AUTONOMOUS VEHICLE CONTROL SYSTEM

Abstract

Autonomous vehicle control system (10) operating on a computer-readable medium, the autonomous vehicle control system (10) comprising: an operational plan controller (26, 50) configured to maintain a plurality of operational plans (52, 54, 56, 58, 60, 62), each corresponding to a predefined set of behavioral properties of an associated autonomous vehicle (12), based on situational awareness data provided via onboard sensors (16) of the autonomous vehicle (12) and mission control data provided by a user interface (22); a decision-making algorithm (28) configured to select one of the plurality of operational plans (52, 54, 56, 58, 60,62) to select the operating behavior of the autonomous vehicle (12) based on the situation awareness data and the mission control data at a given time and to provide an intent decision based on the situation awareness data and the selected operating plan from the multitude of operating plans (52, 54, 56, 58, 60, 62); and an execution machine (30) configured to provide control outputs to operating components (18) belonging to the autonomous vehicle (12) for navigation and control of the autonomous vehicle (12) based on the selected operating plan from the plurality of operating plans (52, 54, 56, 58, 60, 62) and in response to the intent decision, wherein the decision-making algorithm (28) includes a utilization calculation system (32, 100) configured to calculate an overall utilization factor for each of the plurality of operating plans (52, 54, 56, 58, 60, 62) based on a plurality of behavioral properties,wherein the utilization calculation system (32, 100) is set up to select one from the multitude of operating plans (52, 54, 56, 58, 60, 62) based on the overall utilization factor calculated for each of the multitude of operating plans (52, 54, 56, 58, 60, 62), wherein the overall utilization factor is calculated based on the multitude of behavioral properties and based on a respective multitude of programmable weights that are optionally assigned to the multitude of behavioral properties and are provided as part of the mission control data which is provided via the user interface (22).

Description

RELATED APPLICATIONSThe present invention relates generally to artificial intelligence systems, and more particularly to an autonomous vehicle control system.TECHNICAL FIELDThe present disclosure relates generally to artificial intelligence systems, and more particularly to an autonomous vehicle control system.BACKGROUNDUnmanned vehicles are becoming more and more frequent in a series of tactistic missions, for example during surveillance and / or combat missions. For example, in the case of an aircraft, unmanned aerial vehicles (UAVs) have been developed as a means for replacing pilots in the aircraft for controlling the aircraft because some flight operations are becoming more dangerous and tedious. Furthermore, unmanned vehicles may operate in autonomous form during significantly improved computer processing and sensor technology. For example, as opposed to operating via remote control, a given unmanned vehicle may be operated based on sensors configured to monitor external stimuli, and may be programmed to respond to the external stimuli and execute mission targets that are either programmed or provided as input commands. European Patent Application EP 2 317 412 A1 discloses a security management system for devices designed for autonomous operation in a real-time environment, in which both a deterministic processor and a non-deterministic processor are provided for processing incoming alarms and generating control signals in response. The non-deterministic processor can handle unexpert, complex, and unpredictable situations by substantially providing open ended methods that operate in large search spaces with no guarantee of solution. The deterministic processor monitors the behavior of the non-deterministic processor and validates control signals generated by it based on security policies. The deterministic processor also provides a smart interface to the non-deterministic processor that receives alerts from only the deterministic processor and forces time critical delivery of responses.ILLUSTRATIONAn example includes an autonomous vehicle control system. The system includes an operation plan controller to maintain a plurality of operation plans, each corresponding to a predetermined set of behavior characteristics of an associated autonomous vehicle, based on Situationsbewusstseinsdaten provided via onboard autonomous vehicle sensors and mission line data provided from a user interface. The system also includes a decision making algorithm to select one of the plurality of operation plans for the operation behavior of the autonomous vehicle based on the situation awareness data and the mission guidance data at a certain time and provide an intention decision based on the situation awareness data and the selected one of the plurality of operation plans. The system further includes an execution engine to provide control outputs to operating components of the autonomous vehicle for navigation and control based on the selected one of the plurality of operating plans and in response to the intent decision, the decision making algorithm including a usage calculation system configured to calculate a total usage factor for each of the plurality of operating plans based on a plurality of behavioral characteristics, the usage calculation system configured to select the one of the plurality of operating plans based on the total usage factor calculated for each of the plurality of operating plans, the total usage factor calculated based on the plurality of behavioral characteristics and based on a respective plurality of programmable weights selectively associated with the plurality of behavioral characteristics and provided as part of the mission line data, which are provided via the user interface.Another example includes a method of controlling an autonomous vehicle. The method includes providing mission guidance data to an autonomous vehicle control system associated with the autonomous vehicle via a user interface. The method also includes generating situational awareness data associated with the autonomous vehicle in response to receiving sensor data provided by on-board sensors. The method also includes selecting one of a plurality of operation plans each corresponding to a predetermined set of behavior characteristics of the autonomous vehicle based on the situation awareness data and the mission guidance data. The method further includes providing control outputs to operating components associated with the autonomous vehicle for navigation and control of the autonomous vehicle in response to the sensor data and based on the selected one of the plurality of operating plans. The method further comprises calculating a total usage factor for each of the plurality of operating schedules based on a plurality of performance