Monitoring system for autonomous vehicle operation

Information

  • Patent Grant
  • 11305782
  • Patent Number
    11,305,782
  • Date Filed
    Friday, January 11, 2019
    5 years ago
  • Date Issued
    Tuesday, April 19, 2022
    2 years ago
Abstract
Disclosed are devices, systems and methods for a monitoring system for autonomous vehicle operation. In some embodiments, a vehicle may perform self-tests, generate a report based on the results, and transmit it to a remote monitor center over one or both of a high-speed channel for regular data transfers or a reliable channel for emergency situations. In other embodiments, the remote monitor center may determine that immediate intervention is required, and may transmit a control command with high priority, which when received by the vehicle, is implemented and overrides any local commands being processed. In yet other embodiments, the control command with high priority is selected from a small group of predetermined control commands the remote monitor center may issue.
Description
TECHNICAL FIELD

This document relates to vehicle monitoring and control.


BACKGROUND

Autonomous vehicle navigation is a technology for sensing the position and movement of a vehicle, and based on the sensing, autonomously controlling the vehicle to navigate to a destination. Autonomous vehicle navigation can have important applications in the transportation of people, goods and services.


SUMMARY

Disclosed are devices, systems and methods for a monitoring system for autonomous operation of a vehicle, such as a passenger car or a truck. The monitoring system may be configured to transmit control commands that can override the local commands of the vehicle in order to ensure passenger and vehicular safety. This may be achieved by combining information from multiple resources on or near the vehicle, and periodically reporting this information to the monitoring system over a reliable communication network.


In one aspect, the disclosed technology can be used to provide a method for monitoring and controlling a vehicle. This method, which may be implemented at the vehicle, includes periodically generating, with a first period, a report; periodically transmitting, with a second period, the report to a remote monitor center; receiving a control command from the remote monitor center; and implementing the control command from the remote monitor center when the control command has a high priority, wherein an implementation of the control command overrides an implementation of a local control command, and wherein the control command is selected from a predetermined set of control commands.


In another aspect, the disclosed technology can be used to provide a method for monitoring and controlling a vehicle. This method, which may be implemented at a remote monitor center includes periodically receiving, from the vehicle, a report; determining whether the report comprises any immediately actionable status indicators; selecting a control command from a predetermined set of control commands; and transmitting, to the vehicle, the control command with a high priority when the report comprises at least one immediately actionable status indicator, and wherein an implementation of the control command with the high priority at the vehicle overrides an implementation of a local control command at the vehicle.


In another aspect, the disclosed technology can be used to provide a method for monitoring and controlling a vehicle. This method, which may be implemented at the vehicle, includes: collecting status information from one or more systems implemented in the vehicle; classifying the status information by a plurality of status indicators including one or more critical status indicators and one or more uncritical status indicators; generating a critical status report based on the status information associated with the one or more critical status indicators immediately upon receipt of such status information; and generating an uncritical status report based on the status information associated with the one or more uncritical status indicators with a period that varies with the one or more uncritical status indicators.


In another aspect, the disclosed technology can be used to provide a method for monitoring and controlling a vehicle. This method, which may be implemented at the vehicle, includes: collecting status information from one or more systems implemented in the vehicle; classifying the status information by a plurality of status indicators including a warning status indicator, an error status indicator, and a fatal status indicator; generating periodically a status report based on the status information associated with the warning status indicators; generating, upon receipt of status information associated with the fatal status indicator, a status report based on the status information associated with the fatal status indicator immediately; performing, upon receipt of status information associated with the error status indicator, a recovering process on a corresponding system, and, if the recovering process is unsuccessful, generating a status report based on the status information associated with the error status indicator; and sending the generated status report to an external monitoring system.


In another aspect, the disclosed technology can be used to provide a computer apparatus that includes a processor configured to implement a method disclosed in this patent document.


In another aspect, the disclosed technology can be used to provide a computer readable program medium having code stored thereupon, the code, when executed by a processor, causing the processor to implement a method disclosed in this patent document.


The above and other aspects and features of the disclosed technology are described in greater detail in the drawings, the descriptions and the claims.





BRIEF DESCRIPTION OF THE DRAWINGS


FIG. 1 shows a block diagram of an example of the system architecture for vehicular wireless communication, including monitoring and controlling autonomous vehicle operation;



FIG. 2 shows a block diagram of an example of the vehicular components that may support a monitoring system for autonomous vehicle operation;



FIG. 3 shows a flow diagram for an example method of a monitoring system for autonomous vehicle operation;



FIGS. 4A and 4B show two example timelines of operation of a monitoring system for autonomous vehicle operation;



FIG. 5 shows a flowchart of an example method, which may be implemented in a vehicle, for monitoring autonomous vehicle operation;



FIG. 6 shows a flowchart of another example method, which may be implemented in a remote monitor center, for monitoring autonomous vehicle operation; and



FIG. 7 shows an example of a hardware platform that can implement some techniques described in the present document.



FIG. 8 shows a flowchart of another example method that may be implemented in a vehicle, for monitoring autonomous vehicle operation.



FIG. 9 shows a flowchart of another example method that may be implemented in a vehicle, for monitoring autonomous vehicle operation.





DETAILED DESCRIPTION

Disclosed are devices, systems and methods that can be used for embodiments of a monitoring system for autonomous vehicle operation.


The operation of an autonomous vehicle may involve minimal driver interaction, or no driver at all, but the safety of the passengers is paramount. To ensure the safety of the vehicle and the passengers, the vehicle status and driving and environmental conditions may be continuously monitored. The monitoring may be performed both locally and in a remote monitor center. This may provide the advantage that error handling can be immediately enabled under different scenarios.


The disclosed technology in this patent document provides solutions that can be used to address the above and other technical issues in remote monitoring and controlling the operation of vehicles.



FIG. 1 shows a block diagram of an example of the system architecture for vehicular wireless communication and monitoring of autonomous vehicle operation. In an example, the vehicle system 102 includes the vehicle 102-1 and a black box 102-2. The black box 102-2 may be, for example, a storage unit that stores data and reports that the vehicle generates. The black box 102-2 may as also store local and remote control commands that are used to operate the vehicle. In some embodiments, contents of the black box 102-2 may be periodically used to improve the autonomous and monitoring operations of the system.


In addition to the vehicle system 102, the system architecture may include the remote monitor center 108 and at least two communication channels that the vehicle 102-1 may use to transmit messages, various reports or data to the remote monitor center 108. The first channel may be a bidirectional (two-way) high-speed channel 106 for regular (e.g., periodic) data transfers. The second channel may be a unidirectional (one-way, vehicle to remote monitor center) or bidirectional reliable channel 108. The second channel may only be used for emergency situations. One of the advantages of the embodiment shown in FIG. 1 is the presence of redundant channels, which increases the probability that reports and status indicators transmitted from the vehicle are received by the remote monitor center.


In various embodiments, the high-speed channel 106 may employ protocols such as Long-Term Evolution (LTE), Wi-Fi, IEEE 802.11, Bluetooth, Dedicated Short-Range Communication (DSRC), Communication Air-interface Long and Medium range (CALM), and other transmission protocols that may have been designed for Intelligent Transportation System (ITS) implementations.


