Vehicle dynamics and powertrain control system and method using multi-time domain optimization

Abstract

Use of multi-time domain optimization of vehicle dynamics and powertrain control of a vehicle is provided. A long time domain optimization is performed for a trip of the vehicle and an optimal value function is determined. Data from one or more components of the vehicle is received from powertrain and / or connectivity features. A short time domain optimization is performed for the trip using a rollout algorithm, the optimal value function, and the received data. Operation of the vehicle is adjusted using results of the short time domain optimization.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 62 / 931,293, filed November 6, 2019, entitled “METHOD FOR VEHICLE DYNAMICS AND POWERTRAIN CONTROL USINGMULTIPLE HORIZON OPTIMIZATION,” the disclosure of which is expressly incorporated herein by reference in its entirety.

[0003] Government Support Statement

[0004] This invention was completed with government support and was granted designation DE-AR000794 by the Department of Energy's Advanced Research Projects Agency. The government holds certain rights to this invention. Background Technology

[0005] The goal of formulating nonlinear dynamic optimization problems in the spatial domain is to minimize a vehicle's fuel consumption over the entire journey. One advantage of formulating spatial trajectories is that it is well-suited for incorporating route-related information, such as posted speed limit signs, traffic lights, and stop signs, whose positions along the route remain fixed. In contrast, incorporating such route features into time-domain problems would be quite tedious.

[0006] It is with regard to these and other considerations that the various aspects and implementation schemes of this disclosure are presented. Summary of the Invention

[0007] The systems and methods described herein eliminate the drawbacks associated with previous systems and methods. Certain aspects of this disclosure relate to vehicle dynamics and powertrain control using multi-time-domain optimization.

[0008] In one embodiment, a method for applying multi-time-domain optimization to vehicle dynamics and powertrain control is provided. The method includes: performing long-time-domain optimization on the vehicle's travel; determining an optimal value function based on the long-time-domain optimization; receiving data from one or more components of the vehicle, from one or more powertrain or connectivity features; performing short-time-domain optimization on the travel using a rollout algorithm, the optimal value function, and the received data; and adjusting the vehicle's operation using the results of the short-time-domain optimization.

[0009] In one embodiment, a method is provided for using multi-time-domain optimization for vehicle dynamics and powertrain control. The method includes: performing initial optimization of the vehicle's journey at the start of the journey or during the journey; determining an optimal value function based on the initial optimization; storing the optimal value function in vehicle-associated memory; and performing short-time-domain optimization of the journey using updated route information obtained from at least one of a vehicle-to-infrastructure / vehicle-to-vehicle (V2I / V2V) module or a cloud-based service provider.

[0010] In one embodiment, a system for a vehicle is provided. The system includes: a long-time domain optimization module configured to perform long-time domain optimization on a vehicle's trip; a deterministic optimization module configured to determine an optimal value function; and a short-time domain optimization module configured to perform short-time domain optimization on the trip using a rollout algorithm, the optimal value function, and data from one or more powertrain or connectivity features of one or more components of the vehicle.

[0011] This summary is provided to introduce, in a simplified form, the concept choices further described below in the detailed embodiments. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. Attached Figure Description

[0012] The foregoing description of the invention and the following detailed description of exemplary embodiments can be better understood when read in conjunction with the accompanying drawings. Exemplary structures of the embodiments are shown in the drawings to illustrate the embodiments; however, the embodiments are not limited to the specific methods and means disclosed. In the drawings:

[0013] Figure 1 This is an illustration of an exemplary environment for vehicle dynamics and powertrain control systems and methods using multi-time-domain optimization;

[0014] Figure 2 It is the operational flow of an implementation method for applying multi-time-domain optimization to vehicle dynamics and powertrain control;

[0015] Figure 3 This is the operational flow of another implementation of a method for applying multi-time-domain optimization to vehicle dynamics and powertrain control;

[0016] Figure 4 This is a schematic diagram illustrating the application of multi-time-domain optimization to various aspects of vehicle dynamics and powertrain control; and

[0017] Figure 5 An exemplary computing environment is shown, in which exemplary implementation schemes and aspects can be implemented. Detailed Implementation

[0018] This specification provides examples that are not intended to limit the scope of the appended claims. The drawings generally indicate features of the examples, and it should be understood and appreciated that the same reference numerals are used to refer to the same elements. References in the specification to “one embodiment,” “an embodiment,” or “an exemplary embodiment” mean that a particular feature, structure, or characteristic described is included in at least one embodiment described herein, but do not mean that such feature, structure, or characteristic exists in all embodiments described herein.

[0019] In some aspects, the present invention relates to vehicle dynamics and powertrain control systems and methods using multi-horizon optimization.