characteristics, wherein selecting the one of the plurality of operating schedules) comprises selecting the one of the plurality of operating schedules based on the total usage factor calculated for each of the plurality of operating schedules, wherein calculating the total usage factor comprises providing a respective plurality of programmable weights that are selectively associated with the plurality of performance characteristics via the mission line data.Another example includes an autonomous vehicle. The vehicle includes on-board sensors configured to generate situational awareness data associated with situational awareness conditions of the autonomous vehicle. The vehicle also includes operating components configured to provide navigation and control of the autonomous vehicle in response to control outputs. The vehicle also includes an autonomous vehicle control system operating on a computer readable medium. The autonomous vehicle control system includes an operation plan controller configured to maintain a plurality of operation plans each corresponding to a predetermined set of behavior characteristics of an associated autonomous vehicle based on the situational awareness data and the mission guidance data. The system also includes a decision making algorithm configured to select one of the plurality of operation plans for the operation behavior of the autonomous vehicle based on the sensor data and the mission guidance data at a certain time, and provide an intention decision based on the situation awareness data and the selected one of the plurality of operation plans. The system further includes an execution engine configured to provide control outputs to operating components based on the selected one of the plurality of operating schedules and in response to the intent decision. In this case, the algorithm for decision-making comprises a usage calculation system configured to calculate a total usage factor for each of the plurality of operating plans based on a plurality of behavior characteristics, wherein the usage calculation system is configured to select the one of the plurality of operating plans based on the total usage factor calculated for each of the plurality of operating plans, and an intention generation system configured to provide the intention decision, wherein the intention generation system comprises a probability calculator configured to calculate a series of probabilities associated with predefined possible results for the given decision torque based on the situational awareness characteristics and the selected one of the plurality of operating plans, wherein the total utilization factor is calculated based on the plurality of behavioral characteristics and based on a respective plurality of programmable weights selectively associated with the plurality of behavioral characteristics and as part of the mission line data provided via the user interfaces.BRIEF DESCRIPTION OF THE DRAWINGSFIG. 1 illustrates an example of an autonomous vehicle system. FIG. 2 illustrates an example of an operation plan controller. FIG. 3 illustrates an example of a usage calculation system for an algorithm for decision making. FIG. 4 illustrates an example of an intention generation system. FIG. 5 illustrates an example of controlling an autonomous vehicle.DETAILED DESCRIPTIONThe present disclosure relates generally to artificial intelligence systems, and more particularly to an autonomous vehicle control system. For example, an autonomous vehicle control system is implemented at least partially on a computer readable medium, for example a processor installed in an associated autonomous vehicle. For example, the autonomous vehicle may be configured as an unmanned aerial vehicle (UAV). The autonomous vehicle therefore includes on-board sensors configured to generate sensor data associated with a situational awareness of the autonomous vehicle, and further includes operating components associated with navigation and control of the autonomous vehicle (e.g., flaps, an engine, military equipment, or other operating components). The autonomous vehicle control system may therefore provide autonomous control of the autonomous vehicle based on receipt of the sensor data and mission guidance data (e.g., defining parameters of a given mission) and by providing output signals to the operating components.The autonomous vehicle control system includes an operation plan controller, a decision making algorithm, a usage calculation system, and an execution engine. The operation plan controller is configured to maintain predetermined operation plans each corresponding to a predetermined set of behavior characteristics of the autonomous vehicle based on the sensor data and the mission guidance data provided from, for example, a user interface. The usage calculation system is configured to calculate a total usage factor based on a plurality of behavioral characteristics. The decision making algorithm is configured to select one of the plurality of operation plans on the operation behavior of the autonomous vehicle based on the sensor data and the mission line data at a given time and provide an intention decision based on Situationsbewusstseinseigenschaften provided by the sensor data and the total utilization factor for a given decision torque. The execution engine is configured to provide the outputs to the operating components for navigation and control of the autonomous vehicle based on the selected one of the plurality of operating plans and in response to the intent decision at the given decision moment.FIG. 1 illustrates an example of an autonomous vehicle system 10. the autonomous vehicle system 10 includes an autonomous vehicle 12. If described herein, the term "autonomous vehicle" describes an unmanned vehicle operating in autonomous form such that the autonomous vehicle 12 is not remotely controlled or operated in a continuous manner, but instead continuously operates based on a programmed set of instructions that specify movement, movability, and execution of actions to achieve mission goals in response to sensor data associated with external stimuli. For example, the autonomous vehicle 12 may be configured as an unmanned aerial vehicle (UAV) operating in an autonomous, programmable manner for any of a variety of different purposes. The autonomous vehicle 12 includes an autonomous vehicle control system 14 that may be programmed such that the autonomous vehicle 12 may operate autonomously to achieve predetermined mission targets in response to inputs provided, for example, via sensor data and mission guidance data.In the example of FIG. 1, the autonomous vehicle 12 includes a series of on-board sensors 16 that can provide sensor input data SENS_IN to the autonomous vehicle control system 14. For example, the on-board sensors 16 may include optical sensors, one or more cameras, and / or other types of electro-optical imaging sensors (e.g., radar, lidar, or a combination thereof). The on-board sensors 