In some embodiments, the reliable channel 108 may employ a low-rate forward error-correcting (FEC) code or retransmissions to ensure robust communication even when adverse conditions are present over the wireless channels. In some embodiments, the reliable channel 108 may employ protocols or physical layer (PHY) waveforms that leverage one or more of frequency, time, space or code diversity.



FIG. 2 shows a block diagram of an example of the vehicular components that may support a monitoring system for autonomous vehicle operation. In some embodiments, a vehicle hardware system may include multiple electronic control units (ECUs), denoted 204-1, 204-2 and 204-3 in FIG. 2, each of which may control multiple sensors, devices and interfaces. For example, an ECU 204-1 may control at least a first sensor 206-1 and a second sensor 206-2, whereas another ECU 204-2 may control an external device 206-3, and yet another ECU 204-3 may control a vehicle controller area network (CAN) 206-4 and an alternate vehicle interface 206-5. The combinations described in FIG. 2 are not meant to be limiting, and it is understood that an ECU may control any number of sensors, devices or interfaces.


In some embodiments, the sensors controlled by an ECU may include one or more of a Global Positioning System (GPS) sensor, a radar sensor, a LIDAR (light detection and ranging) sensor, an ultrasonic sensor, and a camera (or CMOS image sensor). An ECU and its respective sensors, devices or interfaces engage in two-way communication, which enables the ECU to receive data from the sensors and transmit commands to the sensors.


Some of the ECUs (204-1, 204-2 and 204-3) may include at least one hardware system (or sub-system) and at least one software system. Some ECUs may support self-tests for these systems and sub-systems. Furthermore, if the ECU is controlling any external sensors, devices or interfaces, it may typically include the self-tests for those external sensors, devices or interfaces, respectively. In an example, the ECU that is connected to the vehicle collects information on the vehicle itself.


The analyses of these self-tests result in the generation of reports. In some embodiments, the ECUs may analyze the data generated from self-tests and generate reports based on the analysis. Reports from the ECUs are collected by the monitor ECU 202. In some embodiments, the individual ECUs (204-1, 204-2 and 204-3) may analyze the results of its own self-tests and send the report to the monitor ECU 202. In other embodiments, the individual ECUs may send the raw data to the monitor ECU, which then analyzes the raw data to generate results and reports. In the latter embodiments, the raw data from sensors controlled by different ECUs may be combined prior to analysis to provide reports at a higher systems level, and which cannot be generated by the individual ECUs.



FIG. 3 shows a flow diagram for an example method 300 of a monitoring operation for autonomous vehicle operation. At step 302, a vehicle may perform one or more self-tests for each of the ECUs in that vehicle. As discussed herein, the self-tests are performed by each ECU for its hardware and software systems, as well as for all the sensors, devices and interfaces under its control. In some embodiments, a sensor self-test may include collecting data and comparing it to a baseline to ensure that the sensor is operating as intended. Self-tests may include measuring the state of the vehicle, e.g. position, velocity, acceleration, and checking the measured values against predetermined thresholds to verify normal operating conditions. The thresholds may be updated based on current driving and environmental conditions.


At step 304, the data from the self-tests may be analyzed, either at the respective ECU or at the monitor ECU, as described in the context of FIG. 2. In some embodiments, the analysis of the data may result in the determination of a status, or a status indicator. Based on the status, a report comprising specific information elements may be generated. The information or data included in a report may be based on the status indicator. The status indicators may have levels or tiers, as shown in the example table below:













Status
Data in report







OK
Basic vehicle (dynamic) information; e.g. location, fuel



level, engine temperature, etc.


Warning
Warning messages and logs


Error
Error logs


Fatal
Sensor data that may identify the fatal condition









As seen in the above example table, the size of the report generated may depend on the status. The transmitted report when the status is “OK” may include basic information for vehicle operation (dynamic or current state), and is typically much smaller than the report transmitted when the status is “Fatal,” in which case the report may include the raw data from the sensor that has identified the fatal condition.


Furthermore, in some embodiments, a message with a certain status may transmit a report with the data indicated in the table above, as well as the data from the rows above it. For example, if the status is “Error,” then the report may include the error logs, as well as the warning messages and logs, and the basic information for vehicle operation associated with the “OK” status. This may enable the remote monitor center to better analyze a potential issue since more data is readily available.


At step 306, the report that was generated is transmitted to the remote monitor center. As discussed previously, the report may be sent on at least one of a high-speed channel and a reliable channel. In some embodiments, the report may also be stored on a local storage device.


In some embodiments, the report may be partitioned using a partitioning scheme and different portions may be transmitted over different channels. For example, if the status is “Warning,” and the vehicle has selected to send the basic information for vehicle operation in addition to the warning messages and logs, it may send the former (“OK” status information) over the high-speed channel and the latter (“Warning” status information) over the reliable channel.


At step 308, the vehicle determines whether error handling is required based on the status that was determined at step 304. In some embodiments, when the status indicator is “OK” or “Warning,” no error handling is required (the “NO” path in FIG. 3), and operation of the monitoring system returns to step 302. In contrast, if the status indicator is “Error” or “Fatal,” it is then determined that error handling is warranted (the “YES” path in FIG. 3).


At step 310, the vehicle may take measures to recover from the causes that led to the “Error” or “Fatal” status indicators. In an example, if the error message indicated that a particular sensor, which is required for autonomous operation of the vehicle, was not functioning properly, a reboot command to those sensors may be sent. In the case where the sensor does not return to normal operation or is the cause of a “Fatal” status indicator, a series of commands to have the vehicle park in a safe place may be issued.


At step 312, which may occur at any point in the timeline after step 306 and before the completion of step 310, a remote command is received from the remote monitor center. The remote command may be received based on the remote monitor center analyzing the report transmitted by the vehicle, and determining that a certain action must be taken to ensure passenger and vehicular safety. In some embodiments, the remote command has a higher priority than the local commands being issued by the vehicle. In some embodiments, the higher priority may guarantee that the remote command is executed, and would result in the implementation of the remote command overriding the implementation of any of the local commands.


Like with any other computer-implemented technologies, the remote monitor center may be susceptible to hacking, and thus the number and content of the remote commands that may be issued is limited. For example, only commands that decelerate the vehicle and bring it safely to a stop may be issued by the remote monitor center. This may, for example, ensure that hacking the remote monitor center would never result in the vehicle being involved in an adverse high-speed situation. The predetermined set of control commands that are issued by the remote monitor center may be updated for different environmental and driving conditions.



FIGS. 4A and 4B show two example timelines of operation of a monitoring system for autonomous vehicle operation. These figures comprise common steps, elements or features, which will not be explicitly described in the context of each figure.


As shown in FIG. 4A, the vehicle generates a report (402-1, 402-2,402-3, . . . ) at a period T1. In an example, the vehicle transmits a report (404-1, 404-2, 404-3), with a second period T2, to the remote monitor center when the status of the report is “OK” in reports 402-1 through 402-9.


The generated report 402-10 is assumed to have a “Fatal” status indicator, and the corresponding report is immediately transmitted (404-4) to the remote monitor center. In response to the “Fatal” status indicator, the vehicle issues local control commands in an effort to mitigate the situation. The local commands are executed (406) starting at the generation of the “Fatal” status indicator. It is further assumed that the local control commands have an execution time Tlocal, as shown in FIG. 4A.


