Remote safe driving methods and systems

Abstract

Disclosed are devices, systems and methods for remote safe driving. One exemplary method includes detecting an emergency situation, and in response to the detecting the emergency situation, switching operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components, and periodically transmitting a location of the vehicle to a remote monitoring center. Another exemplary method includes selecting at least one of a set of vehicular driving actions, and transmitting, over a secure connection, the at least one of the set of vehicular driving actions to the vehicle, wherein the set of vehicular driving actions is generated based on a classification of driver behavior.

Description

TECHNICAL FIELD

This document relates to remote 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 control the vehicle to navigate towards a destination. Autonomous vehicle navigation can have important applications in transportation of people, goods and services.

SUMMARY

Disclosed are devices, systems and methods for remote safe driving, which include self-checking systems, emergency handling systems, and remote control systems. In an example, this may be achieved by a remote monitor center controlling some part of the monitoring and emergency handling services on the vehicle, and providing commands to ensure the safety of the vehicle and its passengers in the case of an emergency.

In one aspect, the disclosed technology can be used to provide a method for remote safe driving of a vehicle. This method may be implemented at the vehicle. The method includes detecting an emergency situation, and in response to the detecting the emergency situation, switching operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components, and periodically transmitting a location of the vehicle to a remote monitoring center.

In another aspect, the disclosed technology can be used to provide another method for remote safe driving of a vehicle. This method may be implemented at a remote data center that is in communication with the vehicle. The method includes selecting at least one of a set of vehicular driving actions, and transmitting, over a secure connection, the at least one of the set of vehicular driving actions to the vehicle, wherein the set of vehicular driving actions is generated based on a classification of a plurality of driver behavior.

In yet another example aspect, a computing apparatus that includes a processor for implementing one of the methods recited herein is disclosed.

In yet another example aspect, a computer program product comprising a computer-readable program medium having code stored thereon is disclosed. The code, when executed by a processor, causes the processor to implement a method as described.

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

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 shows a block diagram of an exemplary system for remote safe driving.

FIG. 2 shows an example state diagram implementing a procedure for remote safe driving.

FIG. 3 shows an example state diagram implementing another procedure for remote safe driving.

FIG. 4 shows a block diagram of example subcomponents of a vehicle that can support remote safe driving.

FIG. 5 shows a flowchart of an example method for remote safe driving.

FIG. 6 shows a flowchart for another example method for remote safe driving.

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

DETAILED DESCRIPTION

Autonomous vehicles use a variety of techniques to detect their surroundings, such as radar, laser light, GPS, odometry and computer vision. Control systems may interpret sensory information to identify appropriate navigation paths, as well as planned and unplanned obstacles and relevant signage along the route. The remote driving of vehicles may further rely on monitoring and classification systems that are capable of analyzing sensory data to distinguish between a variety of factors, e.g. different weather conditions, different cars on the road, and different obstacles.

Another integral feature of autonomous driving should be the safety of the vehicle and its passengers, as well as the safety of neighboring people and property. Thus, autonomous vehicles should be equipped with emergency handling systems to ensure the safe driving of the vehicles, especially when performed remotely. The response to an emergency situation should be rapid and precise, since safety is paramount. One of the main goals to enable widespread use of autonomous vehicles is to achieve and exceed the reliability of human driving behavior, and remote safe driving is integral to this goal. The techniques described in the present document can be incorporated in embodiments of a fully-autonomous vehicle, a semi-autonomous vehicle and/or a control center that controls operation of the autonomous vehicle. In particular, using the disclosed techniques, upon detection of an abnormality, an autonomous vehicle may safely stop further driving and ask for assistance. Similarly, in some embodiments, when a control center becomes aware of an autonomous vehicle's distress condition, the control center may provide the vehicle with further instructions to safely cease driving and wait for further assistance. These, and other, features are further described herein.

FIG. 1 shows a block diagram of an exemplary system for remote safe driving. As shown therein, the system for safe driving includes a truck 110 and a remote center (or remote data center, or remote monitor center) 130, which can communicate with each other through a communication protocol 120. In some embodiments, the truck 110 includes an emergency handling system 112, a monitoring system 114, and an electronic control unit (ECU) system 116.