16 may also include location and / or Situationsbewusstseinssensoren (e.g., a global navigation satellite system (GNSS) receiver). Therefore, the on-board sensors 16 may be configured to obtain situational awareness data provided as sensor input data SENS-IN to the autonomous vehicle control system 14. Additionally, the autonomous vehicle 12 may include operating components 18 corresponding to navigation and control devices for operating the autonomous vehicle 12 and achieving mission goals. For example, the operating components 18 may include navigation components (e.g., wings, bodies, and / or liftgates), an engine, military equipment, and / or other operating components. The autonomous vehicle control system 14 may provide control outputs OP_OUT to the operating components 18 to control the operating components 18. Therefore, the autonomous vehicle may operate based on providing the control outputs OP_OUT to the operating components 18 in response to receiving the sensor input data SENS_IN via the on-board sensors 16.The autonomous vehicle control system 14 may be configured as one or more processors 20 programmed to generate the control outputs OP_OUT in response to the sensor input data SENS_IN to control the autonomous vehicle 12. The processor or processors 20 may therefore execute programmable instructions stored, for example, on a memory (not shown). By way of example, the processors 20 forming the autonomous vehicle control system 14 may be programmed via a user interface 22 associated with the autonomous vehicle system 10. For example, the user interface 22 may be configured as a computer system or graphical user interface (GUI) accessible via a computer (e.g., via a network). For example, the user interface 22 may be configured to program the autonomous vehicle control system 14 to define and provide mission objectives and / or to provide limited or temporary control of the autonomous vehicle 12, for example, in response to an intervention request by the autonomous vehicle control system 14, as will be described in more detail herein. In the example of FIG. 1, the user interface 22 is shown providing mission line data CTRL (e.g., wirelessly) that may correspond to predetermined mission parameters 24 describing the mission definitions and destinations, for example including a predetermined navigation route, parameters for navigating the predetermined navigation route, at least one mission destination, and behaviors for reaching the mission destinations. The mission line data CTRL may also provide program data for programming behavioral characteristics and / or vehicle pilot signals to provide user intervention control, for example as described in more detail herein. Although the user interface 22 is described above as a computer system or GUI, in another example, the user interface 22 may be configured as at least one chip or at least one circuit board (e.g., printed circuit board (PCB)) installed in the autonomous vehicle control system 14, such that the user interface 22 may be preprogrammed with the mission control data CTRL and reached by the autonomous vehicle control system 14.In the example of FIG. 1, the processor or processors 20 may be programmed via mission control data CTRL to implement an operation plan controller 26, a decision making algorithm 28, and an execution engine 30. The operation plan controller 26 may control an operation plan associated with the autonomous vehicle 12, for example, according to a current behavior mode in which the autonomous vehicle 12 is operating. For example, the operation plan controller 26 may provide a plurality of selectable operation plans, each corresponding to a predetermined set of behavior characteristics of the autonomous vehicle 12. By way of example, the operation plan controller 26 may set the autonomous vehicle control system 14 to operate in a given operation plan with a given time duration based on the sensor input data SENS_IN and / or the mission guidance data CTRL provided by the user interface 22. As described in detail herein, the operation plan controller 26 may be configured to set a given operation plan based on the decision making algorithm 28 in response to a given intent decision, for example, at a given decision instant.As described herein, the term "intent decision" refers to a decision to be made by the decision making algorithm 28 that matches predetermined parameters associated with the control of the autonomous vehicle 12 and programmable behavior characteristics of the autonomous vehicle control system 14 to control the autonomous vehicle 12 in response to unexpected circumstances. As also described herein, the term "decision moment" refers to a given time and / or a set of circumstances that depend on unexpected and / or unscheduled external stimuli (e.g., provided via the sensor input data SENS_IN) that require a decision via the decision making algorithm 28 to specify the behavior of the autonomous vehicle 12.FIG. 2 illustrates an example of an operation plan controller 50. by way of example, the operation plan controller 50 may be embodied as hardware, software, firmware, or a combination thereof executable by the processor or processors 20. The operation plan controller 50 may correspond to the operation plan controller 26 in the example of FIG. 1. Therefore, in the following description of the example of FIG. 2, reference is made to the example of FIG. 1.The operation plan controller 50 may select an operation plan associated with the autonomous vehicle 12, for example, according to a current behavior mode in which the autonomous vehicle 12 is operating. In the example of FIG. 2, the selected behavioral mode is provided as a command CURR_PLN that may be configured to trigger one or more routines corresponding to the selected operational plan (e.g., in the autonomous vehicle controller 14 or in the operational plan controller 50 itself). The operation plan controller 50 includes a nominal plan 52, an acceleration plan 54, a caution plan 56, a stop plan 58, and a user request plan 60. the nominal plan 52 may be associated with a nominal operating behavior of the autonomous vehicle 12 and may be based on the mission guidance data CTRL. As an example, the nominal plan 52 may be a standard operational plan that the operational plan controller 50 sets as an operational plan for the autonomous vehicle control system 14 when all other systems are stable, such as during initialization (e.g., departure), completion (e.g., landing), and / or during mission defined by the mission parameters 24, such as lack of interference from unexpected and / or unscheduled external factors. By way of example, the mission control data CTRL may specify the external conditions as to when the autonomous vehicle control system 14 should be set in the nominal plan 52.The acceleration plan 54 may be related to an accelerated performance of the autonomous vehicle 12 versus the nominal performance of the nominal plan 52, and may be