Subsequent reports that are generated at the vehicle continue to have a “Fatal” status indicator, and continue to be transmitted (404-5 and 404-6) to the remote monitor center. At some later time (408), a control command is received from the remote monitor center. This remote control command has a higher priority than the local commands issues by the vehicle. As a result, the execution of the remote control command overrides the execution of the local control commands. As shown in FIG. 4A, the remaining time (409) of Tlocal is not executed, but rather the remote control command execution (410) commences.


In the example timeline shown in FIG. 4B, it is assumed that the report 402-10 has an “Error” status indicator, which results in the report being immediately transmitted (404-4) to the remote monitor center. Local commands issued by the vehicle to mitigate the situation are executed (406), commencing at the generation of the report 402-10. In this example, the local commands resolve the situation prior to the generation of the next report 402-11, which is generated with an “OK” status indicator.


Control commands from the remote monitor center are subsequently received (408). In an example, the remote control commands are identical to the local control commands, and are not executed since they are not currently necessary. In another example, the remote control commands are different from the previously issued local control commands, and the vehicle executes them (410). However, there is no overriding of local commands since their execution has been completed.



FIG. 5 shows a flowchart of an example method 500 that may be implemented in a vehicle, for monitoring autonomous vehicle operation. The method 500 includes, at step 502, periodically generating a report with a first period. In some embodiments, the first period is very short, and the report is generated at the vehicle at a high frequency to ensure a rapid response to any adverse condition that may arise. Examples of adverse conditions may include the detection of unknown environments (e.g., a construction zone, scene of an accident), hazardous weather conditions or a loss of communication with the remote monitor center.


The method 500 includes, at step 504, periodically transmitting the report to a remote monitor center with a second period. The second period is typically longer than or equal to the first period. In some embodiments, the second period may be based on the status indicator. For example, a report corresponding to the “OK” status will be sent at a lower frequency than the report associated with the “Warning” status. Similarly, for the “Error” and “Fatal” status indicators, the report may be sent as soon as it is generated, in which case the second period is equal to the first period.


The method 500 includes, at step 506, receiving a control command from the remote monitor center. The control command is received in response to the remote monitor center receiving the periodically transmitted report. In some embodiments, the remote monitor center issues commands to the vehicle based on the report, which may include data from one or more sensors, as well as reports from other vehicles.


The method 500 includes, at step 508, implementing the control command from the remote monitor center when it has a high priority. In some embodiments, the control command received may have a high priority when the recently transmitted report included a “Error” or “Fatal” status indicator. The received control command may instruct the vehicle to take precautionary measures to ensure passenger and vehicular safety, and are able to override the local commands the vehicle is currently executing.


In some embodiments, control commands received from the remote monitor center with a high priority may initialize an emergency parking module, which may include instructions to determine the best way to reduce the vehicle's velocity until it comes to a complete stop. In other embodiments, the vehicle may also continue to frequently transmit its status during this process to the remote monitor center over the reliable channel. If communication to the remote monitor center has been compromised, the vehicle may choose to send its status to another vehicle that does have a connection to the remote monitor center.


In an example, a “Fatal” status indicator may be generated in a report if a tire sensor senses that there is a leak in one of the tires. This report is immediately transmitted to the remote monitor center. Since passenger safety is paramount, the vehicle issues local control commands to decelerate and move toward the closest servicing station. The planned route may be based on archived maps stored on the vehicle's local storage.


The remote monitor center receives the report with the “Fatal” status indicator and the data from the tire sensor. Based on the report and the data, it also determines that deceleration and immediate servicing are warranted.


However, since the remote monitor center may be communicating with other vehicles, it notices that there is significant gridlock due to an accident on the route to the closest servicing station. Thus, the remote monitor center issues a command with high priority to decelerate and divert to a servicing station that is further away than the closest servicing station. When this command is received by the vehicle, it may override the local control commands and the vehicle will now proceed to the servicing station indicated by the remote monitor center.



FIG. 6 shows a flowchart of another example method 600 that may be implemented in a remote monitor center, for monitoring autonomous vehicle operation. The method 600 includes, at step 602, periodically receiving a report from a vehicle that is being monitored by the remote monitor center. In some embodiments, the frequency at which the reports are received may depend on the status indicators contained within the reports.


In other embodiments, the remote monitor center may request that the vehicle transmit the report at a frequency that is different from the frequency typically associated with the existing status indicator. Since the remote monitor center may be monitoring and controlling multiple vehicles in an area, it has a higher system-level view that an individual vehicle may not have, and may therefore request more frequency reporting if the probability of an adverse situation arising is higher than normal.


In yet other embodiments, the remote monitor center may determine the reporting frequency on a history of status indicators and report for that vehicle. In an example, the history that is considered may span hours, days or weeks, and may be implemented using a sliding window function to give greater weight to more recent status indicators.


The method 600 includes, at step 604, determining whether the report comprises any immediately actionable status information. In some embodiments, the “Error” and “Fatal” status indicators may be flagged as immediately actionable. In other embodiments, and in the presence of other possible environmental factors, the “Warning” status may be flagged as immediately actionable. If it is determined that the report includes at least one immediately actionable status information, the control command that is transmitted at step 508 may be done with high priority.


The method 600 includes, at step 606, selecting a control command from a predetermined set of control commands. Since the remote monitor center may be susceptible to hacking, the number and types of commands that the remote monitor center are limited to ensure that a compromised remote monitor center does not adversely affect one or more vehicles under its control. In an example, the predetermined set of control commands may include procedures for defensive driving and bringing the vehicle to a stop. This would ensure that an adverse high-speed situation involving the vehicle is avoided.


The method 600 includes, at step 608, transmitting the control command with a high priority when the report comprises at least one instance of one immediately actionable status information. In some embodiments, the control command with the high priority flag may override any local control commands that the vehicle has issued or is executing in response to the “Error” or “Fatal” status indicator that was transmitted in the report to the remote monitor center.



FIG. 7 shows an example of a hardware platform 700 that can be used to implement some of the techniques described in the present document. For example, the hardware platform 700 may implement the methods 500 or 600 or may implement the various modules described herein. The hardware platform 700 may include a processor 702 that can execute code to implement a method. The hardware platform 700 may include a memory 704 that may be used to store processor-executable code and/or store data. The hardware platform 700 may further include a communication interface 706. For example, the communication interface 706 may implement communication protocols for one or both of a high-speed channel for regular data transfer or a reliable channel for emergency situations.



FIG. 8 shows a flowchart of another example method 800 that may be implemented in a vehicle, for monitoring autonomous vehicle operation. The method 800 includes, at step 802, collecting status information from one or more systems implemented in the vehicle, and at step 804, classifying the status information by a plurality of status indicators including one or more critical status indicators and one or more uncritical status indicators. Here, the one or more systems may include at least one sensor, at least one hardware system, and at least one software system. For example, the plurality of sensors comprises at least one of Global Positioning System (GPS) sensor, a radar sensor, a LIDAR sensor and a camera. In some embodiments of the disclosed technology, the one or more uncritical status indicators include a status indicator concerning vehicle basic dynamic information and warning messages from the one or more systems implemented in the vehicle. Here, the basic dynamic information includes a location of the vehicle, a fuel level of the vehicle, and an engine temperature of the vehicle. In some embodiments of the disclosed technology, the one or more critical status indicators include a status indicator concerning one or more of a hazardous weather condition, an unknown environment condition, and a lost communication with a monitor center. For example, the one or more critical status indicators include a status indicator concerning a condition that renders an operation of the vehicle unsafe. In this case, the method 800 further includes initiating an emergency parking function implemented in the vehicle, and sending a report indicating that the emergency parking function has been initiated.


