The present disclosure relates to methods and systems for autonomous vehicle safety using voice interactions.
There are various levels of autonomy with which a vehicle can operate. The Society of Automotive Engineers (SAE) categorizes autonomous vehicles as Levels 0-5, where Level 0 vehicles are fully manual and Level 5 vehicles are fully autonomous. Level 0 vehicles, in which all aspects of driving are manually controlled, account for the majority of vehicles on the road today. Level 1 vehicles include a single automated aspect that assists the driver, such as an Advanced Driver-Assistance System (ADAS) for steering, speed, or the braking control system. Although Level 2 vehicles provide automated steering and acceleration capabilities, the driver remains in control of the vehicle at all times. A Level 3 vehicle is able to detect the environment and make informed decisions regarding vehicle control, such as to overtake slower moving vehicles. In a Level 3 vehicle, an occupant may be asked to assume control, if the vehicle determines that it is unable to execute a requested task, or if autonomous operation fails. A Level 4 vehicle does not require human interaction because the vehicle can intervene when there is a system failure, however the option to manually override does remain if circumstances warrant. In a Level 5 vehicle, human driving is completely eliminated, and the vehicle is capable of adaptive and situational driving. As a result, a Level 5 vehicle often does not include controls such as a steering wheel or gas or brake pedals.
Some conventional vehicles include speech systems capable of recognizing speech uttered by an occupant of the vehicle. Speech utterances may, for example, include queries or commands directed to one or more features of the vehicle, or to other systems that are accessible to the vehicle.
As described herein a method and a system is provided for enabling increased safety in autonomous vehicles using voice interactions. In some embodiments, a method is provided for informing a driver of a vehicle that an autonomous driving mode is available and the vehicle's control system changes the driving mode from manual control to autonomous upon receiving a voice command from the driver. The method comprises a voice control system that generates voice dialog informing the driver that autonomous mode is possible. The vehicle's control system receives a voice command including speech utterances from a driver indicating a desire to change the driving mode from manual to autonomous. The vehicle's control system can also change the driving mode from manual to autonomous upon receipt of the command.
In some embodiments, a method is provided that enables the driver to ask if the vehicle can be operated in autonomous mode. The vehicle's control system determines if autonomous mode is possible along one or more routes to a destination, and if autonomous mode is available along at least one route, the vehicle's voice control system informs the driver of the possible route, and upon receiving a voice command from the driver, the vehicle switches to autonomous mode along the route.
In some embodiments, a vehicle includes a vehicle control system that controls the operation of the vehicle, and generates dialog informing a driver that autonomous mode is available. The vehicle further includes a microphone to receive voice commands from the driver, so that the voice commands are used to determine if a change from manual mode to autonomous mode or from autonomous mode to manual mode is desired. The vehicle's control system then changes the driving mode based on the voice command from the driver.
In some embodiments, a method is provided that determines if the driving mode must be changed from autonomous mode to manual mode. If the driving mode must be changed to manual mode, the voice control unit of the vehicle informs the driver of the need to change modes, and upon receiving a voice command from the driver acknowledging the change, the vehicle's control system will change the driving mode to manual mode.
In some embodiments, a method is provided that determines if a change in driving modes is necessary or optional. If the vehicle's control system determines that the change is necessary, it will inform the driver of the need to change driving modes and will change the driving mode upon receiving voice acknowledgment from the driver. If the vehicle control unit determines that a change in driving modes is optional, the voice control unit will inform the driver of the option, and if the driver requests to change or stay in autonomous mode, the vehicle control unit will provide the user possible routes on which the vehicle can remain in autonomous mode.
Various aspects and embodiments of the disclosure are described below with reference to the following figures. It should be appreciated that the figures are not necessarily drawn to scale. Items appearing in multiple figures are indicated by like reference numerals in each figure in which the items appear. In the figures:
As used herein “vehicle” can be any machine or mechanized equipment capable of transporting things from one geographical area to a different geographical area. A vehicle may be a car, bus, truck, airplane, or any similar means for transporting people, things or goods.
As used herein “autonomous vehicle” can be any vehicle that operates autonomously or semi-autonomously such that the autonomous vehicle uses sensory input to navigate and move from one geographical area to a different geographical area. Autonomous vehicles can sense their environment using various technologies such as radar, LIDAR, image sensors or other similar sensing technologies. Autonomous vehicles can navigate using global positioning systems (GPS), information provided by other vehicles, input from an occupant (e.g., a driver), or other similar input. In some instances, an autonomous vehicle can be referred to as an autonomous system.
