SYSTEMS AND METHODS FOR MONITORING AND RECALITING INFRASTRUCTURE AND VEHICLE SENSORS

Abstract

One procedure involves identifying the current trajectory of an automated vehicle based on its movement through a maneuvering environment, calculating a distance-based difference between the automated vehicle's current trajectory and an expected trajectory, determining whether the distance-based difference exceeds a variation threshold, and recalibrating one or more sensors of an infrastructure system in response to the distance-based difference exceeding the variation threshold.

Description

AREA

[0001] This disclosure relates to the identification of problems associated with an infrastructure sensor suite and / or a vehicle sensor suite. More specifically, this disclosure relates to the identification of these problems and the recalibration of sensor(s) of the infrastructure sensor suite and / or the vehicle sensor suite based on the identification of these problems. GENERAL STATE OF THE ART

[0002] The statements in this section merely provide background information relating to the present disclosure and may not represent the state of the art.

[0003] Infrastructure-guided shunting of one or more vehicles in a shunting environment typically relies on communication between a sensor suite associated with the infrastructure and a sensor suite associated with each of the one or more vehicles. However, this communication can be unreliable in some cases, leading to inefficiencies in the shunting process. For example, identifying such communication problems is time-consuming and often difficult, and thus, due to late identification, a potential recalibration of the infrastructure sensor suite and / or the vehicle sensor suite occurs too late in the shunting process. This disclosure addresses these and other problems related to the identification and / or recalibration of the infrastructure sensor suite and / or the vehicle sensor suite. SUMMARY

[0004] This section provides a general summary of the revelation and is not a comprehensive revelation of its full scope or all of its features.

[0005] The present disclosure provides a method comprising: identifying the current trajectory of an automated vehicle based on its movement through a maneuvering environment, wherein the current trajectory is based on the automated vehicle's current location and speed; calculating a distance-based difference between the automated vehicle's current trajectory and its expected trajectory, the expected trajectory being based on a target path and speed; and determining whether the distance-based difference exceeds a variation threshold.and recalibrating one or more sensors of an infrastructure system in response to the distance-based difference exceeding the variation threshold, wherein the recalibration of the one or more sensors is based on a vehicle perception analysis; further comprising: causing one or more sensors of the automated vehicle to be recalibrated in response to the distance-based difference exceeding the variation threshold; wherein the recalibration of the one or more sensors of the infrastructure system or of the one or more sensors of the automated vehicle includes intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration, or a combination thereof;wherein the vehicle perception analysis includes a field of view analysis, a power analysis, a signal strength of reflected rays, identification of one or more objects, distance measurements, detection accuracy, or a combination thereof; further comprising: transmitting one or more instructions to the automated vehicle in response to the distance-based difference meeting the variation threshold; and causing the automated vehicle to move from one workstation of the shunting environment to another workstation of the shunting environment based on the one or more instructions; further comprising: aggregating a distance-based difference for each automated vehicle of a plurality of automated vehicles;Generating a statistical distribution of an expected trajectory for each automated vehicle of the multitude of automated vehicles based on the aggregated distance-based differences; and determining whether the distance-based difference exceeds the variation threshold for each automated vehicle of the multitude of automated vehicles based on the statistical distribution; and further comprising: transmitting an alarm in response to an unsuccessful recalibration of one or more sensors, wherein the alarm is a maintenance request.

[0006] The present disclosure provides a system comprising: an infrastructure system configured to: identify the current trajectory of an automated vehicle based on its movement through a maneuvering environment, wherein the current trajectory is based on the automated vehicle's current location and speed; calculate a distance-based difference between the automated vehicle's current trajectory and its expected trajectory, the expected trajectory being based on a target path and speed; determine whether the distance-based difference exceeds a variation threshold and recalibrate one or more sensors of the infrastructure system in response.that the distance-based difference exceeds the variation threshold, wherein the recalibration of one or more sensors is based on a vehicle perception analysis; and the automated vehicle configured to: recalibrate one or more sensors of the automated vehicle in response to the distance-based difference exceeding the variation threshold; wherein the recalibration of one or more sensors of the infrastructure system or of one or more sensors of the automated vehicle includes intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration, or a combination thereof; wherein the vehicle perception analysis includes a field-of-view analysis, a power analysis, a signal strength of reflected rays, an identification of one or more objects,includes distance measurements, detection accuracy, or a combination thereof; wherein the infrastructure system is further configured to: transmit one or more instructions to the automated vehicle in response to the distance-based difference meeting the variation threshold; and cause the automated vehicle to move from one workstation in the shunting environment to another workstation in the shunting environment based on the one or more instructions; wherein the infrastructure system is further configured to: aggregate a distance-based difference for each automated vehicle of a plurality of automated vehicles; generate a statistical distribution of an expected trajectory for each automated vehicle of the plurality of automated vehicles based on the aggregated distance-based differences; and determine,whether the distance-based difference exceeds the variation threshold for each automated vehicle of the multitude of automated vehicles based on the statistical distribution; and wherein the infrastructure system is further configured to: transmit an alarm in response to an unsuccessful recalibration of one or more sensors, wherein the alarm is a maintenance request.