The method 800 includes, at step 806, generating a critical status report based on the status information associated with the one or more critical status indicators immediately upon receipt of such status information. The method 800 includes, at step 808, generating an uncritical status report based on the status information associated with the one or more uncritical status indicators with a period that varies with the one or more uncritical status indicators. The method 800 may further include transmitting the uncritical status report over a high-speed channel for regular data transfers and transmitting the critical status report over a reliable channel for emergency situations.



FIG. 9 shows a flowchart of another example method 900 that may be implemented in a vehicle, for monitoring autonomous vehicle operation. The method 900 includes, at step 902, collecting status information from one or more systems implemented in the vehicle. Here, the one or more systems include at least one sensor, at least one hardware system, and at least one software system. For example, the plurality of sensors comprises at least one of Global Positioning System (GPS) sensor, a radar sensor, a LIDAR sensor and a camera. The method 900 includes, at step 904, classifying the status information by a plurality of status indicators including a warning status indicator, an error status indicator, and a fatal status indicator. In some embodiments of the disclosed technology, the fatal status indicator includes a status indicator concerning one or more of a hazardous weather condition, an unknown environment condition, and a lost communication with a monitor center. For example, the fatal status indicator includes a status indicator concerning a condition that renders an operation of the vehicle unsafe. In this case, the method 900 further includes initiating an emergency parking function implemented in the vehicle, and sending a report indicating that the emergency parking function has been initiated.


The method 900 includes, at step 906, generating periodically a status report based on the status information associated with the warning status indicators. The method 900 also includes, at step 908, generating, upon receipt of status information associated with the fatal status indicator, a status report based on the status information associated with the fatal status indicator immediately. The method 900 also includes, at step 910, performing, upon receipt of status information associated with the error status indicator, a recovering process on a corresponding system, and, if the recovering process is unsuccessful, generating a status report based on the status information associated with the error status indicator. The method 900 also includes, at step 912, sending the generated status report to an external monitoring system. In some embodiments of the disclosed technology, the status report associated with the warning status indicator is transmitted over a high-speed channel for regular data transfers and the status report associated with the fatal status indicator is transmitted over a reliable channel for emergency situations.


Implementations of the subject matter and the functional operations described in this patent document can be implemented in various systems, digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Implementations of the subject matter described in this specification can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a tangible and non-transitory computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more of them. The term “data processing unit” or “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.


A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.


The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).


Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. However, a computer need not have such devices. Computer readable media suitable for storing computer program instructions and data include all forms of nonvolatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.


It is intended that the specification, together with the drawings, be considered exemplary only, where exemplary means an example. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. Additionally, the use of “or” is intended to include “and/or”, unless the context clearly indicates otherwise.


While this patent document contains many specifics, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular inventions. Certain features that are described in this patent document in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.


Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Moreover, the separation of various system components in the embodiments described in this patent document should not be understood as requiring such separation in all embodiments.


Only a few implementations and examples are described and other implementations, enhancements and variations can be made based on what is described and illustrated in this patent document.