As used herein “speech utterance” can be a unit of speech bound in part by silence. Speech utterances may, for example, include queries or commands directed to one or more vehicle features or systems, or to other systems that are accessible to the vehicle.
As used herein “voice interaction” and “voice” can relate to any speech-based communication which can include speech utterances or speech generated by a user or an autonomous system.
As used herein “occupant” can refer to any human or animal within the vehicle and can include the driver or operator of the vehicle.
An occupant of an autonomous vehicle can interact with the autonomous vehicle using speech utterances. Through voice interaction between an occupant and the autonomous vehicle, the occupant can control certain operational aspects of an autonomous vehicle. Permitting the occupant or user of an autonomous vehicle to control or interact with the autonomous vehicle through voice interaction promotes safe and flexible operation of the autonomous vehicle.
For example, voice interaction can be used to either initiate a transfer of control or warn the occupants of a transfer of control. Autonomous vehicles can transfer control of the autonomous vehicle's operation from an occupant (i.e., driver) to the autonomous vehicle's drive and control system (i.e., in Level 2-4 vehicles the autonomous vehicle can switch from being operated manually by a driver to being operating autonomously, or vice versa). A transfer of control may be driver-initiated or vehicle-initiated. When circumstances and the vehicle's capabilities are permissible (e.g., when road conditions and the environment are within the scope of the vehicle's autonomous capabilities) a transfer of control can be initiated by an occupant (i.e., driver) or the autonomous vehicle can alert the occupants of a transfer of control. In one instance, if the vehicle determines that present or future conditions are outside the scope of its capabilities, such as when a highway exit is to be taken, a traffic accident is detected ahead, when adverse weather conditions occur, a sensor malfunctions, etc., the vehicle can notify the occupants that control will be transferred from autonomous to manual. The use of voice interaction between the driver and vehicle may promote flexibility and safety around such transfers of control, through the use of different modalities than are conventionally employed, the expression of urgency when circumstances warrant, and the use of dialogue between the driver and the vehicle.
In another example, voice interaction can be used to interact with vehicles that operate entirely autonomously (e.g., Level 4-5 vehicles), such as a “robo taxi” operated by a ride-sharing service or a vehicle which is owned by the occupant but used to autonomously transport the occupant to a specified destination. Occupants can interact with these entirely autonomous vehicles through a “virtual chauffeur” that can obtain trip details such as whether to stop at a specific point along the route (e.g., to get money from an ATM), to identify the exact stopping point at the destination, to drive slow, etc. This “virtual chauffeur” permits occupants to specify through voice interaction and in real time, various details regarding a trip.
Illustrated in
Sensors 112 provide information to autonomous vehicle operation manager 120, which controls various aspects of autonomous operation of the vehicle to fully or partially aid the occupant in operating the vehicle. The components of the autonomous vehicle operation manager 120 can include operation mode manager 122, navigation manager 124, vehicle position manager 126, speed/acceleration manager 128, steering/maneuvering manager 130, road condition manager 132, route planning manager 134, and vehicle context manager 150. The information generated by certain management modules within the autonomous vehicle operation manager 120 can be related to vehicle operation mode, navigation, vehicle position, speed and acceleration, steering and maneuvering, route planning and road conditions. This information can be used by the vehicle context manager 150 within the vehicle operation manager 120 to produce and update vehicle context data, including a current mode, a general state or condition of the vehicle, and events which have occurred or may be about to occur. For example, vehicle context data may indicate a geographic location of the vehicle, a position of the vehicle on the road and/or within a lane, a position of another vehicle relative to the vehicle, a speed or acceleration of the vehicle, a steering position or maneuver of the vehicle, a current or predicted weather condition, navigation steps of a current route, an alarm or warning signal that was generated or is about to be generated, a change in vehicle speed, a turn that has been or may be about to be made, a lane change which has been or may be about to be made, potential routes which the vehicle may take, and/or any other suitable vehicle context information. In some embodiments, vehicle context information may be captured over a period of time and can include a time stamp or sequence number associated with a state, condition, or event, such as to aid in diagnostic procedures.