[0007] The present disclosure provides one or more non-transient, computer-readable media that store processor-executable instructions which, when executed by at least one processor, cause the at least one processor to: identify a current trajectory of an automated vehicle based on its movement through a maneuvering environment, wherein the current trajectory is based on the automated vehicle's current location and speed; calculate a distance-based difference between the automated vehicle's current trajectory and an expected trajectory, wherein the expected trajectory is based on a target path and speed; and determine whether the distance-based difference exceeds a variation threshold.and recalibrating one or more sensors of an infrastructure system in response to the distance-based difference exceeding the variation threshold, wherein the recalibration of the one or more sensors is based on a vehicle perception analysis; wherein the at least one processor is further caused to: cause one or more sensors of the automated vehicle to be recalibrated in response to the distance-based difference exceeding the variation threshold; wherein the recalibration of the one or more sensors of the infrastructure system or of the one or more sensors of the automated vehicle includes intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration, or a combination thereof;wherein the vehicle perception analysis includes a field of view analysis, a power analysis, a signal strength of reflected rays, identification of one or more objects, distance measurements, detection accuracy, or a combination thereof; wherein the at least one processor is further caused to: transmit one or more instructions to the automated vehicle in response to the distance-based difference meeting the variation threshold; and cause the automated vehicle to move from one workstation of the shunting environment to another workstation of the shunting environment based on the one or more instructions; wherein the at least one processor is further caused to: aggregate a distance-based difference for each automated vehicle of a plurality of automated vehicles;Generating a statistical distribution of an expected trajectory for each automated vehicle of the plurality of automated vehicles based on the aggregated distance-based differences; and determining whether the distance-based difference exceeds the variation threshold for each automated vehicle of the plurality of automated vehicles based on the statistical distribution; and wherein the at least one processor is further caused to: transmit an alarm in response to an unsuccessful recalibration of one or more sensors, wherein the alarm is a maintenance request.

[0008] Further areas of application will become apparent from the description provided herein. It is understood that the description and specific examples serve only for illustration and are not intended to limit the scope of this disclosure. DRAWINGS

[0009] To fully understand the revelation, various forms of it will now be described by way of example with reference to the attached drawings, in which the following applies: Fig. Figure 1 illustrates a system for automated vehicle maneuvering according to one or more embodiments of the present disclosure; Fig. Figure 2 illustrates an exemplary vehicle, which is characterized by the in Fig. 1 system shown is ranked according to one or more embodiments of the present disclosure; Fig. Figure 3 is a flowchart illustrating an exemplary procedure for monitoring and / or recalibrating one or more sensors associated with an automated vehicle and / or an infrastructure system according to one or more embodiments of the present disclosure; Fig. Figure 4 is a flowchart illustrating another exemplary method for monitoring and / or recalibrating one or more sensors associated with an automated vehicle and / or an infrastructure system according to one or more embodiments of the present disclosure; and Fig. Figure 5 is a block diagram illustrating an exemplary computer system according to one or more embodiments of the present disclosure.

[0010] The drawings described herein serve only for illustration and are not intended to limit the scope of the present disclosure in any way. DETAILED DESCRIPTION

[0011] The following description is merely exemplary and is not intended to limit the present disclosure, application, or uses. It is understood that in all drawings, corresponding reference numerals indicate identical or corresponding parts and features.

[0012] One or more of the examples described herein provide a means for identifying one or more problems (e.g., performance and / or operational problems) associated with an infrastructure sensor suite and / or a vehicle sensor suite, and for recalibrating the infrastructure sensor suite and / or the vehicle sensor suite (e.g., recalibrating one or more sensors) based on one or more problems that are identified. In one or more embodiments, the identification of problems and / or recalibration of the infrastructure sensor suite and / or the vehicle sensor suite can be implemented based on communication between the infrastructure sensor suite and / or the vehicle sensor suite in manufacturing processes, without requiring a human operator to identify any problems with the infrastructure sensor suite and / or the vehicle sensor suite.In a case where a large volume of vehicles is manufactured, one or more embodiments thereby provide a more efficient and time-saving process with a more secure communication link between the infrastructure sensor suite and / or the vehicle sensor suite.

[0013] Now, with reference to Fig. Figure 1 shows an automated vehicle marshaling system (AVM system) 100 for maneuvering one or more automated and / or semi-automated vehicles 102 (e.g., one or more vehicles 102a, 102b) within a marshalling environment (e.g., a manufacturing plant or a parking lot). The AVM system 100 includes an infrastructure system 104. The infrastructure system 104 includes a sensor component 106 that communicates with a set of infrastructure sensors 108, such as one or more cameras, lidar, radar, and / or ultrasonic devices. The set of infrastructure sensors 108 is configured to monitor the movement of the vehicle(s) 102 as the vehicle(s) 102 move through the marshalling environment.In one or more examples, the set of infrastructure sensors 108 is configured to monitor a common global coordinate system for monitoring the movement of the vehicle(s) 102 as the vehicle(s) 102 move through the shunting environment. In one or more examples, the set of infrastructure sensors 108 is also configured to detect, identify, and / or verify behavior (e.g., operating characteristics or conditions) with respect to each of the vehicles 102a, 102b as the vehicles 102a, 102b move through the shunting environment, as described herein.

[0014] Infrastructure system 104 also includes a wireless communication component 110, which provides communication between infrastructure system 104 and the vehicle(s) 102. Additionally, infrastructure system 104 includes an infrastructure controller 112. The infrastructure controller 112 is configured to centrally control the operation of each of the vehicles 102a, 102b in a closed-loop system. However, it is understood that the infrastructure controller 112 is configured to centrally control the operation of each of the vehicles 102a, 102b within the functional and / or technical limits of any given system. For example, the operation of each of the vehicles 102a, 102b includes propulsion, braking, and / or steering of the vehicle(s) 102. It is understood that the infrastructure controller 112 can be located within infrastructure system 104 or externally relative to infrastructure system 104.