Claims
  • 1. A method for monitoring and controlling a vehicle, implemented at the vehicle, the method comprising: performing self-tests for each of a plurality of electronic control units of the vehicle;analyzing data from the self-tests to make a determination on a status of the vehicle as one of predetermined statuses, each predetermined status being associated with a corresponding status indicator and a corresponding information to be included in a report;periodically generating, with a first period, the report, wherein the report comprises a first status indicator corresponding to a determined status and results corresponding to the self-tests, the report having a size dependent on the first status indicator;periodically transmitting, with a second period, the report to a remote monitor center, the second period having a duration dependent on the first status indicator;receiving a control command from the remote monitor center, wherein the control command is received in response to the remote monitor center receiving the periodically transmitted report; andimplementing, upon a determination that the control command has a high priority, the control command from the remote monitor center, wherein an implementation of the control command from the remote monitor center overrides an implementation of a local control command, wherein the control command is from a predetermined set of control commands.
  • 2. The method of claim 1, wherein the report further comprises a plurality of status indicators that includes the first status indicator.
  • 3. The method of claim 1, wherein the self-tests are performed for a plurality of sensors, at least one hardware system, and at least one software system.
  • 4. The method of claim 3, wherein the plurality of sensors comprises at least one of a Global Positioning System (GPS) sensor, a radar sensor, a LIDAR sensor, or a camera.
  • 5. The method of claim 1, further comprising: generating environment and driving information based on the analysis.
  • 6. The method of claim 1, wherein the report is periodically transmitted over at least one of a first channel for regular data transfers or a second channel for emergency situations, wherein the first channel employs a protocol selected from the group consisting of Long-Term Evolution (LTE), Wi-Fi, IEEE 802.11, Bluetooth, Dedicated Short-Range Communication (DSRC), Communication Air-interface Long and Medium range (CALM), and a transmission protocol designed for Intelligent Transportation System (ITS) implementations, and wherein the second channel employs at least one of a low-rate forward error correcting code, one or more retransmission, or a protocol that uses frequency diversity, time diversity, space diversity, or code diversity.
  • 7. The method of claim 1, wherein the second period is longer than or equal to the first period.
  • 8. The method of claim 1, further comprising: storing a copy of the report on a local storage device.
  • 9. The method of claim 1, wherein the predetermined set of control commands comprises procedures for defensive driving or bringing the vehicle to a stop.
  • 10. A method for monitoring and controlling a vehicle, implemented at a remote monitor center, the method comprising: periodically receiving, from the vehicle, a report, wherein the report comprises (1) at least one status indicator corresponding to a status of the vehicle that is determined as one of predetermined statuses and (2) information based on self-tests implemented in the vehicle, each predetermined status being associated with a corresponding status indicator and a corresponding information included in the report;determining whether the at least one status indicator included in the report corresponds to at least one immediately actionable status indicator, wherein a presence of the at least one immediately actionable status indicator corresponds to the vehicle issuing a local control command to mitigate a situation;selecting a control command from a predetermined set of control commands; andtransmitting, to the vehicle, the control command with a high priority when the report comprises the at least one immediately actionable status indicator,wherein an implementation of the control command with the high priority at the vehicle overrides an implementation of the local control command at the vehicle,wherein the report further comprises results of self-tests that were performed for each of a plurality of electronic control units in the vehicle,wherein the report has a size dependent on the at least one status indicator, andwherein a rate at which the report is periodically received is dependent on the at least one status indicator.
  • 11. The method of claim 10, wherein the self-tests are performed for a plurality of vehicular sensors, at least one vehicular hardware system, and at least one vehicular software system.
  • 12. The method of claim 10, wherein the rate at which the report is periodically received is variable, and wherein the rate is based on a presence of the at least one immediately actionable status indicator.
  • 13. The method of claim 10, wherein the report is periodically received over at least one of a first channel for regular data transfers or a second channel for emergency situations, and wherein the first channel employs a protocol selected from the group consisting of Long-Term Evolution (LTE), Wi-Fi, IEEE 802.11, Bluetooth, Dedicated Short-Range Communication (DSRC), Communication Air-interface Long and Medium range (CALM), and a transmission protocol designed for Intelligent Transportation System (ITS) implementations, and wherein the second channel employs at least one of a low-rate forward error correcting code, one or more retransmission, or a protocol that uses frequency diversity, time diversity, space diversity, or code diversity.
  • 14. A method for monitoring a vehicle, implemented at the vehicle, the method comprising: collecting, based on performing a plurality of self-tests for each of one or more systems implemented in the vehicle, status information from the one or more systems;classifying the status information by a plurality of status indicators including one or more critical status indicators and one or more uncritical status indicators, each of the plurality of status indicator indicating a corresponding status of the vehicle and associated with corresponding information to be included in a corresponding report;generating a critical status report based on the status information associated with the one or more critical status indicators immediately upon receipt of such status information;generating an uncritical status report based on the status information associated with the one or more uncritical status indicators with a period that varies with the one or more uncritical status indicators, wherein the uncritical status report has a size smaller than that of the critical status report;transmitting, to a remote monitor center, the critical status report and the uncritical status report, wherein the critical status report is transmitted after first predetermined time after the generating of the critical status report and the uncritical status report is transmitted after second predetermined time from the generating of the uncritical status report, the second predetermined time being greater than the first predetermined time; andreceiving a control command from the remote monitor center, wherein the control command is received in response to the remote monitor center receiving the critical status report and the uncritical status report.
  • 15. The method of claim 14, further comprising: wherein the uncritical status report is transmitted, to the remote monitor center, over a first channel for regular data transfers,wherein the first channel employs a protocol selected from the group consisting of Long-Term Evolution (LTE), Wi-Fi, IEEE 802.11, Bluetooth, Dedicated Short-Range Communication (DSRC), Communication Air-interface Long and Medium range (CALM), and a transmission protocol designed for Intelligent Transportation System (ITS) implementations,wherein the critical status report is transmitted, to the remote monitor center, over a second channel for emergency situations, andwherein the second channel employs at least one of a low-rate forward error correcting code, one or more retransmission, or a protocol that uses frequency diversity, time diversity, space diversity, or code diversity.
  • 16. The method of claim 14, wherein the one or more uncritical status indicators include a status indicator concerning vehicle basic dynamic information and warning messages from the one or more systems implemented in the vehicle.
  • 17. The method of claim 16, wherein the basic dynamic information includes a location of the vehicle, a fuel level of the vehicle, and an engine temperature of the vehicle.
  • 18. The method of claim 14, wherein the one or more critical status indicators include a status indicator concerning one or more of a hazardous weather condition, an unknown environment condition, and a lost communication with a monitor center.
  • 19. The method of claim 14, wherein the one or more critical status indicators include a status indicator concerning a condition that renders an operation of the vehicle unsafe.
  • 20. The method of claim 19, further comprising: initiating an emergency parking function implemented in the vehicle; andsending, to a remote monitor center, a report indicating that the emergency parking function has been initiated.
  • 21. The method of claim 14, wherein the one or more systems include at least one sensor, at least one hardware system, and at least one software system.
  • 22. The method of claim 21, wherein the at least one sensor comprises at least one of a Global Positioning System (GPS) sensor, a radar sensor, a LIDAR sensor, or a camera.
  • 23. A method for monitoring and controlling a vehicle, implemented at the vehicle, the method comprising: collecting, based on performing a plurality of self-tests for each of one or more systems implemented in the vehicle, status information from the one or more systems;classifying the status information by a plurality of status indicators including a warning status indicator, an error status indicator, and a fatal status indicator, each of the plurality of status indicator indicating a corresponding status of the vehicle and associated with corresponding information to be included in a corresponding report;generating periodically a first status report based on the status information associated with the warning status indicator;generating, upon receipt of status information associated with the fatal status indicator, a second status report based on the status information associated with the fatal status indicator immediately, wherein the second status report has a size greater than that of the first status report;performing, upon receipt of status information associated with the error status indicator, a recovering process on a corresponding system, and, if the recovering process is unsuccessful, generating a third status report based on the status information associated with the error status indicator, wherein the third status report has a size greater than that of the first status report; andsending the first status report, the second status report, or the third status report to an external monitoring system,wherein the second status report or the third status report is sent after first predetermined time after the generating of the second status report or the third status report and the first status report is sent after second predetermined time after the generating of the first status report, the second predetermined time being greater than the first predetermined time.
  • 24. The method of claim 23, wherein the first status report associated with the warning status indicator is transmitted over a first channel for regular data transfers and the second status report associated with the fatal status indicator is transmitted over a second channel for emergency situations, and wherein the first channel employs a protocol selected from the group consisting of Long-Term Evolution (LTE), Wi-Fi, IEEE 802.11, Bluetooth, Dedicated Short-Range Communication (DSRC), Communication Air-interface Long and Medium range (CALM), and a transmission protocol designed for Intelligent Transportation System (ITS) implementations, and wherein the second channel employs at least one of a low-rate forward error correcting code, one or more retransmission, or a protocol that uses frequency diversity, time diversity, space diversity, or code diversity.
  • 25. The method of claim 23, wherein the fatal status indicator includes a status indicator concerning one or more of a hazardous weather condition, an unknown environment condition, and a lost communication with a monitor center.
  • 26. The method of claim 25, wherein the unknown environment condition comprises a construction zone or a scene of an accident.
  • 27. The method of claim 23, wherein the fatal status indicator includes a status indicator concerning a condition that renders an operation of the vehicle unsafe.
  • 28. The method of claim 27, further comprising: initiating an emergency parking function implemented in the vehicle; andsending a report indicating that the emergency parking function has been initiated.
  • 29. The method of claim 23, wherein the one or more systems include at least one sensor, at least one hardware system, and at least one software system.
  • 30. The method of claim 29, wherein the at least one sensor comprises at least one of a Global Positioning System (GPS) sensor, a radar sensor, a LIDAR sensor, or a camera.
CROSS-REFERENCE TO RELATED APPLICATIONS

This patent document claims the priority and benefits of U.S. Provisional Patent Application No. 62/616,363 filed on Jan. 11, 2018, which is incorporated herein by reference in its entirety.