In representative system 100, multimodal interface 102 receives voice input (e.g., supplied by one or more sensors 112, such as microphone 113) to ASR/NLU 104, as well as input via other modalities 108, such as via a touch screen (not shown in
The occupant context model 162, and information received by autonomous vehicle operation manager 120, may be used by voice assistant 160 to define voice output to the occupant (e.g., intent options, dialogue content, voice quality, intonation, speech style, etc.) via TTS 106. For example, voice assistant 160 may have access to a plurality of intent, dialogue, voice quality, intonation and/or speech style options, select certain options based on current vehicle context information, current occupant context automation, and/or associations between the two, and use the selected options to produce voice output to the occupant. The ASR/NLU 104 may then receive voice input from the occupant in response to this voice output. In some embodiments, ASR/NLU 104 may be configured to disambiguate and/or resolve driver commands comprising free speech. In this manner, voice assistant 160 may flexibly enable a voice dialogue or conversation to occur between the occupant and the vehicle. The information gathered by voice assistant 160 during interaction with the occupant may be provided to autonomous vehicle operation manager 120 for use in controlling operation of the vehicle, such as to complete an action or task specified via voice input.
The elements depicted in
It should be appreciated that, although
Using Voice Interaction to Manage Transfers of Control
Some embodiments of this disclosure are directed to using voice interaction between the driver/occupant and a vehicle, to promote flexibility and safety when transfers of control occur between manual and autonomous operation. For example, a driver can use voice commands that comprise speech utterances to request a transfer from manual operation to autonomous operation, the vehicle can use voice to announce to the driver that autonomous operation is possible or to inform the driver that a transfer to manual operation is preferable. The voice control system 100 can determine the intent of a voice command by parsing the speech utterances and using automatic speech recognition or natural language processing to determine driver intent.
The use of voice may increase flexibility, enabling a dialogue or conversation between the driver and vehicle, and allowing for functionality which conventional approaches cannot support. For example, the use of voice interaction may enable a driver to indicate that he/she intends to assume manual control at a time or upon an event in the future, rather than immediately, or may allow the driver to ask the vehicle to determine a route which allows for a maximum amount of time when the vehicle operates autonomously, or which allows autonomous operation to begin soonest. Further, a dialogue may instill confidence and trust in the driver that the vehicle understands and will act upon his/her commands, which can make vehicle operation safer overall.
At the start of representative process 200, a determination is made by the vehicle control system 190 that autonomous operation is available (step 210) such that a driver or occupant can request that the vehicle operate in an autonomous mode. The vehicle control system 190 makes this determination any number of ways. For example, the determination may be based upon constraints or criteria which vary by vehicle and/or location. In this respect, some vehicles may only be capable of operating autonomously on the highway or routes having a speed limit larger than a predetermined threshold, and some locations (e.g., cities) may specify that autonomous operation is only allowed in certain areas. As a result, the determination may be made by vehicle context manager 150 (
In the representative process 200 the vehicle control system 190 then proceeds to act (step 220) such that voice is used to inform the driver that autonomous vehicle operation is available. This may be performed in any of numerous ways. For example, voice assistant 160 (
The vehicle control system 190 receives a voice command from a driver or occupant of the vehicle to transfer to autonomous vehicle operation (step 230). This voice command can be received by voice assistant 160 via ASR/NLU 104.
In some embodiments, voice assistant 160 may use voice biometrics to determine that a voice command to initiate transfer to autonomous operation originated from the driver and not from another occupant of the vehicle. Of course, techniques other than voice biometrics may also, or alternatively, be used to determine whether a voice command originated with a driver. For example, if a vehicle includes several microphones dispersed throughout, then the location of the microphone closest to the speaker may be used to determine whether he/she is the driver or a passenger.
The vehicle control system 190 then determines whether the received voice command specifies a time or event upon which a transfer to autonomous operation is to be initiated (step 240). A voice command may specify, for example, that autonomous operation should occur in ten seconds, at the next exit, at the Fremont exit, when the next highway is reached, and/or at upon any other suitable time or event. For example, voice assistant 160 may determine whether a voice command received via ASR/NLU 104 specifies a time or event upon which autonomous operation is to begin.
