intensity waveform) can be fed to the machine learning model to determine the quality of the underlying optical component.

[0172] While FIG. 8A illustrates an analysis of cross-feedback signals detected during a cleaning protocol to assess the health of the optical component 502, it is understood that this is provided merely as an example and that other signals may additionally or alternatively be detected and analyzed. For example, crosstalk signals (as discussed above and described with reference to FIG. 6B ) may be detected and / or images (as discussed above and described with reference to FIG. 6D ) may be captured. These crosstalk signals and / or images may also be analyzed to determine a figure of merit regarding the condition of the optical component 502. Additionally, still other signals may be detected / analyzed. For example, internal reflections of optical signals emitted by the light emitter 424 may be detected and analyzed by the photodetector 426 (e.g., even if those optical signals do not represent cross-feedback signals, i.e., if the optical signals are emitted / detected by the light emitter 424 / photodetector 426, respectively, in the same channel of the lidar device 410).

[0173] Cleaning protocols (e.g., A 0、 A final Figures of merit determined by analyzing the cross-feedback signals during a given period (e.g., τ, or pass / fail metric) can also be used to characterize an entire fleet. For example, FIG. 8B is a scatter plot of several optical components 812 across a fleet. For example, each of the optical components 812 may represent a hydrophobic coating on the lidar device 410 of a different vehicle in a fleet of vehicles. As shown in FIG. 8B, each optical component 812 may be analyzed using the process described above to determine an A and τ value (results that are sent to a single device, such as a fleet management server). Based on these values, each of the optical components 812 is placed on the scatter plot. Additionally, a curve 814 is placed on the scatter plot of FIG. 8B that indicates the location of the pass / fail metric as it depends on A and τ. Any optical component 812 on the curve or above and to the left of the curve 814 may correspond to, for example, an optical component that "passes" 812 under the pass / fail metric, while any optical component 812 below and to the right of the curve 814 may correspond to an optical component that "fails" 812 under the pass / fail metric. Such scatter plots may be stored in memory (e.g., a fleet management server) for later access / review.

[0174] By reviewing the scatter plot of FIG. 8B , the overall health of the optical components 812 across the fleet may be assessed. For example, if a large number of optical components 812 fall into the “fail” category under a pass / fail metric, it may be determined that a different type of optical component 812 (e.g., a different type of hydrophobic coating) should replace those currently used in the fleet. Additionally or alternatively, if different types of optical components 812 (e.g., different types of hydrophobic coating) are used across the fleet, the relative performance of the different types of optical components 812 can be compared to determine whether one type is superior to another. The scatter plot of FIG. 8B can also be used to set thresholds. For example, if it is determined that 80% of the fleet of optical components 812 should correspond to a “pass” under a pass / fail metric, a review of the scatter plot of FIG. 8B can help determine where to place the curve 814 that separates “pass” from “fail.”

[0175] While the diagram in FIG. 8B is provided for a fleet of optical components 812, it is understood that a similar plot can be generated for a single optical component at various times. For example, a single optical component can be analyzed at various times to determine the corresponding A0 and τ values ​​at each time point. Each combination of A0 and τ for various times can then be plotted on a scatter plot. By reviewing such scatter plots, an analysis of the figure of merit of the optical component over time can be performed. Furthermore, while only two figures of merit are plotted in FIG. 8B, it is understood that in other scatter plots (e.g., three-dimensional and n-dimensional), scatter plots can also be used to track more than one figure of merit. Additionally or alternatively, multiple curves (or planes in the case of three-dimensional or n-dimensional scatter plots) dividing "pass" and "fail" may be used (e.g., when multiple thresholds are considered).

[0176] 9 is a flowchart diagram of a method 900, according to an example embodiment. In some embodiments, method 900 may be performed by a system (e.g., system 700 shown in FIGS. 7A and 7B). Method 900 may be performed in response to a request from a user (e.g., sent via a mobile application), in response to determining that one or more optical components may have a defect (e.g., based on data previously detected by one or more optical components), at startup (e.g., when the lidar device 410 begins use for object detection and avoidance or when a vehicle including the lidar device 410 leaves a depot), at regular intervals (e.g., hourly, six hourly, twelve hourly, daily, and weekly), etc.

[0177] At block 902, the method 900 may include applying a cleaning protocol to one or more optical components of the lidar device using a cleaning device.

[0178] At block 904, the method 900 may include emitting one or more optical signals from an optical emitter of the lidar device.