US Referenced Citations (220)
Number Name Date Kind
6084870 Wooten et al. Jul 2000 A
6263088 Crabtree Jul 2001 B1
6594821 Banning et al. Jul 2003 B1
6777904 Degner Aug 2004 B1
6975923 Spriggs Dec 2005 B2
7103460 Breed Sep 2006 B1
7689559 Canright Mar 2010 B2
7742841 Sakai et al. Jun 2010 B2
7783403 Breed Aug 2010 B2
7844595 Canright Nov 2010 B2
8041111 Wilensky Oct 2011 B1
8064643 Stein Nov 2011 B2
8082101 Stein Dec 2011 B2
8164628 Stein Apr 2012 B2
8175376 Marchesotti May 2012 B2
8271871 Marchesotti Sep 2012 B2
8346480 Trepagnier et al. Jan 2013 B2
8378851 Stein Feb 2013 B2
8392117 Dolgov Mar 2013 B2
8401292 Park Mar 2013 B2
8412449 Trepagnier Apr 2013 B2
8478072 Aisaka Jul 2013 B2
8553088 Stein Oct 2013 B2
8706394 Trepagnier et al. Apr 2014 B2
8718861 Montemerlo et al. May 2014 B1
8788134 Litkouhi Jul 2014 B1
8908041 Stein Dec 2014 B2
8917169 Schofield Dec 2014 B2
8963913 Baek Feb 2015 B2
8965621 Urmson Feb 2015 B1
8981966 Stein Mar 2015 B2
8983708 Choe et al. Mar 2015 B2
8993951 Schofield Mar 2015 B2
9002632 Emigh Apr 2015 B1
9008369 Schofield Apr 2015 B2
9025880 Perazzi May 2015 B2
9042648 Wang May 2015 B2
9081385 Ferguson et al. Jul 2015 B1
9088744 Grauer et al. Jul 2015 B2
9111444 Kaganovich Aug 2015 B2
9117133 Barnes Aug 2015 B2
9118816 Stein Aug 2015 B2
9120485 Dolgov Sep 2015 B1
9122954 Srebnik Sep 2015 B2
9134402 Sebastian Sep 2015 B2
9145116 Clarke Sep 2015 B2
9147255 Zhang Sep 2015 B1
9156473 Clarke Oct 2015 B2
9176006 Stein Nov 2015 B2
9179072 Stein Nov 2015 B2
9183447 Gdalyahu Nov 2015 B1
9185360 Stein Nov 2015 B2
9191634 Schofield Nov 2015 B2
9214084 Grauer et al. Dec 2015 B2
9219873 Grauer et al. Dec 2015 B2
9233659 Rosenbaum Jan 2016 B2
9233688 Clarke Jan 2016 B2
9248832 Huberman Feb 2016 B2
9248835 Tanzmeister Feb 2016 B2
9251708 Rosenbaum Feb 2016 B2
9277132 Berberian Mar 2016 B2
9280711 Stein Mar 2016 B2
9282144 Tebay et al. Mar 2016 B2
9286522 Stein Mar 2016 B2
9297641 Stein Mar 2016 B2
9299004 Lin Mar 2016 B2
9315192 Zhu Apr 2016 B1
9317033 Ibanez-guzman et al. Apr 2016 B2
9317776 Honda Apr 2016 B1
9330334 Lin May 2016 B2
9342074 Dolgov May 2016 B2
9347779 Lynch May 2016 B1
9355635 Gao May 2016 B2
9365214 Ben Shalom Jun 2016 B2
9399397 Mizutani Jul 2016 B2
9418549 Kang et al. Aug 2016 B2
9428192 Schofield Aug 2016 B2
9436880 Bos Sep 2016 B2
9438878 Niebla Sep 2016 B2
9443163 Springer Sep 2016 B2
9446765 Ben Shalom Sep 2016 B2
9459515 Stein Oct 2016 B2
9466006 Duan Oct 2016 B2
9476970 Fairfield Oct 2016 B1
9483839 Kwon Nov 2016 B1
9490064 Hirosawa Nov 2016 B2
9494935 Okumura et al. Nov 2016 B2
9507346 Levinson et al. Nov 2016 B1
9513634 Pack et al. Dec 2016 B2
9531966 Stein Dec 2016 B2
9535423 Debreczeni Jan 2017 B1
9538113 Grauer et al. Jan 2017 B2
9547985 Tuukkanen Jan 2017 B2
9549158 Grauer et al. Jan 2017 B2
9555803 Pawlicki Jan 2017 B2
9568915 Berntorp Feb 2017 B1
9587952 Slusar Mar 2017 B1
9599712 Van Der Tempel et al. Mar 2017 B2
9600889 Boisson et al. Mar 2017 B2
9602807 Crane et al. Mar 2017 B2
9612123 Levinson et al. Apr 2017 B1
9620010 Grauer et al. Apr 2017 B2
9625569 Lange Apr 2017 B2
9628565 Stenneth et al. Apr 2017 B2
9649999 Amireddy et al. May 2017 B1
9652860 Maali May 2017 B1
9669827 Ferguson et al. Jun 2017 B1
9672446 Vallesi-Gonzalez Jun 2017 B1
9690290 Prokhorov Jun 2017 B2
9701023 Zhang et al. Jul 2017 B2
9712754 Grauer et al. Jul 2017 B2
9720418 Stenneth Aug 2017 B2
9723097 Harris Aug 2017 B2
9723099 Chen Aug 2017 B2
9723233 Grauer et al. Aug 2017 B2
9726754 Massanell et al. Aug 2017 B2
9729860 Cohen et al. Aug 2017 B2
9738280 Rayes Aug 2017 B2
9739609 Lewis Aug 2017 B1
9746550 Nath Aug 2017 B2
9753128 Schweizer et al. Sep 2017 B2
9753141 Grauer et al. Sep 2017 B2
9754490 Kentley et al. Sep 2017 B2
9760837 Nowozin et al. Sep 2017 B1
9766625 Boroditsky et al. Sep 2017 B2
9769456 You et al. Sep 2017 B2
9773155 Shotton et al. Sep 2017 B2
9779276 Todeschini et al. Oct 2017 B2
9785149 Wang et al. Oct 2017 B2
9805294 Liu et al. Oct 2017 B2
9810785 Grauer et al. Nov 2017 B2
9823339 Cohen Nov 2017 B2
9953236 Huang Apr 2018 B1
10147193 Huang Dec 2018 B2
10223806 Yi et al. Mar 2019 B1
10223807 Yi et al. Mar 2019 B1
10410055 Wang et al. Sep 2019 B2
20030114980 Klausner et al. Jun 2003 A1
20030174773 Comaniciu Sep 2003 A1
20040264763 Mas et al. Dec 2004 A1
20070183661 El-Maleh Aug 2007 A1
20070183662 Wang Aug 2007 A1
20070230792 Shashua Oct 2007 A1
20070286526 Abousleman Dec 2007 A1
20080249667 Horvitz Oct 2008 A1
20090040054 Wang Feb 2009 A1
20090087029 Coleman Apr 2009 A1
20100049397 Lin Feb 2010 A1
20100111417 Ward May 2010 A1
20100226564 Marchesotti Sep 2010 A1
20100281361 Marchesotti Nov 2010 A1
20110142283 Huang Jun 2011 A1
20110206282 Aisaka Aug 2011 A1
20110247031 Jacoby Oct 2011 A1
20120041636 Johnson Feb 2012 A1
20120105639 Stein May 2012 A1
20120140076 Rosenbaum Jun 2012 A1
20120274629 Baek Nov 2012 A1
20120314070 Zhang et al. Dec 2012 A1
20130051613 Bobbitt et al. Feb 2013 A1
20130083959 Owechko Apr 2013 A1
20130182134 Grundmann et al. Jul 2013 A1
20130204465 Phillips et al. Aug 2013 A1
20130266187 Bulan Oct 2013 A1
20130329052 Chew Dec 2013 A1
20140072170 Zhang Mar 2014 A1
20140104051 Breed Apr 2014 A1
20140142799 Ferguson et al. May 2014 A1
20140143839 Ricci May 2014 A1
20140145516 Hirosawa May 2014 A1
20140198184 Stein Jul 2014 A1
20140321704 Partis Oct 2014 A1
20140334668 Saund Nov 2014 A1
20150062304 Stein Mar 2015 A1
20150120083 Gurovich Apr 2015 A1
20150269438 Samarsekera et al. Sep 2015 A1
20150310370 Burry Oct 2015 A1
20150353082 Lee et al. Dec 2015 A1
20150367770 Newton-Dunn Dec 2015 A1
20160008988 Kennedy Jan 2016 A1
20160026787 Nairn et al. Jan 2016 A1
20160037064 Stein Feb 2016 A1
20160094774 Li Mar 2016 A1
20160117871 McClellan et al. Apr 2016 A1
20160118080 Chen Apr 2016 A1
20160129907 Kim May 2016 A1
20160165157 Stein Jun 2016 A1