In some embodiments, the emergency handling system defines several emergency status conditions, and corresponding autonomous vehicle actions for each status condition. For example, the emergency status conditions may include:

(a) a “truck/vehicle abnormal” status, which may include a CAN (Controller Area Network) bus response signal indicating any abnormality,

(b) a “sensor abnormal” status, which may indicate that abnormalities with any of the sensors including the camera, radar, GPS, and inertial measurement unit (IMU) have been detected, e.g., a lack of a signal from one or more of these sensors,

(c) an “ECU abnormal” status, which is a self-detection status check for the hardware components of the vehicle,

(d) a “system abnormal” status, which may indicate a problem with the middleware, e.g., a middleware system deadlock that lasts for more than 3 seconds,

(e) a “network abnormal” status, which may indicate a problem with the network, e.g., the network is disconnected,

(f) a “car control fail” status, which indicates a failure in at least one self-detection test of the control module, e.g., no output or an abnormal output,

(g) a “planning fail” status, which indicates a failure in at least one self-detection test of the planning module, e.g., no output or an abnormal output,

(h) a “perception fail” status, which indicates a failure in at least one self-detection test of the perception module, e.g., no output or an abnormal output, and

(i) a “localization fail” status, which indicates a failure in at least one self-detection test of the localization module, e.g., no output or an abnormal output.

In some embodiments, the vehicle may stop in an emergency lane when the “truck (or vehicle) abnormal” status indicator is detected, and may stop in the lane it is currently driving in when any of the other status indicator is detected.

In some embodiments, one or more of the enumerated emergency status conditions may be transmitted to the remote data center over a secure connection as soon as they are detected as part of an emergency signal. In other embodiments, the emergency status conditions may be transmitted as part of periodically transmitted monitoring signals. In yet other embodiments, a semi-persistent approach may be adopted, where periodic monitoring updates are transmitted from the vehicle to the remote data center, but an emergency signal transmission takes precedence and is transmitted as soon as it is generated.

In some embodiments, the remote data center may receive the necessary emergency signals from the vehicle over a dedicated and secure emergency channel. In one example, the status of the vehicle may be derived from the emergency signals received. In another example, the remote data center may receive the status of the vehicle from the vehicle itself, as part of the communication that contained the necessary emergency signals, or in a separate communication. In yet another example, the status condition (which may be a non-emergency or emergency status condition) may be accompanied by a corresponding report providing additional information related to that status condition.

In some embodiments, the emergency signals include a location and a vehicle status message. In an example, the location may be specified in absolute or relative coordinates. The vehicle status message may include a status indicator and specific information elements. In some embodiments, 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

In some embodiments, each of the enumerated status conditions may take on a value shown in the example table above, and may be transmitted to the remote data center, along with any corresponding information elements that may be required. In some embodiments, the operation of the vehicle, the generation of an emergency status, and the response required to resolve the emergency situation may be implemented as shown in the state diagram in FIG. 2.

FIG. 2 shows an example state diagram 200 implementing a procedure for remote safe driving. The state diagram 200 is typically, and ideally, operating in a “running” state 210, where the vehicle is operating as intended, with no failures in self-detection tests and no emergency status indications. In addition to operating in the “running” status, the vehicle may periodically (or semi-persistently, or aperiodically) perform the process 220. In an example, “checking process” includes running self-detection tests.

Upon detecting an emergency condition, the exemplary procedure for remote safe driving may implement one of at least two policy strategies. The first policy 230 dictates that the vehicle should search for the nearest emergency lane, and safely come to a stop in the emergency lane. The second policy 250 dictates that the vehicle stop in the lane it is currently operating in (referred to as the “self-lane”). For example, and under this policy, the vehicle may determine that an immediate stop may be required, and that the driving or emergency conditions may preclude taking the time to search for and move to an emergency lane.

When the vehicle has stopped in the emergency lane 230, the vehicle may take appropriate measures to address the emergency situation, and then restart from the emergency lane 240 (and referred to a Process I). Similarly, when the vehicle has stopped in the self-lane 250, it may restart from the self-lane 260 (referred to as Process II) after appropriate measures have been taken. Restarting operations from either the emergency lane or the self-lane returns the state of the vehicle to the “running” state 210, as shown in FIG. 2.