based on the mission control data CTRL. By way of example, the mission control data CTRL may specify when the autonomous vehicle control system 14 should be switched from the nominal plan 52 to the acceleration plan 54 based on external conditions or based on the mission parameters 24. For example, delays in mission determined by mission parameters 24 based on previous circumstances (e.g., operation in caution plan 56, as described in detail herein) may result in autonomous vehicle 12 being behind the schedule for one or more particular mission criteria defined by mission parameters 24. Therefore, the acceleration plan 54 may be implemented by the operation plan controller 50 for the autonomous vehicle control system 14 when all other systems are stable during mission defined by the mission parameters 24 without disturbances from unexpected and / or unscheduled external factors to recover time. As described herein, the acceleration plan 54 may be implemented in situations when the decision making algorithm 28 calculates that the use of an accelerated mission operation includes the use of an increased risk of the autonomous vehicle 12 or the completion of the mission goals.The caution plan 56 may be associated with reduced risk performance of the autonomous vehicle 12 over the nominal performance of the nominal plans 52, and may be based on the mission control data CTRL. By way of example, the mission control data CTRL may specify when the autonomous vehicle control system 14 should be set based on external conditions, for example perceived hazards and / or threats based on the sensor input data SENS_IN from the nominal plan 52 into the caution plan 56. For example, upon detection of hazardous environmental conditions, an external obstacle, or an impending or detected threat requiring an avoidance maneuver, the operation plan controller 50 may transition or be commanded to the autonomous vehicle control system 14 to the caution mode 56. Therefore, the autonomous vehicle control system 14 may specify a lower speed for the autonomous vehicle 12, for example to provide the ability to reduce risks by providing more time for reaction and / or maneuvering. Alternatively, the caution plan 56 may force a deviation from the predetermined navigation trajectory associated with reaching the mission destinations defined by the mission parameters 24 while still maintaining a fast speed for the autonomous vehicle 12. For example, the autonomous vehicle control system 14 may decide that the operation of the autonomous vehicle 12 is too risky in a predetermined navigation history defined by the mission parameters 24 in the nominal plan 52, as described in more detail herein, and may therefore instruct the operation plan controller 50 to set the caution plan 56 as the current operation plan CURR_PLN.Analogously to above, the stop plan 58 may be associated with interrupted performance of the autonomous vehicle 12, for example, in response to detecting an imminent collision with an obstacle or other driving vehicle. By way of example, the stop plan 58 may be associated with an autonomous ground vehicle, or an autonomous aircraft that is prepared or landed at the launch. Finally, the user request plan 60 may correspond to a situation where the autonomous vehicle control system 14 transmits a request for instructions from the user interface 22. For example, in response to the decision making algorithm 28 determining an approximately equivalent usage or probability in determining a given view decision at a respective decision instant, the autonomous vehicle 12 may be switched to the user request plan 60. By way of example, the user request plan 60 may be associated with another operating plan of the operating plan controller 50, for example the nominal plan 52, the caution plan 56, or the stop plan 58, such that the autonomous vehicle 12 may continue to operate in a predetermined manner according to the selected operating plan CURR_PLN, while awaiting additional instructions as specified by the user request plan 60. Further, the operation plan controller 50 may also include at least one additional plan 62 that may specify a respective, at least one additional behavior mode in which the autonomous vehicle 12 may operate. Therefore, the operation plan controller 50 is not limited to providing the current plan CURR_PLN as one of the plans of the nominal plan 52, the acceleration plan 54, the caution plan 56, the stop plan 58, and the user request 60.Referring again to the example of FIG. 1, the decision making algorithm 28 includes a usage calculation system 32 and an intent generation system 34. the usage calculation system is configured to calculate an overall usage factor (TUF) for each of the operational plans (e.g., the nominal plan 52, the acceleration plan 54, the caution plan 56, the stop plan 58, the user request plan 60, and / or the additional plan 62) maintained by the operational plan controller 26. The calculation of the TUF may be based on performance characteristics that may correspond to characteristics of the autonomous vehicle 12, user inputs provided via the user interface 22, avoidance of obstacles (e.g., external objects, e.g., another aircraft, ground characteristics, buildings, etc.), integrity of the sensors 16, and / or predetermined performance characteristics of the operating components 18 of the autonomous vehicle 12. Therefore, the usage calculation system 32 may be configured to instruct the operation plan controller 26 to select the operation plan based on the TUF calculated for each of the operation plans (e.g., based on the highest TUF).FIG. 3 illustrates an example of a usage calculation system 100 for a decision making algorithm (e.g., decision making algorithm 28). As a result, the usage computation system 100 may be implemented as hardware, software, firmware, or a combination thereof executable by the processor or processors 20. The usage calculation system 100 may correspond to the usage calculation system 32 in the example of FIG. 1. Therefore, in the following description of the example of FIG. 3, reference is made to FIG. 1.The usage calculation system 100 may implement a plurality of predetermined behavior factors to calculate the TUF that specifies the operating behavior of the autonomous vehicle control system 14. In the example of FIG. 3, the behavioral factors include performance utilization factors 102 associated with performance characteristics of the autonomous vehicle 12 and / or characteristics of the mission defined by the mission parameters 24. By way of example, the performance usage factors 102 may include a mission-related schedule, for example defined by the mission parameters 24, and include capabilities of the autonomous vehicle 12, for example, speed, handling, maneuverability, responsiveness, turn circle, and / or other navigation characteristics (for example, six-degree-of-freedom movement), changes in performance based on a loading of military equipment, and / or a plurality of other performance characteristics of the autonomous vehicle 12. the performance factors also include operator usage factors 104 related to the mission guidance data CTRL and availability of operator inputs to control the autonomous vehicle 12, For example, regarding a current speed of the autonomous vehicle 12, as well as a level of detail required to provide user inputs (e.g., in response to requests that may be provided in the user request plan 60).The behavioral factors may also include avoidance safety utility factors 106 associated with consequences of an autonomous vehicle collision. The avoidance safety utility factors 106 may take into account the speed of the autonomous vehicle 12 versus a type of potential obstacle with which the autonomous vehicle 12 may have an imminent collision, for example, based on an evaluation of static objects (e.g., the ground) versus dynamic objects (e.g., other vehicles, threats, etc.). The behavioral factors may include integrity safety utility factors 108 associated with an impact of environmental conditions on the on-board sensors 16 and operating components 18 associated with the autonomous vehicle 12. For example, the integrity safety utility factors 108 may be related to the effects of weather on the on-board sensors 16 and operating components 18, such as the effects of weather that obscures the on-board sensors 16 and operating components 18, the effects of rain on the traction of tires on an airport concrete runway, the effect of turbulence on the operating components 18, the effect of clouds on the sensors 16, etc.In the example of FIG. 3, the usage calculation system 100 also includes programmable weights, respectively, that are selectively associated with the plurality of behavioral characteristics. By way of example, each of the programmable weights may be provided as part of mission line data CTRL provided via the user interface 22. The programmable weights include performance usage factors 110 ("PU WEIGHTS") that may be associated with the performance usage factors 102, operator usage weights 112 ("OU WEIGHTS") that may be associated with operator usage factors 104, avoidance safety weights 114 ("ASU WEIGHTS") that may be associated with the avoidance safety usage factors 106, and integrity safety weights 116 ("ISU WEIGHTS") that may be associated with the integrity safety usage factors 108. Each of the performance usage weights 110, operator usage weights 112, avoidance safety usage weights 114, and integrity safety usage weights 116 may include one or more weighted multiplicative factors that may emphasize or attenuate certain of the behavioral factors at a given time (e.g., in each of the performance usage factors 102, the operator usage factors 104, the avoidance safety usage factors 106, and integrity safety usage factors 108). Selection of the performance usage weights 110, the operator usage weights 112, the avoidance safety usage factors 114, and / or the integrity safety usage factors 116 may be based on, for example, mission line data CTRL at various stages of a given mission defined by the mission parameters 24. Therefore, a user may implement the user interface 22 to adjust the weights of the respective performance usage weights 110, the operator usage weights 112, the avoidance safety usage factors 114, and / or the integrity safety usage factors 116 at various stages of the mission defined by the mission parameters 24 in optional and programmable form to specify the operational plan of the autonomous vehicle control system 14 for operation of the autonomous vehicle 12.In the example of FIG. 3, the weighted performance usage factors 102, represented as WPU, the weighted operator usage factors 104, represented as WOU, the weighted avoidance security usage factors 106, represented as WASU, and the weighted integrity security factors 108, represented as WISU, are provided to a TUF calculation component 118. The TUF calculation component 118 is configured to calculate the TUF for any given one of the operational plans (e.g., the nominal plan 52, the acceleration plan 54, the caution plan 56, the stop plan 58, and / or the user request plan 60). In addition, the TUF calculation component 118 may obtain situational awareness data via the sensor input data SENS_IN, such that the TUF may be modified based on external considerations (e.g., weather, threats, potential obstacles, etc.). Therefore, the TUF calculation component 118 may calculate the TUF for each of the operation plans, and provide the calculated TUF for each of the operation plans to the operation plan controller 26 for selection of a given one of the operation plans at the given time.FIG. 4 illustrates an example of an intent generation system 150. By way of example, intent generation system 150 may be embodied as hardware, software, firmware, or a combination thereof executable by processors 20. The intent generation system 150 is illustrated in the example of FIG. 4 as a motion intent generation system to provide a decision making capability in the context of the motion of the autonomous vehicle 12, for example, to allow the autonomous vehicle 12 to move on an airport runway. By way of example, the intention generation system 150 is shown as a collision avoidance intention generator to provide an intention decision to operate the autonomous vehicle 12 to avoid a collision of the autonomous vehicle 12 with a possible obstacle (e.g., another aircraft on the runway). The intention generation system 150 may correspond to the intention generation system 34 in the example of FIG. 1. Therefore, in the following description of the example of FIG. 4, reference is made to FIG. 1.The intention generation system 150 comprises an intention generator 152 which is configured to provide the intention decision for a given decision torque. The intent generator 152 is shown to include a probability calculator 154 configured to calculate a set of probabilities in association with predetermined possible results for a given decision moment. For example, the set of probabilities may include a probability of collision with another aircraft approaching the same intersection of the runway as the autonomous vehicle 12. Therefore, the possible action sequences for the autonomous vehicle 12 could be: continue to travel at the same speed, slow, accelerate, stop, turn left, turn right, straight off, etc. Therefore, the intent creator 152 is configured to provide an intent decision based on the set of probabilities to provide the intent decision based on a most acceptable relative probability of the set of probabilities. In the example of FIG. 4, the probability calculator 154 calculates the set of probabilities based on the Situationsbewusstseinseigenschaften provided via the sensor input data SENS_IN, and the selected operation plan shown as "CURR_PLN" in the example of FIG. 4. The probabilities may be calculated by the probability calculator 154 based on any of several algorithms, such