[0015] The infrastructure controller 112 includes an infrastructure-side AVM algorithm 114 (e.g., an AVM software module) configured to use one or more algorithmic learning models to perform vehicle translation analysis and / or vehicle perception analysis, as described herein. It is understood that a vehicle-side AVM algorithm (e.g., a vehicle-side AVM algorithm 212) is also configured to use the one or more algorithmic learning models to support the vehicle translation analysis and / or vehicle perception analysis performed by the infrastructure-side AVM algorithm 114. It is further understood that the vehicle-side AVM algorithm 212 is also configured to use the one or more algorithmic learning models to perform the vehicle translation analysis and / or vehicle perception analysis itself (e.g.,by the vehicle-side AVM algorithm 212). In one or more examples, the one or more algorithmic learning models can be trained dynamically (e.g., in real time) via a supervised or unsupervised learning process. It is understood that the one or more algorithmic learning models can be, for example, a neural network model or any other type of learning model. It is also understood that the infrastructure-side AVM algorithm 114 and / or the vehicle-side AVM algorithm 212 can execute the one or more algorithmic learning models to perform the vehicle translation analysis and / or the vehicle perception analysis on each of the vehicles 102a, 102b.

[0016] The infrastructure-side AVM algorithm 114 is also configured to facilitate communication between the infrastructure controller 112 and a vehicle controller (e.g., a vehicle controller 200, as in Fig. 2 shown), which is assigned to each of the vehicles 102a, 102b. In one or more examples, communication between the infrastructure controller 112 and the vehicle controller 200 can take the form of an exchange of one or more infrastructure shunting messages and / or one or more vehicle shunting messages.

[0017] In one or more embodiments, the infrastructure-side AVM algorithm 114 can execute one or more algorithmic learning models to perform vehicle translation analysis and / or vehicle perception analysis based on the exchange of one or more infrastructure shunting messages and / or one or more vehicle shunting messages at each of the vehicles 102a, 102b.

[0018] In one or more embodiments, the infrastructure system 104 is configured to store expected behavior associated with any vehicle configured to move through the shunting environment. For example, the expected behavior is stored in a database (not shown) associated with the infrastructure system 104. As another example, the database may be located internally or externally with respect to the infrastructure system 104. As another example, the expected behavior stored may be historical data used as a basis for vehicle translation analysis and / or vehicle perception analysis. As another example, the expected behavior stored may relate to the expected behavior of a vehicle near a specific workstation of one or more workstations associated with the shunting environment.

[0019] In one or more embodiments, the infrastructure-side AVM algorithm 114 is further configured to perform one or more analyses to support the detection, identification, and / or verification of the behavior with respect to each of the vehicles 102a, 102b. In one or more examples, the infrastructure-side AVM algorithm 114 is configured to verify the behavior with respect to each of the vehicles 102a, 102b based on whether the identified behavior detected with respect to each of the vehicles 102a, 102b is consistent with the expected behavior of the vehicle at a specific location within the shunting environment.

[0020] In one or more embodiments, the one or more analyses used to support the detection, identification, and / or verification of the behavior of each of the vehicles 102a, 102b can also be used as a basis for performing the vehicle translation analysis. In one or more examples, the one or more analyses can compare a target path and / or a target speed of each of the vehicles 102a, 102b with a current location and / or speed of each of the vehicles 102a, 102b. As another example, the set of infrastructure sensors 108 is configured to monitor each of the vehicles 102a, 102b in order to determine the current location and / or speed of each of the vehicles 102a, 102b.As yet another example, the set of infrastructure sensors 108 is configured to monitor any angle of each of the vehicles 102a, 102b, such as, but not limited to, the front of each of the vehicles 102a, 102b, the rear of each of the vehicles 102a, 102b, and / or one or more sides of each of the vehicles 102a, 102b. As a further example, the set of infrastructure sensors 108 is also configured to monitor a side-to-side positioning associated with each of the vehicles 102a, 102b, which is a distance between a center point of any vehicle (e.g., a reference point 210, as in ). Fig. 2 shown) and a center point of a specific lane on which the vehicle is moving.

[0021] In one or more examples, the vehicle translation analysis may involve calculating a distance-based difference between the current trajectory of each of vehicles 102a and 102b and their expected trajectory. It is understood that the expected trajectory of each of vehicles 102a and 102b is based on the expected location and / or speed of each of vehicles 102a and 102b. It is also understood that the current trajectory of each of vehicles 102a and 102b is based on the current location and / or speed of each of vehicles 102a and 102b.

[0022] In one or more embodiments, the vehicle translation analysis can further include the generation (e.g., creation) of a statistical distribution of the expected trajectory of each of the vehicles 102a, 102b in real time, based on an aggregation of the distance-based difference specific to each of the vehicles 102a, 102b. As an example, the statistical distribution assigned to each of the vehicles 102a, 102b is used as the basis for determining whether the distance-based difference specific to each of the vehicles 102a, 102b exceeds a variation threshold. For example, the variation threshold can represent a predefined range that is determined as an acceptable distance-based difference without impeding the movement of the vehicles 102a, 102b through the shunting environment.It is understood that the predefined area can be, for example, any area based on any ranking-related considerations or other considerations.

[0023] In one or more embodiments, vehicle translation analysis can be used to identify a vehicle positioning slope associated with the movement of each of the vehicles 102a, 102b over time as each of the vehicles 102a, 102b traverses (e.g., moves over) the shunting environment. In one or more examples, and in a case where the vehicle(s) 102 are under full or primary control by the infrastructure system 104, vehicle translation analysis can be used to identify any problems with an infrastructure-based sensor suite.For example, the infrastructure-based sensor suite may include the set of infrastructure sensors 108 and / or any of the components within the infrastructure system 104 that support the set of infrastructure sensors 108, such as the infrastructure controller 112, the infrastructure-side AVM algorithm 114, the sensor component 106, and / or the wireless communication component 110. In one or more examples, and in a case where the vehicle(s) 102 is under complete control by the vehicle itself (e.g., the vehicle(s) 102) or primary control by the vehicle itself, vehicle translation analysis can be used to identify any problems with a vehicle sensor suite. For example, the vehicle-based sensor suite may include the multitude of onboard sensors 204 and / or any of the components within the vehicle(s) that support the multitude of onboard sensors 204, as in . Fig. 2 shows, for example, the vehicle control system 200, one or more actuators 202, a human-machine interface (MMS) 206, a vehicle system 208 and / or the vehicle-side AVM algorithm 212.