20160210528 Duan Jul 2016 A1
20160275766 Venetianer et al. Sep 2016 A1
20160321381 English Nov 2016 A1
20160334230 Ross et al. Nov 2016 A1
20160342837 Hong et al. Nov 2016 A1
20160347322 Clarke et al. Dec 2016 A1
20160375907 Erban Dec 2016 A1
20170053169 Cuban et al. Feb 2017 A1
20170061632 Linder et al. Mar 2017 A1
20170124476 Levinson et al. May 2017 A1
20170134631 Zhao et al. May 2017 A1
20170177951 Yang et al. Jun 2017 A1
20170301104 Qian Oct 2017 A1
20170305423 Green Oct 2017 A1
20170318407 Meister Nov 2017 A1
20170365105 Rao Dec 2017 A1
20180151063 Pun May 2018 A1
20180158197 Dasgupta Jun 2018 A1
20180260956 Huang Sep 2018 A1
20180283892 Behrendt Oct 2018 A1
20180373980 Huval Dec 2018 A1
20190025853 Julian Jan 2019 A1
20190065863 Luo et al. Feb 2019 A1
20190066329 Yi et al. Feb 2019 A1
20190066330 Yi et al. Feb 2019 A1
20190066344 Yi et al. Feb 2019 A1
20190108384 Wang et al. Apr 2019 A1
20190132391 Thomas May 2019 A1
20190132392 Liu May 2019 A1
20190210564 Han Jul 2019 A1
20190210613 Sun Jul 2019 A1
20190236950 Li Aug 2019 A1
20190266420 Ge Aug 2019 A1
Foreign Referenced Citations (40)
Number Date Country
101770211 Jul 2010 CN
101918932 Dec 2010 CN
104954420 Sep 2015 CN
106340197 Jan 2017 CN
106781591 May 2017 CN
107505944 Dec 2017 CN
108010360 May 2018 CN
2608513 Sep 1977 DE
890470 Jan 1999 EP
1754179 Feb 2007 EP
2448251 May 2012 EP
2463843 Jun 2012 EP
2761249 Aug 2014 EP
2946336 Nov 2015 EP
2993654 Mar 2016 EP
3081419 Oct 2016 EP
100802511 Feb 2008 KR
1991009375 Jun 1991 WO
2005098739 Oct 2005 WO
2005098751 Oct 2005 WO
2005098782 Oct 2005 WO
2010109419 Sep 2010 WO
2013045612 Apr 2013 WO
2014111814 Jul 2014 WO
2014166245 Oct 2014 WO
2014201324 Dec 2014 WO
2015083009 Jun 2015 WO
2015103159 Jul 2015 WO
2015125022 Aug 2015 WO
2015186002 Dec 2015 WO
2016090282 Jun 2016 WO
2016135736 Sep 2016 WO
2017079349 May 2017 WO
2017079460 May 2017 WO
2017013875 May 2018 WO
2019040800 Feb 2019 WO
2019084491 May 2019 WO
2019084494 May 2019 WO
2019140277 Jul 2019 WO
2019168986 Sep 2019 WO
Non-Patent Literature Citations (57)
Entry
M.P.Singh, Prabhat Kumar, “An Efficient Forward Error Correction Scheme for Wireless Sensor Network”, 2011, Elsevier, p. 1 ( Year: 2011).
Carle, Patrick J.F. et al. “Global Rover Localization by Matching Lidar and Orbital 3D Maps.” IEEE, Anchorage Convention District, pp. 1-6, May 3-8, 2010. (Anchorage Alaska, US).
Caselitz, T. et al., “Monocular camera localization in 3D LiDAR maps,” European Conference on Computer Vision (2014) Computer Vision—ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol. 8690. Springer, Cham.
Mur-Artal, R. et al., “ORB-SLAM: A Versatile and Accurate Monocular SLAM System,” IEEE Transaction on Robotics, Oct. 2015, pp. 1147-1163, vol. 31, No. 5, Spain.
Sattler, T. et al., “Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?” CVPR, IEEE, 2017, pp. 1-10.
Engel, J. et la. “LSD-SLAM: Large Scare Direct Monocular SLAM,” pp. 1-16, Munich.
Levinson, Jesse et al., Experimental Robotics, Unsupervised Calibration for Multi-Beam Lasers, pp. 179-194, 12th Ed., Oussama Khatib, Vijay Kumar, Gaurav Sukhatme (Eds.) Springer-Verlag Berlin Heidelberg 2014.
International Application No. PCT/US2019/013322, International Search Report and Written Opinion dated Apr. 2, 2019.
International Application No. PCT/US19/12934, International Search Report and Written Opinion dated Apr. 29, 2019.
International Application No. PCT/US18/53795, International Search Report and Written Opinion dated Dec. 31, 2018.
International Application No. PCT/US18/57484, International Search Report and Written Opinion dated Jan. 7, 2019.
International Application No. PCT/US2018/057851, International Search Report and Written Opinion dated Feb. 1, 2019.
International Application No. PCT/US2019/019839, International Search Report and Written Opinion dated May 23, 2019.
International Application No. PCT/US19/25995, International Search Report and Written Opinion dated Jul. 9, 2019.
Geiger, Andreas et al., “Automatic Camera and Range Sensor Calibration using a single Shot”, Robotics and Automation (ICRA), pp. 1-8, 2012 IEEE International Conference.
Zhang, Z. et al. A Flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence (vol. 22, Issue: 11, Nov. 2000).
International Application No. PCT/US2018/047830, International Search Report and Written Opinion dated Apr. 27, 2017.
Bar-Hillel, Aharon et al. “Recent progress in road and lane detection: a survey.” Machine Vision and Applications 25 (2011): 727-745.
Schindler, Andreas et al. “Generation of high precision digital maps using circular arc splines,” 2012 IEEE Intelligent Vehicles Symposium, Alcala de Henares, 2012, pp. 246-251. doi: 10.1109/IVS.2012.6232124.
International Application No. PCT/US2018/047608, International Search Report and Written Opinion dated Dec. 28, 2018.
Hou, Xiaodi and Zhang, Liqing, “Saliency Detection: A Spectral Residual Approach”, Computer Vision and Pattern Recognition, CVPR'07—IEEE Conference, pp. 1-8, 2007.
Hou, Xiaodi and Harel, Jonathan and Koch, Christof, “Image Signature: Highlighting Sparse Salient Regions”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, No. 1, pp. 194-201, 2012.
Hou, Xiaodi and Zhang, Liqing, “Dynamic Visual Attention: Searching For Coding Length Increments”, Advances in Neural Information Processing Systems, vol. 21, pp. 681-688, 2008.
Li, Yanghao and Wang, Naiyan and Shi, Jianping and Liu, Jiaying and Hou, Xiaodi, “Revisiting Batch Normalization for Practical Domain Adaptation”, arXiv preprint arXiv: 1603.04779, 2016.
Li, Yanghao and Wang, Naiyan and Liu, Jiaying and Hou, Xiaodi, “Demystifying Neural Style Transfer”, arXiv preprint arXiv: 1701.01036, 2017.
Hou, Xiaodi and Zhang, Liqing, “A Time-Dependent Model of Information Capacity of Visual Attention”, International Conference on Neural Information Processing, pp. 127-136, Springer Berlin Heidelberg, 2006.