FIG. 3 shows an example state diagram 300 implementing the “Process I” and “Process II” procedures (as discussed in the context of FIG. 2) for remote safe driving. As shown therein, the state diagram 300 includes remote data center (or simply, the “data center”) 310 implementing a sync process 320 and a self-checking procedure for each subsystem in the vehicle to ensure that the vehicle may be may be restarted. For example, the sync process 320 ensures that the subsystem self-checks are implemented in a coordinated manner. In some embodiments, the vehicle self-checking and self-start process 335 includes running the self-check and reporting the results back to the data center, which remotely starts the vehicle.

In some embodiments, the hardware self-checking process 345 may include self-checking one or more of the ECU module (e.g., CPU, GPU, memory, mainboard), the sensor module (e.g., camera, radar, IMU, GPS sensor), and the power module (e.g., converter system), and reporting the results of each subsystem self-check to the data center 310.

In some embodiments, the software self-checking process 355 may include self-checking the Octopus platform, which is an open-source platform for graph-based program analysis. The software self-checking process may further include self-checking the algorithms modules (e.g., maps and localization, perception, control, motion planning).

In some embodiments, the surrounding checking process 365 may ensure other vehicles, objects and/or persons in the vicinity of the vehicle are accounted for prior to restarting.

In some embodiments, the autonomous driving process 375 includes bringing the vehicle into a semi- or fully-autonomous driving mode.

FIG. 4 shows a block diagram of example subcomponents of a vehicle that can support remote safe driving. In some embodiments, the vehicle may include a sensor system 420, a middleware system 440, and an algorithm module 460. In some embodiments, one or more of these subcomponents may be part of an ECU system (e.g. the ECU system 116 shown in FIG. 1). In other embodiments, the ECU system may control one or more of these systems and modules.

In an example, the sensor system 420 may include a CAN bus sensor, a camera, radar capabilities, a GPS unit and/or an IMU, and Lidar capabilities. In another example, the middleware system 440 may include the system module, and the algorithm module 460 may include a localization module, a perception module, a control module, and a planning module.

In some embodiments, a monitoring system (e.g. the monitoring system 114 shown in FIG. 1) may periodically (or continuously, or triggered aperiodically) monitor the status of each component of the sensor system 420, middleware system 440 and algorithm module 460. For example, the monitoring system receives a location message and a vehicle status message. In some embodiments, the location message may use GPS84 coordinates.

In some embodiments, the vehicle status message may be defined as including the following subfields, one or more of which may be transmitted at each time:

(1) vehicle running status as a 1-bit field with a “0” indicating that the vehicle is running and a “1” indicating that the vehicle has stopped;

(2) vehicle self-status using the standard or extended frame formats (as described in CAN 2.0 A and CAN 2.0 B);

(3) hardware status defined as:

		Length
	Field name	(bits)	Purpose
	Mainboard status	6	Indicates status of mainboard
	CPU status	6	Indicates status of CPU
	Memory status	6	Indicates status of memory
	GPU status	10	Indicates status of GPU
	Power status	6	Indicates status of power supply

(4) system status defined as:

	Length
Field name	(bits)	Purpose
Middleware module status	10	Indicates status of middleware
Data status	4	Indicates status of data-based
		modules and data integrity
Algorithm module status	20	Indicates status of algorithm
		modules

(5) algorithm status defined as:

	Length
Field name	(bits)	Purpose
Motion planning status	8	Indicates status of motion planning
		module
Control status	8	Indicates status of control module
Prediction status	8	Indicates status of prediction module
Localization/Pose status	8	Indicates status of localization and
		pose modules

The message formats shown above are exemplary, and other formats with different lengths for the bitfields, as well as additional bitfields and status indicators, are envisioned as part of the disclosed technology.

Embodiments of the disclosed technology may be advantageously implemented in a modular fashion to support both fully-autonomous as well as semi-autonomous vehicles. For example, a semi-autonomous vehicle that is actively and safely being controlled by a driver may not need to implement autonomous driving (e.g., the autonomous driving process 375 in FIG. 3), self-checks for the control module (e.g. the control module that is part of the algorithm module 460 in FIG. 4), or use the control status bitfield as described above. The remote center may configure an implementation of the safe driving system described in this document to suit the needs of the driver and/or passengers of the fully- or semi-autonomous vehicle.