[0024] In one or more embodiments, the vehicle translation analysis is further configured to determine one or more trends associated with varying sizes of vehicle groups moving across certain locations within the shunting environment. In other words, the varying sizes of vehicle groups can represent different sizes of groups of vehicles composed of varying numbers of vehicles within those groups. As one example, the one or more trends can be determined based on historical data associated with moving averages of each vehicle group from one or more preceding vehicle groups. As another example, the one or more determined trends can indicate a variation associated with the variation threshold.In other words, one or more specific tendencies can indicate, for example, a higher-than-expected variation associated with the variation threshold, or a lower-than-expected variation associated with the variation threshold. As yet another example, one or more specific tendencies can indicate variation-related biases associated with specific locations within the shunting environment, relative to the variation threshold. For example, the variation-related biases might include instances where vehicles, over time, may veer to the right or left as they move through the specific location(s) within the shunting environment.

[0025] In one or more examples, vehicle perception analysis can include a field of view analysis, a power analysis, signal strength of reflected beams, identification of one or more objects, distance measurements, detection accuracy, or a combination thereof. As another example, vehicle perception analysis can be performed at any time and location within the shunting environment while each of the vehicles 102a and 102b traverses the shunting environment.

[0026] In one or more embodiments, the infrastructure-side AVM algorithm 114 can define a bounding frame 116 (e.g., one or more bounding frames 116a, 116b, as in Fig. (shown in Figure 1) create a boundary frame assigned to the vehicle(s) 102. As an example, boundary frame 116 (e.g., a virtual vehicle layout) delimits the vehicle(s) 102 within a matrix grid. As another example, and insofar as more than one vehicle 102 is shunted by the infrastructure system 104, boundary frames 116a and 116b each delimit each vehicle 102a and 102b, respectively. As a further example, the creation (e.g., generation) of boundary frame(s) 116 can assist in the precise shunting of the vehicle(s) 102 by the shunting environment and thus support the operational functionality of the infrastructure sensor suite and / or the vehicle sensor suite.

[0027] In one or more embodiments, the AVM system 100 also includes a vehicle manufacturing cloud system 118, which can act as the central cloud system that manages and / or facilitates the manufacturing process associated with the vehicle(s) 102 described herein. In one or more examples, the infrastructure system 104 is configured to communicate wirelessly with the vehicle manufacturing cloud system 118, and in some cases, the vehicle manufacturing cloud system 118 is configured to cause the infrastructure system 104 to monitor the progress of the vehicle(s) 102 as the vehicle(s) 102 move through the shunting environment.

[0028] With further reference to Fig. 2. The vehicle(s) 102 can be powered in various ways, for example, by an electric motor and / or an internal combustion engine. It is also understood that the vehicle(s) 102 can be any type of vehicle powered by an electric motor and / or an internal combustion engine, such as a car, a truck, a robot, an aircraft, and / or a boat. The vehicle(s) 102 generally includes the vehicle control unit 200, the one or more actuators 202, the multiple onboard sensors 204, the MMS 206, and the vehicle system 208. The vehicle(s) 102 also has the reference point 210, that is, a specified point within a space defined by a vehicle body, which identifies the location of the vehicle(s) 102.For example, reference point 210 is a geometric center point where the respective longitudinal and lateral center axes of vehicle(s) 102 intersect. Alternatively, reference point 210 is a point where vehicle(s) 102 is located while navigating towards a waypoint.

[0029] In some examples, the vehicle control unit 200 is configured or programmed to control the operation of one or more of the vehicle's brakes, drive system (e.g., controlling the acceleration of the vehicle(s) 102 by controlling one or more internal combustion engines, electric motors, hybrid motors, etc.), steering, air conditioning, interior and / or exterior lighting, etc. In other examples, the vehicle control unit 200 is further configured or programmed to determine whether and when it should control such operations concerning the vehicle(s) 102 instead of a human driver. It is understood that any of the operations associated with the vehicle(s) 102 can be facilitated by an automated, a semi-automated, or a manual mode.For example, the automated mode can facilitate the complete control of any operation by the vehicle control unit 200 without the assistance of the human driver. Similarly, the semi-automated mode can facilitate the at least partial control of any operation by the human driver in combination with the vehicle control unit 200. Finally, the manual mode can facilitate the complete control of operations by the human driver without the assistance of the vehicle control unit 200.

[0030] The vehicle control unit 200 includes one or more processors (not shown) or may be communicatively coupled to them (e.g., via a vehicle communication bus). For example, the one or more processors may be a controller or the like, which is included in the vehicle(s) 102 for monitoring and / or controlling various vehicle controls, such as a powertrain control, a brake control, a steering control, etc. The vehicle control unit 200 is generally arranged for various communications in a vehicle communication network (not shown), which may include a bus in the vehicle(s) 102, such as a Controller Area Network (CAN) or the like, and / or other wired and / or wireless mechanisms.

[0031] The vehicle control unit 200 transmits messages via a vehicle network to various devices in the vehicle(s) 102 and / or receives messages from the various devices, for example, the one or more actuators 202, the MMS 206, etc. Alternatively or additionally, in cases where the vehicle control unit 200 includes multiple devices, the vehicle communication network is used for communication between devices that are referred to in this disclosure as the vehicle control unit 200. Furthermore, as discussed below, various other controllers and / or sensors of the vehicle control unit 200 provide data via the vehicle communication network.