If it is determined that the voice command specifies a time or event upon which autonomous operation is to be initiated, then the vehicle control system 190 checks whether the specified time or event has occurred (step 250) and reiterates this check until the specified time or event occurs. In some instances, the event can be referred to as a trigger event. For example, if the voice command is issued by the driver at 2:20 PM to switch to autonomous mode at 2:30 PM, then the vehicle control system 190 will perform the check (step 250) until a time element (i.e., system clock, counter or otherwise) within the vehicle control system 190 equals a time value equivalent to 2:30 PM. In another example, if the driver specifies via voice command that the vehicle should operate in autonomous mode once the vehicle merges onto a particular highway, the vehicle control system 190 will perform the check (step 250) until a geo-location application within the vehicle indicates that the vehicle's position is proximate to or on the specified highway. Once the specified time or event has occurred, the vehicle control system 190 process then enables autonomous operation (step 260). For example, voice assistant 160 (
In the event that the received voice command (step 230) does not specify a time or event upon which autonomous mode should be enabled (step 240), the vehicle control system 190 can proceed to enable autonomous operation (step 260).
It should be appreciated that a vehicle may inform the driver that autonomous operation is available for any of numerous reasons. For example, in some embodiments of this disclosure, a driver may be informed that autonomous operation is available if it is detected that the driver is drowsy, incapacitated, distracted (e.g., by his/her phone, by kids fighting in the backseat, etc.), or otherwise unable to devote his/her full attention to driving. When this occurs, the driver may be prompted to initiate a transfer to autonomous operation. In certain circumstances (e.g., upon detecting that the driver has fallen asleep or become incapacitated), a transfer may be initiated automatically. As such, some embodiments of this disclosure may improve the safety of the driver and passengers in the vehicle.
The vehicle control system 190 determines that autonomous vehicle operation, or autonomous mode, is available in response to environmental data indicating that autonomous mode is preferred or can be made in response to a voice command from the driver or a vehicle occupant questioning whether autonomous operation is available (step 310). For example, a voice command may be received by voice assistant 160 (
Upon receiving the voice command (step 310), the vehicle control system 190 can identify potential routes to the destination (step 320), so that one potential route which allows autonomous operation may be chosen. Potential routes to a destination may be identified in any suitable way. For example, voice assistant 160 may query route planning component 134 to identify one or more potential routes to the destination based on information provided by navigation manager 124. For example, route planning manager 134 may employ rules- and/or inferencing-based processing to identify the potential routes that exist to the destination, determine which of the potential routes allow for autonomous vehicle operation (e.g., travel in areas in which autonomous operation is allowed), evaluate potential routes according to various criteria, select a particular route based on those criteria, etc.
The vehicle control system 190 then evaluates the possible routes and determines which possible routes permit autonomous operation (step 330). In making this determination, the vehicle control system 190 can determine (step 330) that no potential routes permit autonomous operation, or that there are one or more potential routes. This determination may be made in any suitable way, such as by route planning component 134, using the techniques described immediately above. When no autonomous route is available, the vehicle control system 190 can leverage the voice control system 100 to inform the driver via voice (e.g., using TTS 106) that there is no route to the destination which allows for autonomous vehicle operation (step 335).
If at least one potential route allows for autonomous vehicle operation, then the vehicle control system 190 evaluates the possible routes (step 340) according to one or more criteria. This evaluation may, for example, be performed by route planning manager 134. Any of numerous criteria may be used to evaluate a potential route, and the criteria may be predetermined and/or determined dynamically. For example, a potential route may be evaluated based upon the amount of time that it allows the vehicle to remain in autonomous operation, how soon it allows the destination to be reached, whether gas is available along the route, and/or any of numerous other criteria.
The voice control system 100 is then leveraged to use voice to inform the driver that autonomous vehicle operation is available (step 350), and to provide information on one or more of the potential routes along which autonomous operation may be used, so that the driver may select a particular one that best suits his/her needs. In some instance, this voice can be referred to as voice-based dialog. For example, voice assistant 160 may produce voice output via TTS 106, using information provided by route planning manager 134 and/or other components of autonomous vehicle operation manager 120. The vehicle control system 190 can receive a voice command from the driver to transfer to autonomous operation along one of the potential routes (step 360) and then switch the vehicle into autonomous mode (step 370).
While the description above with reference to
Any of numerous circumstances may give rise to the driver needing to assume manual operation of the vehicle. For example, if a highway is about to end (e.g., if autonomous operation is only available on highway travel), weather conditions deteriorate, or an accident is detected ahead, the driver may need to assume manual operation. Similarly, there may be numerous circumstances in which a transfer to manual operation is preferable, but not necessary. For example, if staying on a previously established route to a destination means switching to manual operation, but there are other routes available, then a transfer to manual operation may be optional.