FIG. 5 shows a flowchart of an example method 500, which may be implemented at the vehicle, for remote safe driving. The method 500 includes, at step 510, detecting an emergency situation. In some embodiments, the emergency situation may include an abnormal sensor operation, an abnormal electronic control unit (ECU) operation, an abnormal network operation, a communication failure, a failure of a planning module, a failure of a car control module, a failure of a localization module, or a failure of a perception module. In other embodiments, the emergency situation may include a failure or faulty operation of one or more of the subcomponents shown in the context of FIG. 4. In yet other embodiments, the emergency situation may be an event external to the vehicle (e.g. environmental or traffic-related).

The method includes, at step 520, switching, in response to the detecting, operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components. In some embodiments, the subset of vehicular components include non-essential sensors and subsystems that are non-emergency subsystems. Since recovering from the emergency situation is integral to the safety of the vehicle and its passengers, and to people and property in the vicinity of the vehicle, subsystems that are not required to resolve the emergency situation are turned off in order to ensure enough power is available for critical subsystems. In an example, the non-emergency subsystems may include the vehicle entertainment subsystem, and map and navigation support for retail establishments and points of interest.

In some embodiments, subsystems may correspond to the sensor system, the middleware system and/or the algorithm module (as shown in FIG. 4). In other embodiments, a subsystem may correspond to the individual sensors (e.g. radar, camera, LiDAR, etc.) or the individual modules (e.g. localization module, perception module, etc.).

As discussed in the context of the state diagram shown in FIG. 2, a response to the emergency situation may include stopping the vehicle in either the self-lane or in an emergency lane. In some embodiments, and once the vehicle has been safely guided to a stop, another set of subcomponents that are critical to autonomous driving are shut down and restarted, and a status check is performed on at least one of the other set of components. This ensures that the vehicle is in a condition to either continue on its route or be diverted to a service station for further inspection. In other embodiments, if it is determined that further operation of the vehicle may not be safe, and other failsafe or precautionary procedures (e.g. calling for a tow truck) may be triggered, either by the emergency handling system or the remote data center.

In some embodiments, performing a status check an restarting (or starting) certain components may be based on the changing environment. For an example, if it starts to get dark while the vehicle remains on the side of the road, a status check may be performed on the hazard lights, which may then be turned on to ensure the visibility of the vehicle. For another example, if rush hour starts and parking restrictions are imposed in the right-most lane in which the vehicle is parked, a status check may be performed on the autonomous driving system (ADS), and the vehicle carefully driven to an alternate safe spot.

The method includes, at step 530, periodically transmitting, in response to the detecting, a location of the vehicle to a remote monitoring center. In some embodiments, as soon as any emergency status condition is detected, the vehicle may periodically transmit its GPS coordinates (or location relative to known mile markers, other landmarks, or Wi-Fi transmitters) to the remote data center. In an example, the period of the transmission of the vehicle location may be much shorter than a period typically used for transmitting monitoring status updates.

In some embodiments, cargo being hauled by the vehicle may be critically important to a customer and is deemed an essential component when an emergency is detected. For example, when the vehicle is transitioning to a low-power operating mode in which non-essential and non-emergency components are shut down, power may be routed to the cargo container to ensure that it is maintained at a predetermined thermal profile. The periodic transmission of the location of the vehicle will advantageously enable the remote center (e.g., 130 in FIG. 1) to determine how quickly the vehicle can return to operational status (e.g., by tracking a vehicle sent to assist the vehicle having the emergency), and it can explicitly ensure that the thermal profile of the cargo container is maintained per customer requests.

FIG. 6 shows a flowchart for an example method 600, which may be implemented at a remote data center, for remote safe driving. The method 600 includes, at step 610, selecting at least one of a set of vehicular driving actions. In some embodiments, the vehicular driving actions may include parking the vehicle, moving from a predetermined origin to a predetermined destination, and moving to a refueling location. In some embodiments, the enumeration of the vehicular driving actions may be generated based on a classification of driver behavior.