as Bayesian network, flow plots, and / or a variety of other decision theory calculations.The situation awareness characteristics may be provided via the sensor input data SENS_IN and are shown to include a relative distance 156, a relative speed 158, a relative trajectory 160, and environmental considerations 162. The relative distance, relative speed 158, and relative trajectory 160 may correspond to the respective motion characteristics of the autonomous vehicle 12 from one or more potential obstacles, such as another aircraft on the runway (e.g., at an intersection of the runway). The relative distance 156 may therefore correspond to a relative distance between the autonomous vehicle 12 and the potential obstacle, for example, with respect to the intersection or with respect to each other. The relative speed 158 may thus correspond to a relative speed between the autonomous vehicle 12 and the potential obstacle to each other or relative to the intersection. The relative trajectory 160 may thus correspond to a relative direction of movement between the autonomous vehicle 12 and the potential obstacle, for example, it could indicate an overlap of movement and thus a potential collision. The environmental considerations 162 may include characteristics of the environment in which the autonomous vehicle 12 is operating. For example, rain, snow, or ice on the roller coast may degrade the performance of the autonomous vehicle 12 on the roller coast, and thus the likelihood of a collision of the autonomous vehicle 12 and the potential obstacle at a given relative distance 156, relative speed 158, and / or relative trajectory may increase.As described above, upon calculation of the set of probabilities of the possible results of the decision moment via the probability calculator 154, the intent generator 152 may provide the view decision corresponding to a most preferred, likely result for a given action flow. Referring again to FIG. 1, the decision making algorithm 28 may communicate the intent decision to the execution engine 30. The execution engine 30 may be configured to execute the physical results of the intent decision by generating an appropriate amount of outputs, which may collectively correspond to the control outputs OP_OUT. Therefore, the control outputs OP_OUT may be provided to the operating components 18 of the autonomous vehicle 12 for making the intent decision. For example, the probability calculator 154 could calculate the probability of a collision with the other aircraft approaching the runway as described above for each of the action sequences (e.g., stop, slow, accelerate, stop, turn left, turn right, turn straight off, etc.). Thus, as an example, the intent generator 152 could determine that the most preferred course of action is to turn left at the intersection of the roller bed based on the calculated probabilities for the autonomous vehicle 12. Therefore, the intention generator 152 may provide the corresponding intention decision to the execution engine 30 to generate the corresponding control outputs OP_OUT to actuate the wheels of the autonomous vehicle 12 (the wheel or wheels corresponding to the appropriate operating components 18) to perform a left turn of the autonomous vehicle 12 at the appropriate time (e.g., as provided by the sensor input data SENS_IN). Accordingly, the autonomous vehicle 12 may operate in a manner that substantially reduces the likelihood of a collision with the potential obstacle based on the determined intent decision.The present description of the intention generation system 150 providing an intention decision making for the autonomous vehicle 12 will be given by way of example. Therefore, intent generation system 150 may be configured to generate intent decisions for any of various other situations and scenarios requiring intent decisions based on external stimuli and / or situational awareness. For example, the intent generation system 150 may be implemented to provide intent decisions during the mission defined by the mission parameters 24, for example, to decide to deviate from a predetermined navigation history in response to unexpected circumstances (e.g., threats, weather conditions, etc.). Additionally, intent generation system 150 may provide navigation intent decisions in response to a deviation from a predetermined navigation history, to attempt an alternate route to fulfil the mission, and / or to decide to abort the mission. Accordingly, the intent generation system 150 may be implemented by the decision making algorithm 28 in various forms to provide autonomous control of the autonomous vehicle 12.In view of the above structural and functional features, a method according to various aspects of the present disclosure will be better understood with reference to FIG. 5. Although for convenience of explanation, the method of FIG. 5 is described and illustrated as being performed in series, it should be appreciated and understood that the present disclosure is not limited to the illustrated order because some aspects according to the present disclosure could operate in different orders and / or concurrently with other aspects illustrated and described herein. In addition, it is conceivable that not all the features illustrated are required to implement a method according to one aspect of the present disclosure.FIG. 5 illustrates a method 200 for controlling an autonomous vehicle (e.g., the autonomous vehicle 12). At 202, mission guidance data (e.g., mission guidance data CTRL) is provided to an autonomous vehicle control system (e.g., autonomous vehicle control system 14) associated with the autonomous vehicle via a user interface (e.g., user interface 22). At 204, situational awareness data associated with the autonomous vehicle is generated in response to receiving the sensor data (e.g., sensor data SENS_IN) provided by on-board sensors (e.g., on-board sensors 16). At 206, one of a plurality of operation plans (e.g., operation plans 52, 54, 56, 58, 60, 62) each corresponding to a predetermined set of behavior characteristics of the autonomous vehicle is selected based on the situational awareness data and the mission guidance data. At 208, control outputs (e.g., the control outputs OP_OUT) are provided to operating components (e.g., the operating components 18) associated with the autonomous vehicle for navigation and control of the autonomous vehicle in response to the sensor data and based on the selected one of the plurality of operating plans.Examples of the disclosure have been described above. It is, of course, not possible to describe any conceivable combination of components or methods for purposes of describing the disclosure, but one skilled in the art will recognize that many other combinations and permutations of the disclosure are possible. Accordingly, the disclosure is intended to cover all such changes, modifications and variations as fall within the scope of this application, including the appended claims.