Using voice commands or a vehicle-initiated dialog with the driver to switch between autonomous or manual mode may make a vehicle-initiated transfer of control safer, whether the transfer of control is necessary or optional. In this respect, conventional approaches to transfers of control typically involve informing a driver of the need to assume manual control of the vehicle using an icon on a screen and a beep or alarm. Using voice may more fully engage the driver's other senses and may allow for urgency to be expressed around a transfer of control. For example, through the use of an “urgent” style of speech by a multi-style TTS and selective wording (e.g., “you must take control” instead of “please take control”), some embodiments of the disclosure may more effectively communicate to a driver when a transfer of control must take place. Voice interaction may be used to communicate information to the driver to facilitate a safe transfer to manual control of the vehicle. For example, voice interaction may be used to communicate the vehicle's speed, traffic density, the time until a next action is needed (e.g. to the exit), the time remaining on the drive, and/or other information which a driver may wish to know before assuming manual control of the vehicle. Providing this information may not only facilitate a safe transfer of control, but also allow the driver to change his/her mind regarding a transfer of control if certain information is different than expected.
The use of voice also enables a dialogue to occur between the driver and vehicle. This may allow for not only more flexible interaction around transfers of control (e.g., by allowing the driver to inform the vehicle that he/she needs more time before a transfer is to occur, allowing him/her to ask for more information around various options, allowing him/her to understand the vehicle's reasoning behind a request to transfer control, etc.), but can also instill confidence and trust in the driver that the vehicle understands his/her commands, and will carry them out correctly, which can further enhance vehicle safety.
As an example, voice interaction may be used to explain to the driver that, if the driver indicated via voice command that they wished to assume manual control of the vehicle but the vehicle remained in autonomous operation, the transfer did not occur because certain requirements were not met. For example, voice interaction could be used to explain to the driver that, although the vehicle detected that the driver's eyes were on the road and their hands were on the steering wheel, their foot must also be on the accelerator before manual operation can begin. By explaining the reasoning behind specific actions taken (and not taken) by the vehicle, some embodiments of the disclosure may increase the driver's confidence in the vehicle, and enable the driver to learn how to operate the vehicle more effectively over time, leading to increased vehicle safety. The use of voice interaction to explain actions which are taken or not taken by the vehicle may not be limited to actions relating to transfers of control. Voice interaction may be used to communicate the reasoning behind any of numerous types of actions.
In some embodiments, driver context information (e.g., occupant context model 162 (
The vehicle control system 190 then determines whether the transfer of control is necessary, or optional (step 420). This determination may also be made in any suitable way. For example, a determination that a transfer of control is necessary may be based upon the options which are available to the vehicle. If all viable options are outside of the vehicle's capabilities, then it may be determined that a transfer of control is necessary. If it is determined that a transfer of control is necessary (step 420), then the vehicle control system 190 uses voice to inform the driver of a need to transfer to manual vehicle operation (step 430). This may be performed in any of numerous ways. For example, voice assistant 160 (
If a determination is made that a transfer of control is optional (step 420) then the vehicle control system 190 can use voice to inform the driver that they have the option to change to manual vehicle operation (step 460). For example, voice assistant 160 may employ TTS 106 to inform the driver of the option to transfer control. The vehicle control system 190 may then receive a voice acknowledgement from the driver to remain in autonomous mode (step 470). For example, a voice command may be received by voice assistant 160 via ASR/NLU 104.
Upon receiving a voice command indicating that the vehicle should remain in an autonomous operating mode (step 470), the vehicle control system 190 then determines whether a new route is needed (step 480), and if one is not needed, the vehicle control system 190 may direct the vehicle to continue navigating along the original route (step 485). This determination may be made in any of numerous ways. For example, it may be determined that a new route is needed if remaining in autonomous operation will cause a previously scheduled highway exit to be missed.
If it is determined that a new route is needed, then the vehicle control system 190 can identify a new route (step 490), and direct the vehicle to navigate along the new route (step 495). For example, voice assistant 160 may instruct autonomous vehicle operation manager 120 to calculate a new route using information provided by navigation manager 124.
In one example, a vehicle operating in autonomous mode passively notifies a driver that the driver needs to take manual control of the vehicle in a set period of time, e.g., ninety seconds. The driver fails to notice the passive notification from the vehicle and continues to remain distracted (e.g., looking at their phone, reading, sleeping, watching scenery, sitting in the back seat). Upon determining that the driver remains distracted, the vehicle issues another notification to the driver that includes both audio and visual stimulation to tell the driver that they should touch a display in the vehicle to indicate that they will take over manual operation. It should be appreciated that the vehicle could require any form of affirmative input from the driver that indicates the driver is alert and acknowledged the vehicle's notification.