For example, the classification may be a clustering algorithm that uses a data set of driver behavior, which may be used to train the algorithm to identify the aforementioned vehicular driving actions. The clustering algorithm may be a hierarchical clustering algorithm, a centroid-based clustering algorithm, a distribution-based clustering algorithm, or other such supervised learning algorithms.

The method 600 includes, at step 620, transmitting, over a secure connection, the at least one of the set of vehicular driving actions to the vehicle. In some embodiments, the secure connection may be the emergency channel (or link) exclusively that is reserved for emergency communications. In other embodiments, the secure connection may be an operational channel (or link) that is typically used for high-speed data communications.

In some embodiments, the operational link may be secured using an Internet layer cryptographic protocol, which enforces authenticity, integrity and secrecy. In an example, the operational link may use the Internet Protocol security (IPsec) protocol, pre-shared keys (PSK) or a public-key cryptosystem, e.g. RSA or Diffie-Hellman key exchange. The emergency channel may be secured using a low-latency Application layer cryptographic protocol, due to the imperative nature of emergency communications. In an example, the Secure Sockets Layer (SSL) protocol or the Transport Layer Security (TLS) protocol may be used for the emergency channel, which due to the time sensitive nature of the messages, does not require explicit client authentication after an initial authentication process.

Embodiments of the disclosed technology can be configured to implement solutions for remote safe driving as discussed in this document. These solutions include:

1. A method for remote safe driving of a vehicle, comprising: detecting an emergency situation; and in response to the detecting, switching operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components; and periodically transmitting a location of the vehicle to a remote monitoring center.

2. The method of solution 1, wherein the emergency situation comprises an abnormal sensor operation, an abnormal electronic control unit (ECU) operation, an abnormal network operation, a communication failure, a failure of a planning module, a failure of a car control module, a failure of a localization module, or a failure of a perception module.

3. The method of solution 1 or 2, wherein the subset of vehicular components comprises non-essential sensors and non-emergency subsystems.

4. The method of any of solutions 1 to 3, further comprising: stopping the vehicle due to the emergency situation; shutting down and restarting another subset of vehicular components; and performing a status check on at least one of the another subset of vehicular components.

In some solutions, the other set of vehicular components that are restarted may be selected in response to changes in the external environment. For an example, if the vehicle has come to a stop and dusk is approaching, the hazard lights will be turned on to ensure the visibility of the vehicle by other vehicles.

5. The method of solution 4, wherein the vehicle stops in a lane in which the vehicle is operating.

6. The method of solution 4, wherein stopping the vehicle comprises: finding an emergency lane; and stopping the vehicle in the emergency lane.

7. The method of any of solutions 4 to 6, further comprising: selectively restarting the operation of the vehicle based on a result of the status check.

8. The method of any of solutions 1 to 7, wherein the location of the vehicle comprises at least one of Global Positioning System (GPS) coordinates, a location relative to mile markers, or a location relative to known Wi-Fi transmitters.

9. A method for remote safe driving of a vehicle, comprising: selecting at least one of a set of vehicular driving actions; and transmitting, over a secure communication channel, the at least one of the set of vehicular driving actions to the vehicle, wherein the set of vehicular driving actions is generated based on a classification of driver behavior.

10. The method of solution 9, wherein the set of vehicular driving actions comprises one or more of parking the vehicle, moving from a predetermined origin to a predetermined destination, and moving to a refueling location.

11. The method of solution 9 or 10, wherein the classification of the plurality of driver behavior is based on a clustering algorithm.

12. The method of any of solutions 9 to 11, wherein the secure communication channel is an operational channel that is secured using an Internet layer cryptographic protocol.

13. The method of any of solutions 9 to 11, wherein the secure communication channel is an emergency channel that is secured using a low-latency Application layer cryptographic protocol.

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 and 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 one or more communication protocols (LTE, Wi-Fi, and so on).

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, e.g., 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, “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 remote safe driving of a vehicle, comprising: periodically transmitting monitoring signals to a remote monitoring center in communication with the vehicle;detecting an emergency situation; andin response to the detecting,switching operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components; andperiodically transmitting, to the remote monitoring center, a location of the vehicle where the emergency situation has been detected,wherein a period of the transmitting of the location of the vehicle is shorter than a period of the transmitting of the monitoring signals.