[0020] Figure 1 This is an illustration of an exemplary environment 100 using a multi-time-domain optimized vehicle dynamics and powertrain control system and method. The vehicle 110 includes an automotive powertrain 120 with an electronic control unit (ECU), an optional vehicle-to-the-world (V2X) module 130, an engine 140, a hybrid electric drive system 150, and a vehicle speed control device 160 (e.g., cruise control, adaptive cruise control, etc.).

[0021] Vehicle 110 further includes a long-time-domain optimization module 170, a short-time-domain optimization module 173, an optimization algorithm (based on back induction, such as dynamic programming (DP) or stochastic dynamic programming (SDP)) 175, and a rollout algorithm 180. A processor 185 (such as that included within a computing device) may also be included in vehicle 110. Processor 185 may perform some or all of the operations further described herein, depending on the implementation.

[0022] The long-term optimization module 170, the short-term optimization module 173, the back-induction optimization algorithm 175, the rollout algorithm 180, and the processor 185 can all be implemented using various computing devices. The vehicle powertrain 120 with an ECU, the optional V2X module 130, the engine 140, the hybrid electric drive system 150, and the vehicle speed control device 160 can also be implemented using one or more of various computing devices. In some embodiments, the computing device can be implemented (e.g., embodied in) the vehicle 110. Suitable computing devices are... Figure 5 The device shown is a computing device 500.

[0023] Multi-time-domain optimization methods for vehicle dynamics and powertrain control (VD&PT) are described as leveraging connectivity and automation to predict the impact of future driving conditions. As further described herein, it is envisioned that long-term time-domain optimization can be performed at the start of a trip and / or during the trip, depending on the implementation. Thus, for example, long-term time-domain optimization can be computed or recomputed during the trip (e.g., if route information changes during the trip). Alternatively or additionally, long-term time-domain optimization can be performed for multiple trips simultaneously, and this information can be stored. In some implementations, a trip can be considered as an extended segment of a route that can be pre-computed prior to trip execution.

[0024] The aspects described herein are applied to the optimization of automotive powertrains characterized by an ECU that monitors engine operation, a hybrid electric drive system, and vehicle speed control. Vehicles may be equipped with a V2X module that provides features such as GPS positioning, navigation systems, and Dedicated Short-Range Communication (DSRC). The technologies and aspects described herein significantly improve the fuel economy of such vehicles by combining and optimizing the various contributing powertrain and connectivity features.

[0025] Figure 2 This describes the operational flow of an implementation of a method 200 for applying multi-time-domain optimization to vehicle dynamics and powertrain control. Also related to... Figure 3 Other aspects and details are described below. Method 200 can be implemented in environment 100, including vehicle 110.

[0026] At point 210, before vehicle 110 begins its journey (or at one or more times during the journey, depending on the implementation), long-term optimization can be performed on initial values ​​and available data at that time (such as route information, posted speed limit signs, traffic lights, and stop signs). In this way, the optimal value function can be determined. Long-term optimization can be performed by long-term optimization module 170.

[0027] At 220, the value function can be stored in a memory associated with, for example, the vehicle 110 or one of the computing devices or vehicle components of the vehicle 110 (e.g., the vehicle powertrain 120 with an ECU, V2X module 130, engine 140, hybrid electric drive system 150, vehicle speed control device 160, long-time domain optimization module 170, short-time domain optimization module 173, back-induction optimization algorithm 175, rollout algorithm 180, processor 185).

[0028] At point 230, as vehicle 110 moves along its journey (i.e., after the start of the journey and during the journey), data from one or more of the vehicle's various components (e.g., the powertrain 120 with an ECU, the V2X module 130, the engine 140, the hybrid electric drive system 150, and the vehicle speed control device 160) is received from one or more powertrain and / or connectivity features. Exemplary features include, but are not limited to, traffic conditions, current powertrain and vehicle operating status (of vehicle 110), and V2X information. Data may be received at processor 185 or other computing devices, depending on the implementation.

[0029] At 240, for example, short-time optimization is performed using short-time optimization module 173, employing rollout algorithm 180 (which combines short-time optimization module 173 with long-time optimization module 170), the optimal value function, and data from one or more powertrain and / or connectivity features. Short-time optimization module 173 solves using back-inductive optimization algorithm 175.

[0030] At point 250, the results of short-time domain optimization can be used to adjust the operational aspects of vehicle 110 during the journey.

[0031] Figure 3 This is the operational flow of another implementation of method 300 for applying multi-time-domain optimization to vehicle dynamics and powertrain control. Method 300 can be implemented in environment 100 including vehicle 110.