After a predetermined period of time, if the driver fails to touch the display, the vehicle may assess one or more environmental factors to determine whether the driver is alert or distracted. These environmental factors could include, but are not limited to, determining whether the driver's eyes are directed towards the road, identifying driver biofeedback, determining whether the driver is sleeping, or determining whether noise or commotion is preventing the driver from receiving the notification. Subsequently, the vehicle can issue one or more additional notifications or alerts to engage the driver, such as: increasing the brightness of a display, flashing lights, vibrating a seat, generating a tone, turning down the volume, or other similar alerts or notifications.
Once the driver acknowledges that they can take over manual operation, the vehicle's control system begins the process of switching from autonomous operation to manual operation. If during the switching process the driver indicates that they can no longer take over manual operation, the vehicle determines whether a new route is necessary and upon identifying another exit further down the road, updates the route accordingly to permit the vehicle to continue operating in autonomous mode until the driver is capable of taking over manual operation.
Voice-Enabled Virtual Chauffeur
Some embodiments are directed to vehicles which may operate entirely autonomously (e.g., vehicles at Levels 4-5), such as a “robo taxi” operated by a ride-sharing service, or a vehicle which is owned by the occupant but often used to autonomously transport the occupant to a specified destination. Specifically, some embodiments are directed to providing voice-enabled “virtual chauffeur” capabilities in such vehicles. As noted above, such vehicles may not have a human driver with whom an occupant can interact to specify the fine details of a trip, or any control instruments to which an occupant may provide input. As such, voice-enabled “virtual chauffeur” capabilities may allow the occupant to specify various details about a trip, and to control various navigation aspects in real time as if he/she were speaking to a driver.
For example, if the occupant asks a question about a trip, such as to inquire about the remaining distance to the destination, the estimated arrival time, whether there are any traffic jams ahead, or other trip details, then receiving the voice command or utterance (step 510) may involve voice assistant 160 receiving the question via ASR/NLU 104, processing the question using occupant context model 162 and/or information provided by vehicle context manager 150, and responding to the question via TTS 106.
Another example may involve the occupant setting a new waypoint while traveling along a route toward a destination. For example, the occupant may indicate that the vehicle is to let him/her out at a particular spot, and then ask for the vehicle to wait until she is done, or to leave the waypoint temporarily (e.g., for a time interval specified by the occupant) and either make a trip around the block or find suitable temporary parking. The vehicle may automatically employ navigation manager 124 and route planning manager 134 of autonomous vehicle operation manager 120 (
As another example, the occupant may spot a building or other point of interest outside the vehicle, and either describe it verbally (e.g., “the red building on the left-hand side”), or by looking at it (e.g., “that building”), and ask the vehicle to let him/her out there. The vehicle may employ gaze detection (e.g., using camera/gaze detection 114) and a two- or three-dimensional representation of the vehicle's vicinity (e.g., using vehicle position manager 126 of vehicle autonomous operation manager 120) to identify the point of interest identified by the occupant and translate it to an address which may then be used (e.g., by navigation manager 124) to establish a new waypoint or destination. For example, the occupant may specify that the point of interest is to be the new destination by saying “please let me out there” (e.g., received by voice assistant via ASR/NLU 104), and the vehicle may identify (e.g., using navigation manager 124) the closest safe place for letting the occupant leave the vehicle.
In certain situations, it may be inadvisable to allow an occupant to set a new way point and/or new destination for a trip. For example, if the occupant is a child, or incapacitated, then it may be inadvisable to allow the occupant to set a new waypoint or destination. As a result, some embodiments may involve voice assistant 160 employing voice biometrics to determine whether an occupant who requests a new waypoint or destination is allowed to do so. Defining the functionality that is made available to a given vehicle occupant may be accomplished in any suitable way. For example, some embodiments may provide for a “safe mode” to be used when the occupant on a trip is a child or incapacitated, and enable an authorized user to board the occupant in the car, set the destination, and only allow certain changes to be made by the occupant during the trip (e.g., to change climate controls, switch channels on the radio, etc.). Some embodiments may provide for establishing backup communication plans with an authorized user, in case an emergency or unforeseen circumstances arise. For example, some embodiments may provide for contacting an authorized user if the vehicle gets a flat tire while transporting a child to a soccer game, so that the authorized user may choose how to handle the situation. As another example, some embodiments may enable an authorized user to intervene while a trip is ongoing, such as if a vehicle becomes stuck in a traffic jam while transporting an elderly person to a doctor's appointment, enabling the authorized user to select or approve an alternate route so that the elderly person makes it to the appointment on time.