[0032] Additionally, the vehicle control unit 200 is configured via a vehicle-side AVM algorithm 212 to communicate through a vehicle-to-infrastructure communication network, for example, to identify the trajectory of the vehicle(s) 102 relative to the intended travel path. It is understood that, based on the vehicle's / vehicles' assembly level, the vehicle's / vehicles' movement can utilize the vehicle sensor suite to a greater or lesser extent and will thus rely on the infrastructure sensor suite to move around in the shunting environment (e.g., via shunting equipment).

[0033] The vehicle control unit 200 is also configured via the vehicle-side AVM algorithm 212 to communicate with other traffic objects (e.g., vehicles, infrastructure, etc.) through a wireless vehicle communication interface, such as via a vehicle-to-vehicle communication network. The vehicle communication network represents one or more mechanisms through which the vehicle control unit 200 of the vehicle(s) 102 communicates with other traffic objects. For example, the vehicle communication network can consist of one or more wireless communication mechanisms, including any desired combination of wireless (e.g., cellular, wireless, satellite, microwave, and / or radio frequency) communication mechanisms and any desired network topology (or topologies if multiple communication mechanisms are used).Examples of vehicle communication networks include cellular networks, Bluetooth®, IEEE 802.11, dedicated short range communications (DSRC), and / or wide area networks (WANs), which include the internet and provide data communication services.

[0034] The vehicle actuators 202 are implemented via circuits, chips, or other electronic and / or mechanical components that can actuate various vehicle subsystems in accordance with appropriate control signals. The actuators 202 can be used to control the braking, acceleration, and steering of the vehicle(s) 102. The vehicle control unit 200 can be programmed to activate the vehicle actuators 202, which include drive, steering, and / or braking, based on the planned acceleration or deceleration of the vehicle(s) 102.

[0035] The multitude of onboard sensors 204 includes a variety of devices to provide data to the vehicle control system 200. For example, the multitude of onboard sensors 204 may include object detection sensors (e.g., lidar sensor(s)) located on or in the vehicle(s) 102, providing relative locations, sizes, and / or shapes of one or more objects surrounding the vehicle(s), such as additional vehicles, bicycles, robots, drones, etc., moving alongside, in front of, and / or behind the vehicle(s). As another example, one or more of the multitude of onboard sensors 204 may be one or more radar sensors mounted on one or more bumpers of the vehicle(s), capable of providing the positions of the object(s) relative to the location of each of the vehicles 102.

[0036] The multiple onboard sensors 204 can include a camera sensor, for example, to provide front, side, and rear views, etc., of an area surrounding the vehicle(s) 102. As another example, the vehicle control unit 200 can be programmed to receive sensor data from camera sensor(s) and implement image processing techniques to detect a road, infrastructure elements, etc. The vehicle control unit 200 can also be programmed to determine a current vehicle location based on location coordinates (e.g., GPS coordinates) received by the vehicle(s) 102 and indicating the location of the vehicle(s) 102 using a GPS sensor (not shown).

[0037] The MMS 206 is configured to receive information from the human driver(s) during the operation of the vehicle(s) 102. Furthermore, the MMS 206 is configured to display information to the human driver, such as an occupant of the vehicle(s) 102. In some variations, the vehicle control unit 200 is programmed to receive target data (e.g., location coordinates) from the MMS 206.

[0038] The vehicle system 208 is configured to control each of the subsystems within the vehicle(s) 102 and to facilitate requests via each of the components described above (e.g., the vehicle controller 200, the one or more actuators 202, the multitude of onboard sensors 204, and / or the MMS 206). Accordingly, the vehicle(s) 102 can be autonomously guided toward a waypoint using at least the multitude of onboard sensors 204. Route guidance can be performed using the vehicle's location, the distance to be traveled, a queue for vehicle maneuvering, etc.

[0039] Fig. Figure 3 is a flowchart illustrating an exemplary procedure 300 for monitoring and / or recalibrating one or more sensors associated with an automated vehicle (e.g., vehicle 102) and / or an infrastructure system (e.g., infrastructure system 104). In procedure 302, the current trajectory of the automated vehicle is identified. For example, the current trajectory of the automated vehicle is identified based on its movement through a maneuvering environment. As another example, the current trajectory is based on the current location and / or speed of the automated vehicle. Yet another example is the identification of the current trajectory of the automated vehicles by the infrastructure system.

[0040] In process 304, a distance-based difference is calculated between the current trajectory of the automated vehicle and an expected trajectory. For example, the expected vehicle trajectory is based on a target path and speed of the automated vehicle. In process 306, it is determined whether the distance-based difference exceeds a variation threshold (e.g., a distance variation limit).

[0041] In process 308, one or more sensors (e.g., the set of infrastructure sensors 108) of the infrastructure system are recalibrated in response to the distance-based difference exceeding the variation threshold. For example, the recalibration of the one or more sensors is based on a vehicle perception analysis. In one or more embodiments, the infrastructure system is configured to cause one or more sensors (e.g., the plurality of onboard sensors 204) of the automated vehicle to be recalibrated. In one or more examples, the infrastructure system is configured to cause the one or more sensors of the automated vehicle to be recalibrated in response to the distance-based difference exceeding the variation threshold.For example, recalibrating one or more sensors of the infrastructure system and / or one or more sensors of the automated vehicle involves intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration, or a combination thereof. As another example, vehicle perception analysis involves field-of-view analysis, power analysis, signal strength of reflected beams, identification of one or more objects, distance measurements, detection accuracy, or a combination thereof.