[0179] At block 906, the method 900 may include detecting, by a photodetector of the lidar device, reflections of the one or more optical signals.

[0180] At block 908, the method 900 may include determining, by the controller, based on the detected reflection of the one or more optical signals, that one or more defects exist within the one or more components or cleaning apparatus.

[0181] In some embodiments of method 900, block 902 may include spraying a cleaning solution onto at least one of the one or more optical components from a sprayer of the cleaning device. Block 902 may also include applying pressurized air onto the at least one optical component by a pressurized air supply of the cleaning device.

[0182] In some embodiments of the method 900, the one or more defects may include degradation of the hydrophobic coating. The degradation may correspond to a decrease in the hydrophobicity of the hydrophobic coating.

[0183] In some embodiments of the method 900, block 904 may include emitting a series of optical signals. Further, block 906 may include detecting a series of reflections of the one or more optical signals.

[0184] In some embodiments of method 900, block 908 may include generating a plot of the intensity of a series of reflections of one or more optical signals over time and fitting the generated plot to a function.

[0185] In some embodiments of method 900, block 908 may include comparing the function to which the generated plot is fitted to a calibration function generated during calibration of the lidar device.

[0186] In some embodiments of the method 900, the function to which the generated plot is fitted may include an exponential function. Furthermore, the peak value and time constant of the exponential function may represent a figure of merit.

[0187] In some embodiments of method 900, block 908 may include accounting for weather conditions in the surrounding environment of the lidar device. Further, in some embodiments, accounting for weather conditions in the surrounding environment of the lidar device may include applying one or more offsets to the intensity plot based on the weather conditions.

[0188] In some embodiments, the method 900 may also include implementing corrective action based on the one or more defects determined to exist.

[0189] In some embodiments of method 900, block 902 may include spraying a cleaning solution onto at least one of the one or more optical components from a sprayer of the cleaning device. Block 902 may also include wiping the at least one optical component to remove the cleaning solution with a wiper of the cleaning device.

[0190] The present disclosure is not limited with respect to the specific embodiments described in this application, which are intended as illustrations of various aspects. Many modifications and variations can be made without departing from the spirit and scope of the present disclosure, as will be apparent to those skilled in the art. In addition to the methods and apparatus recited herein, functionally equivalent methods and apparatus within the scope of the present disclosure will be apparent to those skilled in the art from the foregoing description. Such modifications and variations are intended to fall within the scope of the appended claims.

[0191] The above detailed description, with reference to the accompanying drawings, describes various features and functions of the disclosed systems, devices, and methods. In the figures, like symbols typically refer to like components identically, unless the context dictates otherwise. The exemplary embodiments described herein and in the figures are not intended to be limiting. Other embodiments may be utilized, and other changes may be made, without departing from the scope of the subject matter presented herein. It will be readily understood that the aspects of the present disclosure, as generally described herein and illustrated in the figures, can be arranged, substituted, combined, separated, and designed in a wide variety of different configurations, all of which are expressly contemplated.

[0192] With respect to any or all of the message flow diagrams, scenarios, and flowcharts in the figures and discussed herein, each step, block, operation, and / or communication may represent the processing of information and / or the transmission of information according to the exemplary embodiments. Alternative embodiments are included within the scope of these exemplary embodiments. In these alternative embodiments, for example, operations described as steps, blocks, transmissions, communications, requests, responses, and / or messages may be executed in an order different from that shown or discussed, such as substantially simultaneously or in reverse order, depending on the functionality involved. Furthermore, more or fewer blocks and / or operations may be used in any of the message flow diagrams, scenarios, and flowcharts discussed herein, and these message flow diagrams, scenarios, and flowcharts may be combined with each other, either in part or in whole.

[0193] A step, block, or operation corresponding to the processing of information may correspond to circuitry that can be configured to perform specific logical functions of the methods or techniques described herein. Alternatively or additionally, a step or block corresponding to the processing of information may correspond to a module, segment, or portion of program code (including associated data). The program code may include one or more instructions executable by a processor to perform specific logical operations or actions in the method or technique. The program code and / or associated data may be stored in any type of computer-readable medium, such as a storage device including a RAM, a disk drive, a solid-state drive, or another storage medium.

[0194] Additionally, steps, blocks, or acts representing one or more information transmissions may correspond to information transmissions between software and / or hardware modules in the same physical device, although other information transmissions may be information transmissions between software and / or hardware modules in different physical devices.