Implementation Detail
Techniques operating according to the principles described herein may be implemented in any suitable manner. Included in the description above are a series of flow charts showing the steps and acts of various processes for using voice interaction to enable an occupant of an autonomous vehicle to control certain operational aspects of the vehicle. The processing and decision blocks of the flow charts above represent steps and acts that may be included in algorithms that carry out these various processes. Algorithms derived from these processes may be implemented as software integrated with and directing the operation of one or more single- or multi-purpose processors, may be implemented as functionally-equivalent circuits, or may be implemented in any other suitable manner. It should be appreciated that the flow charts included herein do not depict the syntax or operation of any particular circuit or of any particular programming language or type of programming language. Rather, the flow charts illustrate the functional information one skilled in the art may use to fabricate circuits or to implement computer software algorithms to perform the processing of a particular apparatus carrying out the types of techniques described herein. It should also be appreciated that, unless otherwise indicated herein, the particular sequence of steps and/or acts described in each flow chart is merely illustrative of the algorithms that may be implemented and can be varied in implementations and embodiments of the principles described herein.
Accordingly, in some embodiments, the techniques described herein may be embodied in computer-executable instructions implemented as software that can be stored in storage 196 and included as application software, system software, firmware, middleware, embedded code, or any other suitable type of computer code. Such computer-executable instructions may be written using any of a number of suitable programming languages and/or programming or scripting tools, and also may be compiled as executable machine language code or intermediate code that is executed on a framework or virtual machine.
When techniques described herein are embodied as computer-executable instructions, these computer-executable instructions may be implemented in any suitable manner, including as a number of functional facilities, each providing one or more operations to complete execution of algorithms operating according to these techniques. A “functional facility,” however instantiated, is a structural component of a computer system that, when integrated with and executed by one or more computers, causes the one or more computers to perform a specific operational role. A functional facility may be a portion of or an entire software element. For example, a functional facility may be implemented as a function of a process, or as a discrete process, or as any other suitable unit of processing. If techniques described herein are implemented as multiple functional facilities, each functional facility may be implemented in its own way; all need not be implemented the same way. Additionally, these functional facilities may be executed in parallel and/or serially, as appropriate, and may pass information between one another using a shared memory on the computer(s) or computing elements on which they are executing, using a message passing protocol, or in any other suitable way.
Generally, functional facilities include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Typically, the functionality of the functional facilities may be combined or distributed as desired in the systems in which they operate. In some implementations, one or more functional facilities carrying out techniques herein may together form a complete software package. These functional facilities may, in alternative embodiments, be adapted to interact with other, unrelated functional facilities and/or processes, to implement a software program application. In other implementations, the functional facilities may be adapted to interact with other functional facilities in such a way as form an operating system, including the Windows® operating system, available from the Microsoft® Corporation of Redmond, Wash. In other words, in some implementations, the functional facilities may be implemented alternatively as a portion of or outside of an operating system.
Some exemplary functional facilities have been described herein for carrying out one or more tasks. It should be appreciated, though, that the functional facilities and division of tasks described is merely illustrative of the type of functional facilities that may implement the exemplary techniques described herein, and that embodiments are not limited to being implemented in any specific number, division, or type of functional facilities. In some implementations, all functionality may be implemented in a single functional facility. It should also be appreciated that, in some implementations, some of the functional facilities described herein may be implemented together with or separately from others (i.e., as a single unit or separate units), or some of these functional facilities may not be implemented.
Computer-executable instructions implementing the techniques described herein (when implemented as one or more functional facilities or in any other manner) may, in some embodiments, be encoded on one or more computer-readable media such as storage 196 to provide functionality to the media. Computer-readable media include magnetic media such as a hard disk drive, optical media such as a Compact Disk (CD) or a Digital Versatile Disk (DVD), a persistent or non-persistent solid-state memory (e.g., Flash memory, Magnetic RAM, etc.), or any other suitable storage media. Such a computer-readable medium may be implemented in any suitable manner, including as computer-readable storage media 196 of
In some, but not all, implementations in which the techniques may be embodied as computer-executable instructions, these instructions may be executed on one or more suitable computing device(s) operating in any suitable computer system, including the exemplary control system 190 of
Embodiments have been described where the techniques are implemented in circuitry and/or computer-executable instructions. It should be appreciated that some embodiments may be in the form of a method, of which at least one example has been provided. The acts performed as part of the method may be ordered in any suitable way. Accordingly, embodiments may be constructed in which acts are performed in an order different than illustrated, which may include performing some acts simultaneously, even though shown as sequential acts in illustrative embodiments.