[0042] In one or more embodiments, the infrastructure system is configured to transmit one or more instructions to the automated vehicle. For example, the transmission of the one or more instructions occurs in response to the distance-based difference meeting the variation threshold. The infrastructure system is further configured to cause the automated vehicle to move from one workstation in the shunting environment to another based on the one or more instructions. In one or more embodiments, the infrastructure system is configured to transmit an alarm in response to an unsuccessful recalibration of one or more sensors. For example, the alarm is a maintenance request.However, it is understood that the alarm can be any type of request associated with a functionality relating to the automated vehicle and / or the infrastructure system.

[0043] In one or more embodiments, the infrastructure system is configured to aggregate a distance-based difference for each automated vehicle within a plurality of automated vehicles. The infrastructure system is also configured to generate a statistical distribution of the expected trajectory of each automated vehicle within the plurality of automated vehicles. For example, the generation of the statistical distribution of the expected trajectory of each automated vehicle within the plurality of automated vehicles is based on the aggregated distance-based differences. Furthermore, the infrastructure system is configured to determine, for each automated vehicle within the plurality of automated vehicles, whether the distance-based difference exceeds the variation threshold.For example, the determination of whether the distance-based difference for each automated vehicle out of the multitude of automated vehicles exceeds the variation threshold is based on the statistical distribution.

[0044] Fig. Figure 4 is a flowchart illustrating another exemplary procedure 400 for monitoring and / or recalibrating one or more sensors associated with an automated vehicle (e.g., vehicle 102) and / or an infrastructure system (e.g., infrastructure system 104). In procedure 402, a current trajectory of the automated vehicle is identified. For example, the current trajectory of the automated vehicle is identified based on the automated vehicle's movement through a maneuvering environment. As another example, the current trajectory is based on the automated vehicle's current location and / or speed. Yet another example is the identification of the automated vehicle's current trajectory by the infrastructure system.In process 404, a distance-based difference is calculated between the current trajectory of the automated vehicle and an expected trajectory of the automated vehicle. For example, the expected vehicle trajectory is based on a target path and a target speed of the automated vehicle.

[0045] In Operation 406, a determination is made as to whether the distance-based difference exceeds a variation threshold. In one or more examples, and in a case where a determination is made that the distance-based difference exceeds the variation threshold, in Operation 408, one or more sensors (e.g., the set of infrastructure sensors 108) of the infrastructure system are recalibrated in response to the distance-based difference exceeding the variation threshold. For example, the recalibration of the one or more sensors is based on a vehicle perception analysis. As another example, the recalibration of the one or more sensors of the infrastructure system involves intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration, or a combination thereof.As yet another example, vehicle perception analysis includes a field of view analysis, a power analysis, a signal strength of reflected rays, an identification of one or more objects, distance measurements, detection accuracy or a combination thereof.

[0046] In one or more examples, a determination that the distance-based difference exceeds the variation threshold may indicate abnormal functionality associated with the operational behavior of the infrastructure sensor suite and / or the vehicle sensor suite. For example, infrastructure system 104 is configured to then transmit one or more operational commands to a relevant sensor suite system (e.g., another infrastructure sensor suite and / or the vehicle sensor suite) to dynamically identify, verify, and / or diagnose a problem affecting the infrastructure sensor suite and / or the vehicle sensor suite. In one or more examples, sensor recalibration for the infrastructure sensor suite and / or the vehicle sensor suite may occur in a closed-loop system.It is understood, however, that sensor recalibration for the infrastructure sensor suite and / or the vehicle sensor suite can occur within the functional and / or technical constraints of any given system. For example, sensor recalibration can include camera calibration, radar calibration, and others. As another example, camera calibration can include intrinsic calibration, which is associated with the camera's internal parameters; extrinsic calibration, which is associated with a field of view related to the camera's orientation; and / or color calibration. As yet another example, radar calibration can include frequency calibration, angle calibration, and / or power calibration.

[0047] In other examples, and in one case where, during operation 406, a determination is made that the distance-based difference does not exceed the variation threshold, the infrastructure system is configured to cause the automated vehicle to move from one shunting environment workstation to another during operation 410. For example, the automated vehicle is caused to move from one shunting environment workstation to another based on one or more instructions. As another example, the infrastructure system is configured to transmit the one or more instructions to the automated vehicle. Yet another example is the transmission of the one or more instructions in response to the distance-based difference meeting (not exceeding) the variation threshold.In one or more examples, the finding that the distance-based difference does not exceed the variation threshold may indicate that the infrastructure sensor suite and / or the vehicle sensor suite are outputting sensor data within an expected variation and therefore no corrective action is required.

[0048] Fig. Figure 5 illustrates an operating environment, such as a computer system, that facilitates the execution of one or more of the systems and procedures described herein. More specifically, the systems and procedures described herein may be implemented using a computing device 502. For example, the computing device 502 may be a personal computer, a desktop computer, a laptop computer, a tablet, a handheld computer, a server, a workstation, a mainframe computer, a wearable computer, a supercomputer, or a combination thereof. It is understood, however, that the foregoing examples of computing device 502 are not exhaustive and that the computing device 502 may be any type of processing or computing device.The computing device 502 generally includes a processor 504, a display adapter 506, one or more input / output ports 508, one or more input / output components 510, a network adapter 512, a power supply 514, and a memory 516. However, it is understood that the computing device 502 may include any additional components and need not include any of the listed components (e.g., the processor 504, the display adapter 506, the one or more input / output ports 508, the one or more input / output components 510, the network adapter 512, the power supply 514, and the memory 516).