[0195] The particular arrangement shown in the figures should not be considered limiting. It should be understood that other embodiments may include more or fewer of each element shown in a given figure. Furthermore, some of the illustrated elements may be combined or omitted. Furthermore, example embodiments may include elements not illustrated in the figures.

[0196] While various aspects and embodiments are disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, the true scope being indicated by the following claims.

Claims

1. applying a cleaning protocol to one or more optical components of a Light Detection and Ranging (LIDAR) device using a cleaning device, wherein applying the cleaning protocol includes applying moisture to the one or more optical components, and wherein the cleaning protocol is applied according to a regular schedule or in response to a trigger event; emitting one or more optical signals from a light emitter of the lidar device during the cleaning protocol; detecting, by a photodetector of the LIDAR device during the cleaning protocol, reflections of the one or more optical signals, including reflections from the moisture; and determining, by a controller, based on the detected reflections of the one or more optical signals, that one or more defects exist within the one or more optical components or within the cleaning device.

2. The method of claim 1 , wherein the cleaning protocol is applied according to the periodic schedule.

3. 3. The method of claim 2, wherein the periodic schedule provides for application of the cleaning protocol once every 30 minutes, once every hour, once every four hours, once every 12 hours, once every day, once every two days, once every four days, once every week, once every two weeks, or once every month.

4. The method of claim 1 , wherein the cleaning protocol is applied in response to the trigger event.

5. The trigger event is via a vehicle user interface associated with the lidar device; Using a mobile application on your mobile device; or The method of claim 4 , comprising one or more signals sent by a user via a browser-based application.

6. The method of claim 5 , wherein the one or more signals indicate a required cleaning.

7. The method of claim 5 , wherein the one or more signals are indicative of a requested component reliability analysis.

8. The method of claim 4 , wherein the trigger event comprises one or more signals transmitted from the controller.

9. The method of claim 4 , wherein the trigger event comprises a weather event.

10. The method of claim 4 , wherein the triggering event comprises a communication from an off-board computing device.

11. The method of claim 10 , wherein the off-board computing device comprises a fleet management device.

12. The method of claim 4 , wherein the trigger event comprises a determination by the controller that one or more objects detected in the surrounding environment have been improperly identified.

13. The method of claim 4 , wherein the trigger event comprises a determination by the controller that one or more detected optical signals of a given type exceed a given intensity threshold.

14. 14. The method of claim 13, wherein the one or more detected optical signals of the given type include one or more detected cross-feedback signals or one or more detected cross-talk signals.

15. one or more optical components; an optical emitter configured to emit one or more optical signals; a light detection and ranging (lidar) device comprising: a light detector configured to detect reflections of the one or more optical signals; a cleaning device configured to apply a cleaning protocol to the one or more optical components, wherein applying the cleaning protocol comprises applying moisture to the one or more optical components, the cleaning device being configured to apply the cleaning protocol according to a regular schedule or in response to a trigger event; and and a controller configured to determine that one or more defects are present in the one or more optical components or the cleaning device based on reflections, including reflections from the moisture, detected during performance of a cleaning protocol.

16. The system of claim 15 , wherein the cleaning protocol is applied according to the periodic schedule.

17. 17. The system of claim 16, wherein the periodic schedule provides for application of the cleaning protocol once every 30 minutes, once every hour, once every four hours, once every 12 hours, once every day, once every two days, once every four days, once every week, once every two weeks, or once every month.

18. The system of claim 15 , wherein the cleaning protocol is applied in response to the trigger event.

19. The system of claim 18 , wherein the triggering event comprises a communication from an off-board computing device.

20. Receiving data corresponding to reflections of one or more optical signals detected by a photodetector of a Light Detection and Ranging (LIDAR) device during performance of a cleaning protocol, the one or more optical signals being emitted by a light emitter of the LIDAR device in response to a cleaning device applying the cleaning protocol to one or more optical components of the LIDAR device, wherein applying the cleaning protocol includes applying moisture to the one or more optical components, and the cleaning protocol is applied according to a periodic schedule or in response to a trigger event; a computing device configured to determine, based on the received data including data corresponding to reflection from the moisture, that one or more defects are present within the one or more optical components or the cleaning device.

21. The method of claim 1, further comprising modifying the detected optical signal to simulate a signal in the absence of rain or snow.

Images