Various aspects of the embodiments described above may be used alone, in combination, or in a variety of arrangements not specifically discussed in the embodiments described in the foregoing and is therefore not limited in its application to the details and arrangement of components set forth in the foregoing description or illustrated in the drawings. For example, aspects described in one embodiment may be combined in any manner with aspects described in other embodiments.
Use of ordinal terms such as “first,” “second,” “third,” etc., in the claims to modify a claim element does not by itself connote any priority, precedence, or order of one claim element over another or the temporal order in which acts of a method are performed, but are used merely as labels to distinguish one claim element having a certain name from another element having a same name (but for use of the ordinal term) to distinguish the claim elements.
Also, the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of “including,” “comprising,” “having,” “containing,” “involving,” and variations thereof herein, is meant to encompass the items listed thereafter and equivalents thereof as well as additional items.
The word “exemplary” is used herein to mean serving as an example, instance, or illustration. Any embodiment, implementation, process, feature, etc. described herein as exemplary should therefore be understood to be an illustrative example and should not be understood to be a preferred or advantageous example unless otherwise indicated.
Having thus described several aspects of at least one embodiment, it is to be appreciated that various alterations, modifications, and improvements will readily occur to those skilled in the art. Such alterations, modifications, and improvements are intended to be part of this disclosure and are intended to be within the spirit and scope of the principles described herein. Accordingly, the foregoing description and drawings are by way of example only.
This application claims the benefit under 35 U.S.C. 119 (e) of U.S. Provisional Application No. 62/788,471 filed on Jan. 4, 2019 the contents of which are incorporated by reference herein in their entirety.
Number | Name | Date | Kind |
---|---|---|---|
5274560 | LaRue | Dec 1993 | A |
9581460 | McNew | Feb 2017 | B1 |
10451428 | Lathrop | Oct 2019 | B2 |
20120316699 | Filev | Dec 2012 | A1 |
20140303827 | Dolgov | Oct 2014 | A1 |
20150314780 | Stenneth | Nov 2015 | A1 |
20170068245 | Scofield | Mar 2017 | A1 |
20170088145 | Gordon | Mar 2017 | A1 |
20170110022 | Gulash | Apr 2017 | A1 |
20170259832 | Lathrop | Sep 2017 | A1 |
20170263252 | Abdelsamie | Sep 2017 | A1 |
20170287476 | Tzirkel-Hancock | Oct 2017 | A1 |
20180238698 | Pedersen | Aug 2018 | A1 |
20180336007 | Li | Nov 2018 | A1 |
20190094038 | Oh | Mar 2019 | A1 |
20190121522 | Davis | Apr 2019 | A1 |
20190204827 | Bhalla | Jul 2019 | A1 |
20190315274 | Mehdi | Oct 2019 | A1 |
20200041993 | Li | Feb 2020 | A1 |
20200086887 | Gohl | Mar 2020 | A1 |
20200139992 | Oba | May 2020 | A1 |
20200141748 | Krysiuk | May 2020 | A1 |
20200192358 | Yu | Jun 2020 | A1 |
20210139036 | Kim | May 2021 | A1 |
20210370935 | Kuenzner | Dec 2021 | A1 |
Number | Date | Country |
---|---|---|
106379310 | Feb 2017 | CN |
102018002941 | Oct 2018 | DE |
2017151672 | Sep 2017 | WO |
Entry |
---|
“Dual-Mode Vehicle Routing in Mixed Autonomous and Non-Autonomous Zone Networks” by Beirigo, Schulte, and Negenborn. 2018 21st International Conference on Intelligent Transportation Systems, Maui, Hawaii, USA, Nov. 4-7, 2018 (Year: 2018). |
Machine translation from Espacenet of CN106379310 (translated Jun. 3, 2022) (Year: 2022). |
International Search Report and Written Opinion, PCT Application No. PCT/US2020/012227, dated Mar. 12, 2020 (14 pages). |
Number | Date | Country | |
---|---|---|---|
20200216086 A1 | Jul 2020 | US |
Number | Date | Country | |
---|---|---|---|
62788471 | Jan 2019 | US |