[0049] The processor 504 is configured to provide instructions to the computing device 502, enabling the computing device 502 to process one or more tasks, which involve implementing a software program to perform one or more operations, as described in more detail herein. It is also understood that the computing device 502 can contain any number of processors 504. The display adapter 506 can be a graphics card or a video card, providing the computing device 502 with the ability to display content on a display device 518.For example, the display device 518 may be any screen, monitor, and / or light-emitting component associated with any personal computer, desktop, laptop, tablet, handheld computer, server, workstation, mainframe, wearable computer, supercomputer, or a combination thereof. It is understood, however, that the foregoing examples of the display device 518 are not exhaustive and that the display device 518 may be any type of device capable of providing a visual display.

[0050] The input / output port(s) 508 provides a number of interfaces (e.g., sockets) for one or more cables to be connected to the computing device 502. It is understood that any number of input / output ports 508 may be present on the computing device 502. For example, the input / output port(s) 508 provides a means for the computing device 502 to receive signals and / or data from an external device connected to the computing device 502 by one or more cables. As another example, the input / output port(s) 508 provides a means for the computing device 502 to send signals and / or data to an external device connected to the computing device 502 by one or more cables.The input / output component(s) 510 may include one or more components that support the input / output port(s) 508, such as, but not limited to, a switch, a push button, a pressure pad, a float switch, a keypad, a radio receiver, or a combination thereof.

[0051] The network adapter 512 can be any type of network interface controller configured to provide a means of communication over a network 520 with another computing device, such as a remote computing device 522. For example, the remote computing device 522 can be a user device, such as a mobile phone, smartphone, tablet, laptop, or a combination thereof. The power supply 514 is configured to convert high-voltage alternating current (e.g., AC) to direct current (e.g., DC) to provide power to the other components (e.g., the processor 504, the display adapter 506, the one or more input / output port(s) 508, the one or more input / output component(s) 510, the network adapter 512, and the memory 516) of the computing device 502.

[0052] Additionally, the memory 516 can be a mass storage device and / or system memory, such as a hard disk drive, a memory card, a solid-state drive, random access memory (RAM), or a combination thereof. The memory 516 is configured to provide memory for instructions and data associated with the operation of the computing device 502. The memory 516 can generally include an operating system 524, calibration software 526, and calibration data 528. For example, the operating system 524 is configured to manage and / or process any of the data and / or instructions associated with the calibration software 526 and / or the calibration data 528, as described in more detail herein.

[0053] Furthermore, the computing device 502 includes a system bus 530, which is configured to connect each of the various components (e.g., the processor 504, the display adapter 506, the one or more input / output ports 508, the one or more input / output component(s) 510, the network adapter 512, the power supply 514, and the memory 516) of the computing device 502. It is also understood that each component of the computing device 502 and the functionality assigned to each component of the computing device 502 can be implemented within the remote computing device 522. While the operating environment, which is in Fig. Figure 5 illustrates a specific configuration that is associated with at least the computing device 502, the network 520 and the remote computing device 522; it is understood that the operating environment can be configured in any way.

[0054] Thus, one or more examples of the present disclosure provide a means for monitoring an infrastructure sensor suite and / or a vehicle sensor suite based on the exchange of one or more messages between the infrastructure sensor suite and / or the vehicle sensor suite. The present disclosure also provides a means for recalibrating the infrastructure sensor suite and / or the vehicle sensor suite based on the detection of one or more problems with either the infrastructure sensor suite and / or the vehicle sensor suite.

[0055] Unless expressly stated otherwise herein, all numerical values ​​indicating mechanical / thermal properties, percentages of compositions, dimensions and / or tolerances, or other parameters are to be understood as modified by the word "approximately" or "about" when describing the scope of this disclosure. This modification is desirable for various reasons, including industrial practice, material, manufacturing and assembly tolerances, and testability.

[0056] As used in this document, the phrase "at least one of A, B and C" should be interpreted as meaning a logical (A OR B OR C) using a non-exclusive logical OR, and should not be interpreted as meaning "at least one of A, at least one of B and at least one of C".

[0057] In this application, the terms "controller" and / or "module" may refer to, be part of, or include: an application-specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinational logic circuit; a field-programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the foregoing, such as in a system-on-a-chip.

[0058] The term storage is a subset of the term computer-readable medium. The term computer-readable medium, as used here, does not include transitory electrical or electromagnetic signals that propagate through a medium (such as a carrier wave); the term computer-readable medium can therefore be considered tangible and non-transient.Non-restrictive examples of a non-transient, tangible, computer-readable medium include non-volatile memory circuits (such as a flash memory circuit, a wipeable programmable read-only memory circuit, or a mask read-only memory circuit), volatile memory circuits (such as a static random access memory circuit or a dynamic random access memory circuit), magnetic storage media (such as an analog or digital magnetic tape or a hard disk drive), and optical storage media (such as a CD, a DVD, or a Blu-ray Disc).

[0059] The devices and procedures described in this application may be implemented in whole or in part by a specialized computer created by configuring a general-purpose computer to perform one or more specific functions contained in computer programs. The functional blocks, flowchart components, and other elements described above serve as software specifications that can be translated into computer programs through the routine work of an experienced technician or programmer.

[0060] The description of the revelation is purely exemplary, and thus variations that do not deviate from the content of the revelation are intended to fall within its scope. Such variations are not to be considered a deviation from the nature and scope of the revelation.

[0061] According to the present invention, one or more non-transient computer-readable media are provided that store processor-executable instructions which, when executed by at least one processor, cause the at least one processor to: identify a current trajectory of an automated vehicle based on a movement of the automated vehicle through a maneuvering environment, wherein the current trajectory is based on a current location and speed of the automated vehicle; calculate a distance-based difference between the current trajectory of the automated vehicle and an expected trajectory of the automated vehicle, wherein the expected vehicle trajectory is based on a target path and a target vehicle speed; determine whether the distance-based difference exceeds a variation threshold;and recalibrating one or more sensors of an infrastructure system in response to the distance-based difference exceeding the variation threshold, wherein the recalibration of the one or more sensors is based on a vehicle perception analysis.