2. The method of claim 1, wherein the emergency situation comprises an abnormal sensor operation, an abnormal electronic control unit operation, an abnormal network operation, a failure of a planning module, a failure of a car control module, a failure of a localization module, or a failure of a perception module.

3. The method of claim 1, wherein the subset of vehicular components comprises non-essential sensors and non-emergency subsystems.

4. The method of claim 1, further comprising: stopping the vehicle due to the emergency situation;shutting down and restarting another subset of vehicular components; andperforming a status check on at least one of the another subset of vehicular components.

5. The method of claim 4, wherein the vehicle stops in a lane in which the vehicle is operating.

6. The method of claim 4, wherein stopping the vehicle comprises: finding an emergency lane; andstopping the vehicle in the emergency lane.

7. The method of claim 4, further comprising: selectively restarting the operation of the vehicle based on a result of the status check.

8. A non-transitory computer-readable storage medium having instructions stored thereupon, the instructions, when executed by a processor, causing the processor to implement a method for remote safe driving of a vehicle, comprising: instructions for periodically transmitting monitoring signals to a remote monitoring center in communication with the vehicle;instructions for detecting an emergency situation; andin response to the detecting, instructions for switching operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components; andinstructions for periodically transmitting, to the remote monitoring center, a location of the vehicle where the emergency situation has been detected,wherein a period of the transmitting of the location of the vehicle is shorter than a period of the transmitting of the monitoring signals.

9. The non-transitory computer-readable storage medium of claim 8, wherein the emergency situation comprises an abnormal sensor operation, an abnormal electronic control unit operation, an abnormal network operation, a failure of a planning module, a failure of a car control module, a failure of a localization module, or a failure of a perception module.

10. The non-transitory computer-readable storage medium of claim 8, wherein the subset of vehicular components comprises non-essential sensors and non-emergency subsystems.

11. The non-transitory computer-readable storage medium of claim 8, further comprising: instructions for stopping the vehicle due to the emergency situation;instructions for shutting down and restarting another subset of vehicular components; andinstructions for performing a status check on at least one of the another subset of vehicular components.

12. The non-transitory computer-readable storage medium of claim 11, wherein the vehicle stops in a lane in which the vehicle is operating.

13. The non-transitory computer-readable storage medium of claim 11, wherein stopping the vehicle comprises: instructions for finding an emergency lane; andinstructions for stopping the vehicle in the emergency lane.

14. The non-transitory computer-readable storage medium of claim 11, further comprising: instructions for selectively restarting the operation of the vehicle based on a result of the status check.

15. The non-transitory computer-readable storage medium of claim 8, wherein the location of the vehicle comprises at least one of Global Positioning System (GPS) coordinates, a location relative to mile markers, or a location relative to known Wi-Fi transmitters.

16. An apparatus for remote safe driving of a vehicle, comprising: a processor; anda memory that comprises instructions stored thereupon, wherein the instructions when executed by the processor configure the processor to: periodically transmit monitoring signals to a remote monitoring center in communication with the vehicle;detect an emergency situation; andin response to the detection of the emergency situation,switch operation of the vehicle to a low-power operation mode that comprises shutting down a subset of vehicular components; andperiodically transmit, to the remote monitoring center, a location of the vehicle where the emergency situation has been detected,wherein a period of a transmission of the location of the vehicle is shorter than a period of a transmission of the monitoring signals.

17. The apparatus of claim 16, wherein the emergency situation comprises an abnormal sensor operation, an abnormal electronic control unit operation, an abnormal network operation, a failure of a planning module, a failure of a car control module, a failure of a localization module, or a failure of a perception module.

18. The apparatus of claim 16, wherein the instructions further configure the processor to report the detection of the emergency situation to the remote monitoring center using an emergency signal that includes a location and a vehicle status message.

19. The apparatus of claim 16, wherein the instructions further configure the processor to implement a first policy that causes the vehicle to search for a nearest emergency lane and come to a stop in the nearest emergency lane.

20. The apparatus of claim 16, wherein the instructions further configure the processor to implement a second policy that causes the vehicle to determine whether an immediate stop is needed.