Wang, Panqu and Chen, Pengfei and Yuan, Ye and Liu, Ding and Huang, Zehua and Hou, Xiaodi and Cottrell, Garrison, “Understanding Convolution for Semantic Segmentation”, arXiv preprint arXiv: 1702.08502, 2017.
Li, Yanghao and Wang, Naiyan and Liu, Jiaying and Hou, Xiaodi, “Factorized Bilinear Models for Image Recognition”, arXiv preprint arXiv: 1611.05709, 2016.
Hou, Xiaodi, “Computational Modeling and Psychophysics in Low and Mid-Level Vision”, California Institute of Technology, 2014.
Spinello, Luciano, Triebel, Rudolph, Siegwart, Roland, “Multiclass Multimodal Detection and Tracking in Urban Environments”, Sage Journals, vol. 29 Issue 12, pp. 1498-1515 Article first published online: Oct. 7, 2010; Issue published: Oct. 1, 2010.
Matthew Barth, Carrie Malcolm, Theodore Younglove, and Nicole Hill, “Recent Validation Efforts for a Comprehensive Modal Emissions Model”, Transportation Research Record 1750, Paper No. 01-0326, College of Engineering, Center for Environmental Research and Technology, University of California, Riverside, CA 92521, date unknown.
Kyoungho Ahn, Hesham Rakha, “The Effects of Route Choice Decisions on Vehicle Energy Consumption and Emissions”, Virginia Tech Transportation Institute, Blacksburg, VA 24061, date unknown.
Ramos, Sebastian, Gehrig, Stefan, Pinggera, Peter, Franke, Uwe, Rother, Carsten, “Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling”, arXiv: 1612.06573v1 [cs.CV] Dec. 20, 2016.
Schroff, Florian, Dmitry Kalenichenko, James Philbin, (Google), “FaceNet: A Unified Embedding for Face Recognition and Clustering”, CVPR 2015.
Dai, Jifeng, Kaiming He, Jian Sun, (Microsoft Research), “Instance-aware Semantic Segmentation via Multi-task Network Cascades”, CVPR 2016.
Huval, Brody, Tao Wang, Sameep Tandon, Jeff Kiske, Will Song, Joel Pazhayampallil, Mykhaylo Andriluka, Pranav Rajpurkar, Toki Migimatsu, Royce Cheng-Yue, Fernando Mujica, Adam Coates, Andrew Y. Ng, “An Empirical Evaluation of Deep Learning on Highway Driving”, arXiv:1504.01716v3 [cs.RO] Apr. 17, 2015.
Tian Li, “Proposal Free Instance Segmentation Based on Instance-aware Metric”, Department of Computer Science, Cranberry-Lemon University, Pittsburgh, PA., date unknown.
Mohammad Norouzi, David J. Fleet, Ruslan Salakhutdinov, “Hamming Distance Metric Learning”, Departments of Computer Science and Statistics, University of Toronto, date unknown.
Jain, Suyong Dutt, Grauman, Kristen, “Active Image Segmentation Propagation”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Jun. 2016.
MacAodha, Oisin, Campbell, Neill D.F., Kautz, Jan, Brostow, Gabriel J., “Hierarchical Subquery Evaluation for Active Learning on a Graph”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
Kendall, Alex, Gal, Yarin, “What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision”, arXiv:1703.04977v1 [cs.CV] Mar. 15, 2017.
Wei, Junqing, John M. Dolan, Bakhtiar Litkhouhi, “A Prediction- and Cost Function-Based Algorithm for Robust Autonomous Freeway Driving”, 2010 IEEE Intelligent Vehicles Symposium, University of California, San Diego, CA, USA, Jun. 21-24, 2010.
Peter Welinder, Steve Branson, Serge Belongie, Pietro Perona, “The Multidimensional Wisdom of Crowds”; http://www.vision.caltech.edu/visipedia/papers/WelinderEtaINIPS10.pdf, 2010.
Kai Yu, Yang Zhou, Da Li, Zhang Zhang, Kaiqi Huang, “Large-scale Distributed Video Parsing and Evaluation Platform”, Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, China, arXiv: 1611.09580v1 [cs.CV] Nov. 29, 2016.
P. Guarneri, G. Rocca and M. Gobbi, “A Neural-Network-Based Model for the Dynamic Simulation of the Tire/Suspension System While Traversing Road Irregularities,” in IEEE Transactions on Neural Networks, vol. 19, No. 9, pp. 1549-1563, Sep. 2008.
C. Yang, Z. Li, R. Cui and B. Xu, “Neural Network-Based Motion Control of an Underactuated Wheeled Inverted Pendulum Model,” in IEEE Transactions on Neural Networks and Learning Systems, vol. 25, No. 11, pp. 2004-2016, Nov. 2014.
Stephan R. Richter, Vibhav Vineet, Stefan Roth, Vladlen Koltun, “Playing for Data: Ground Truth from Computer Games”, Intel Labs, European Conference on Computer Vision (ECCV), Amsterdam, the Netherlands, 2016.
Thanos Athanasiadis, Phivos Mylonas, Yannis Avrithis, and Stefanos Kollias, “Semantic Image Segmentation and Object Labeling”, IEEE Transactions on Circuits and Systems for Video Technology, vol. 17, No. 3, Mar. 2007.
Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele, “The Cityscapes Dataset for Semantic Urban Scene Understanding”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, 2016.
Adhiraj Somani, Nan Ye, David Hsu, and Wee Sun Lee, “DESPOT: Online POMDP Planning with Regularization”, Department of Computer Science, National University of Singapore, date unknown.
Adam Paszke, Abhishek Chaurasia, Sangpil Kim, and Eugenio Culurciello. Enet: A deep neural network architecture for real-time semantic segmentation. CoRR, abs/1606.02147, 2016.
Szeliski, Richard, “Computer Vision: Algorithms and Applications” http://szeliski.org/Book/, 2010.
Luo, Yi et al. U.S. Appl. No. 15/684,389 Notice of Allowance dated Oct. 9, 2019.
International Application No. PCT/US2019/013322, International Preliminary Report on Patentability dated Jul. 14, 2020, 10 pages.
No Author. International Standard, ISO 26262-1, Second Edition, Dec. 2018: Road vehicles—Functional safety—Part 1: Vocabulary. Ref. No. ISO26262-1:2018 (E). pp. 1-42.
European Application No. 19738646.9/3738106 Extended European Search Report dated Aug. 9, 2021, pp. 1-8.
Chinese Application No. 201980008172.4 First Office Action dated Dec. 31, 2021, pp. 1-28.
Related Publications (1)
Number Date Country
20190210613 A1 Jul 2019 US
Provisional Applications (1)
Number Date Country
62616363 Jan 2018 US