[0062] According to one embodiment, the at least one processor is further caused to do the following: Cause one or more sensors of the automated vehicle to be recalibrated in response to the distance-based difference exceeding the variation threshold.

[0063] According to one embodiment, the recalibration of one or more sensors of the infrastructure system or of one or more sensors of the automated vehicle includes intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration or a combination thereof.

[0064] According to one embodiment, the vehicle perception analysis includes a field of view analysis, a power analysis, a signal strength of reflected rays, an identification of one or more objects, distance measurements, detection accuracy or a combination thereof.

[0065] According to one embodiment, the at least one processor is further caused to: transmit one or more instructions to the automated vehicle in response to the distance-based difference meeting the variation threshold; and cause the automated vehicle to move from one workstation in the shunting environment to another workstation in the shunting environment based on the one or more instructions.

[0066] According to one embodiment, the at least one processor is further caused to: aggregate a distance-based difference for each automated vehicle of a plurality of automated vehicles; generate a statistical distribution of an expected trajectory of each automated vehicle of the plurality of automated vehicles based on the aggregated distance-based differences; and determine whether the distance-based difference exceeds the variation threshold for each automated vehicle of the plurality of automated vehicles based on the statistical distribution.

[0067] According to one embodiment, the at least one processor is further caused to do the following: transmit an alarm in response to an unsuccessful recalibration of one or more sensors, wherein the alarm is a maintenance request.

Claims

[1] Procedure, encompassing: Identifying a current trajectory of an automated vehicle based on the movement of the automated vehicle through a maneuvering environment, wherein the current trajectory is based on a current location and speed of the automated vehicle; Calculating a distance-based difference between the current trajectory of the automated vehicle and an expected trajectory of the automated vehicle, where the expected vehicle trajectory is based on a target path and a target speed of the automated vehicle; Determine whether the distance-based difference exceeds a threshold of variation; and Recalibrating one or more sensors of an infrastructure system in response to the distance-based difference exceeding the variation threshold, wherein the recalibration of the one or more sensors is based on a vehicle perception analysis. [2] The method of claim 1, further comprising: Causing one or more sensors of the automated vehicle to be recalibrated in response to the distance-based difference exceeding the variation threshold. [3] Method according to claim 2, wherein the recalibration of one or more sensors of the infrastructure system or of one or more sensors of the automated vehicle includes intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration or a combination thereof. [4] Method according to claim 2, wherein the vehicle perception analysis includes a field of view analysis, a power analysis, a signal strength of reflected rays, an identification of one or more objects, distance measurements, detection accuracy or a combination thereof. [5] The method of claim 1, further comprising: Transmitting one or more instructions to the automated vehicle in response to the distance-based difference meeting the variation threshold; and To cause the automated vehicle to move from one workstation in the shunting environment to another workstation in the shunting environment based on one or more instructions. [6] The method of claim 1, further comprising: Aggregating a distance-based difference for each automated vehicle out of a large number of automated vehicles. [7] Method according to claim 6, further comprising: Generating a statistical distribution of an expected trajectory for each automated vehicle from the multitude of automated vehicles based on the aggregated distance-based differences; and Determine whether the distance-based difference exceeds the variation threshold for each automated vehicle in the multitude of automated vehicles based on the statistical distribution. [8] Method according to claim 1, further comprising: Transmitting an alarm in response to an unsuccessful recalibration of one or more sensors, where the alarm is a maintenance request. [9] System, comprehensive: an infrastructure system configured to do the following: Identifying a current trajectory of an automated vehicle based on the movement of the automated vehicle through a maneuvering environment, wherein the current trajectory is based on a current location and speed of the automated vehicle. Calculating a distance-based difference between the current trajectory of the automated vehicle and an expected trajectory of the automated vehicle, where the expected vehicle trajectory is based on a target path and a target vehicle speed. Determine whether the distance-based difference exceeds a variation threshold, and Recalibrating one or more sensors of the infrastructure system in response to the distance-based difference exceeding the variation threshold, wherein the recalibration of the one or more sensors is based on a vehicle perception analysis; and the automated vehicle, which is configured to do the following: Recalibrating one or more sensors of the automated vehicle in response to the distance-based difference exceeding the variation threshold. [10] System according to claim 9, wherein the recalibration of one or more sensors of the infrastructure system or of one or more sensors of the automated vehicle includes intrinsic calibration, extrinsic calibration, color calibration, frequency calibration, angle calibration, power calibration or a combination thereof. [11] System according to claim 9, wherein the vehicle perception analysis includes a field of view analysis, a power analysis, a signal strength of reflected rays, an identification of one or more objects, distance measurements, detection accuracy or a combination thereof. [12] System according to claim 9, wherein the infrastructure system is further configured as follows: Transmitting one or more instructions to the automated vehicle in response to the distance-based difference meeting the variation threshold; and To cause the automated vehicle to move from one workstation in the shunting environment to another workstation in the shunting environment based on one or more instructions. [13] System according to claim 10, wherein the infrastructure system is further configured as follows: Aggregating a distance-based difference for each automated vehicle out of a large number of automated vehicles. [14] System according to claim 13, wherein the infrastructure system is further configured as follows: Generating a statistical distribution of an expected trajectory for each automated vehicle from the multitude of automated vehicles based on the aggregated distance-based differences; and Determine whether the distance-based difference exceeds the variation threshold for each automated vehicle in the multitude of automated vehicles based on the statistical distribution. [15] System according to claim 10, wherein the infrastructure system is further configured to: Transmitting an alarm in response to an unsuccessful recalibration of one or more sensors, where the alarm is a maintenance request.

Images