Claims

An autonomous vehicle control system (10) operating on a computer readable medium, the autonomous vehicle control system (10) comprising: an operation plan controller (26, 50) configured to maintain a plurality of operation plans (52, 54, 56, 58, 60, 62) each corresponding to a predetermined set of behavioral characteristics of an associated autonomous vehicle (12) based on Situationsbewusstseinsdaten provided via on-board sensors (16) of the autonomous vehicle (12), and mission guidance data provided from a user interface (22); an algorithm for decision making (28) configured to select one of the plurality of operation plans (52, 54, 56, 58, 60, 62) for the operation behavior of the autonomous vehicle (12) based on the situation awareness data and the mission guidance data at a particular time and provide an intention decision based on the situation awareness data and the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62); and an execution engine (30) configured to provide control outputs to operation components (18) associated with the autonomous vehicle (12) for navigation and control of the autonomous vehicle (12) based on the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62) and in response to the intention decision, wherein the algorithm for decision making (28) includes a usage calculation system (32, 100), An apparatus configured to calculate a total utilization factor for each of the plurality of operating plans (52, 54, 56, 58, 60, 62) based on a plurality of behavioral characteristics, wherein the utilization calculation system (32, 100) is configured to select the one of the plurality of operating plans (52, 54, 56, 58, 60, 62) based on the total utilization factor calculated for each of the plurality of operating plans (52, 54, 56, 58, 60, 62), wherein the total utilization factor is calculated based on the plurality of behavioral characteristics and based on a respective plurality of programmable weights that are selectively associated with the plurality of behavioral characteristics and provided as part of the mission line data provided via the user interface (22).The system (10) of claim 1, wherein the decision making algorithm (28) further comprises an intent generation system (34, 150) configured to provide the intent decision, the intent generation system (34, 150) comprising a probability calculator (154) configured to calculate a set of probabilities associated with predetermined possible results for the given decision moment based on the situational awareness data and the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62).The system (10) of claim 1, wherein the plurality of behavioral characteristics comprises at least one of: performance usage factors (102) associated with performance characteristics of the autonomous vehicle (12); operator usage factors (104) associated with the mission guidance data and availability of the operator inputs to control the autonomous vehicle (12); avoidance safety usage factors (106) associated with a collision of the autonomous vehicle (12); and integrity safety usage factors (116) associated with an impact of environmental conditions on the on-board sensors (16) and operating components (18) associated with the autonomous vehicle (12).The system (10) of claim 1, wherein the mission guidance data comprises mission parameters (24) describing mission definitions and goals, wherein the usage calculation system (32, 100) is configured to select the one of the plurality of operational plans (52, 54, 56, 58, 60, 62) based on the mission parameters (24) and based on the total usage factor calculated for each of the plurality of operational plans (52, 54, 56, 58, 60, 62).The system (10) of claim 1, wherein the plurality of operational plans (52, 54, 56, 58, 60, 62) include at least a nominal plan associated with a nominal performance of the autonomous vehicle (12) and the mission guidance data; an acceleration plan (54) associated with an accelerated performance of the autonomous vehicle (12) versus the nominal performance and based on the mission guidance data; a caution plan (56) associated with a reduced risk performance of the autonomous vehicle (12) versus the nominal performance and based on the mission guidance data; a stop plan (58) associated with a aborted performance of the autonomous vehicle (12); and a user request plan (60) in which the autonomous vehicle (12) transmits a request for instructions from the user interface (22).The system (10) of claim 1, wherein the decision making algorithm (28) comprises a collision avoidance algorithm configured to provide the intent decision to avoid a collision of the autonomous vehicle (12) with a potential obstacle.The system (10) of claim 6, wherein the collision avoidance algorithm is configured to provide the intent decision to avoid the collision of the autonomous vehicle (12) with the potential obstacle based on at least one of: a relative distance of the autonomous vehicle (12) and the potential obstacle; a relative speed (158) of the autonomous vehicle (12) and the potential obstacle; a relative trajectory (160) of the autonomous vehicle (12) and the potential obstacle; and environmental conditions associated with an environment of the autonomous vehicle (12).The autonomous vehicle (12) comprising the autonomous vehicle control system (10) of claim 1, wherein the autonomous vehicle (12) further comprises: the on-board sensors (16) configured to generate the sensor data; and the operating components (18) configured to provide navigation and control of the autonomous vehicle (12).A method of controlling an autonomous vehicle (12), the method comprising: providing mission guidance data to an autonomous vehicle control system (10) associated with the autonomous vehicle (12) via a user interface (22); generating situational awareness data associated with the autonomous vehicle (12) in response to receiving sensor data provided by on-board sensors (16); selecting one of a plurality of operating plans (52, 54, 56, 58, 60, 62) each corresponding to a predetermined set of behavioral characteristics of the autonomous vehicle (12) based on the situational awareness data and the mission guidance data; Providing control outputs to operating components (18) associated with the autonomous vehicle (12) for navigation and control of the autonomous vehicle (12) in response to the sensor data and based on the selected one of the plurality of operating plans (52, 54, 56, 58, 60, 62), the method further comprising calculating a total utilization factor for each of the plurality of operating plans (52, 54, 56, 58, 60, 62) based on a plurality of behavioral characteristics, wherein selecting the one of the plurality of operating plans (52, 54, 56, 58, 60, 62) comprises selecting the one of the plurality of operating plans (52, 54, 56, 58, 60, 62) based on the total utilization factor calculated for each of the plurality of operating plans (52, 54, 56, 58, 60, 62), wherein calculating the total utilization factor comprises providing a respective plurality of programmable weights, which are selectively assigned to the plurality of behavioral characteristics via the mission line data.The method of claim 9, wherein providing the mission guidance data comprises providing mission parameters (24) describing mission definitions and goals, wherein selecting the one of the plurality of operational plans (52, 54, 56, 58, 60, 62) comprises selecting the one of the plurality of operational plans (52, 54, 56, 58, 60, 62) based on the mission parameters (24) and based on the total utilization factor calculated for each of the plurality of operational plans (52, 54, 56, 58, 60, 62).The method of claim 9, further comprising providing an intent decision at a given decision torque based on the sensor data and based on the selected one of the plurality of operating plans (52, 54, 56, 58, 60, 62), wherein providing the control outputs further comprises providing the control outputs to the operating components (18) associated with the autonomous vehicle (12) in response to the intent decision and based on the selected one of the plurality of operating plans (52, 54, 56, 58, 60, 62).The method of claim 11, further comprising calculating a set of probabilities associated with predetermined possible results for the given decision moment based on the situational awareness data and the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62), wherein providing the intent decision comprises providing the intent decision based on a most acceptable relative probability of the set of probabilities.The method of claim 11, wherein generating the situational awareness data comprises: obtaining a relative distance between the autonomous vehicle (12) and a potential obstacle; obtaining a relative velocity (158) between the autonomous vehicle (12) and the potential obstacle; obtaining a relative trajectory (160) between the autonomous vehicle (12) and the potential obstacle; and obtaining environmental considerations associated with an environment of the autonomous vehicle (12); wherein calculating the set of probabilities comprises calculating the set of probabilities associated with predetermined possible results for the given decision torque based on the relative distance, the relative velocity (158), the relative trajectory, and the environmental conditions and based on the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62).An autonomous vehicle, comprising: on-board sensors (16) configured to generate situational awareness data associated with situational awareness conditions of the autonomous vehicle (12); operating components (18) configured to provide navigation and control of the autonomous vehicle (12) in response to control outputs; and an autonomous vehicle control system (10) operating on a computer readable medium, the autonomous vehicle control system (10) comprising: an operation plan controller (26, 50) configured to maintain a plurality of operation plans, each corresponding to a predetermined set of behavior characteristics of an associated autonomous vehicle (12), based on the situational awareness data and the mission guidance data; an algorithm for decision making configured to select one of the plurality of operation plans (52, 54, 56, 58, 60, 62) for the operation behavior of the autonomous vehicle (12) based on the sensor data and the mission guidance data at a certain time and provide an intention decision based on the situation awareness data and based on the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62); and an execution engine (30) configured to provide control outputs to operation components (18) based on the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62) and in response to the intention decision, wherein the algorithm for decision making (28) comprises: a usage calculation system (32, 100) configured to provide a total usage factor for each of the plurality of operation plans (52, 54, 56, 58, 60, 62), 62) based on a plurality of behavior characteristics, wherein the usage calculation system (32, 100) is configured to select the one of the plurality of operation plans (52, 54, 56, 58, 60, 62) based on the total usage factor calculated for each of the plurality of operation plans (52, 54, 56, 58, 60, 62), and an intention generation system (34, 150) configured to provide the intention decision, wherein the intention generation system (34, 150) comprises a probability calculator configured to calculate a series of probabilities associated with predetermined possible results for the given decision torque based on the situational awareness characteristics and the selected one of the plurality of operation plans (52, 54, 56, 58, 60, 62), wherein the total usage factor is calculated based on the plurality of behavior characteristics and based on a respective plurality of programmable weights, which are selectively associated with the plurality of behavioral characteristics and as part of the mission line data provided via the user interfaces (22).

Images