[0032] At point 310, at the start of the trip (or at one or more times during the trip, depending on the implementation), long-term optimization is performed, and a value function is computed for the entire trip (or the remainder of the trip, or one or more segments, portions, or routes of the trip, depending on the implementation). Long-term optimization can be performed by long-term optimization module 170. Therefore, initial optimization is performed at the start of the trip (or at one or more times during the trip, depending on the implementation). Route information (including speed limits, available traffic conditions, and gradients of the entire planned route) is fed into the long-term optimization using data from cloud-based service providers (e.g., TomTom, Waze, etc.) and smart digital maps (containing, for example, speed limits and elevation data). The optimal value function is used to provide an approximate optimized trajectory for vehicle speed and powertrain control setpoints along the entire route of the trip. For example, one or more of various back-inductive numerical methods (such as DP or SDP) can be used to solve the long-term optimization problem, but this is not intended to be limiting.

[0033] At 320, the value function can be stored in a memory associated with, for example, the vehicle 110 or one of the computing devices or vehicle components of the vehicle 110 (e.g., the vehicle powertrain 120 with an ECU, V2X module 130, engine 140, hybrid electric drive system 150, vehicle speed control device 160, long-time domain optimization module 170, short-time domain optimization module 173, back-induction optimization algorithm 175, rollout algorithm 180, processor 185).

[0034] If route information and / or events occurring along the route are variable or uncertain, the optimization needs to be rerun with updated information to reflect these changes. For online use, periodically performing full route (or remaining route) optimization becomes computationally impractical given limited onboard computing and memory resources. This is the motivation for transforming the long-time domain problem into a short (e.g., rolling) time domain optimization control problem, which is solved using back induction and rollout algorithms.

[0035] At position 330, for N H Long-term optimization is rerun, starting from the j-th grid point along the route (where N... H (Significantly shorter than the rest of the route). The stage cost (or operating cost) of short-time domain optimization contains the same terms as long-time domain optimization and uses the value function in memory as the terminal cost. The constraints fed to this short-time domain dynamic optimization contain updated route information obtained from vehicle-to-infrastructure / vehicle-to-vehicle (V2I / V2V) modules, cloud-based service providers, and Dedicated Short-Range Communication (DSRC) units.

[0036] At position 340, N H The time-domain optimization problem is solved in reverse using the rollout algorithm, starting from the terminal stage ({j+Nth) in the current scrolling time domain. H The process starts from the j-th grid point and continues until the initial stage (the j-th grid point).

[0037] At 350, the obtained optimal strategy is then applied at the j-th grid point to transition the system to the {j+1}-th grid point.

[0038] At position 360, at the {j+1}th grid point, the same process is recursively applied to solve for N. H Time domain issue.

[0039] Consider long-time dynamic optimization problems, such as those encountered in full-route optimization. As mentioned earlier, given the limited available onboard computing resources and the variable conditions encountered along the way, this long-time optimization must be transformed into a short-time problem.

[0040] The rollout algorithm is a value space approximation method that utilizes the cost function of some known suboptimal / heuristic policies (called the base policy or base heuristic). Under appropriate assumptions, it can be proven that if the base heuristic produces a feasible solution, then the rollout algorithm also produces a feasible solution at a cost no less than that corresponding to the base heuristic. This is called cost improvement of the rollout policy, and this result can be proven using mathematical induction. If the base policy is chosen as the reference DP policy, then the cost improvement guarantees that the implemented online solution is no worse than that reference. For the cost improvement to be effective, it is important that the base heuristic and the rollout policy are computed on the same set of constraints. Cost improvement is relevant in the context of considering real-time eco-driving problems because the rollout algorithm is inherently robust to parameter uncertainties and modeling errors encountered along the way.

[0041] In powertrain control, considering traffic conditions and downstream road conditions, the terminal cost in the powertrain optimization problem can be determined through specific heuristics. For example, the terminal cost can be considered as the optimal cost (called the cost function or value function) incurred from the current state (i.e., the terminal state of the current rolling time-domain problem) to reach the destination under no-traffic conditions. Subsequently, the powertrain optimizer can periodically solve the resulting dynamic optimization problem to ensure that all key constraints are satisfied under updated operating conditions.

[0042] One advantage of the developed rollout algorithm is that the optimal solution is updated periodically in response to changing route conditions. Furthermore, the reduction in computational effort for short-time domain optimization is attractive while achieving near-optimal results. The cost-improving properties of the rollout algorithm guarantee the expected performance of the final solution, especially when applied to real-world problems involving uncertainty. Another advantage is that these techniques can still operate even without V2X communication (because the basic heuristics remain valid). Moreover, the execution frequency of short-time domain optimization can be adjusted based on computational requirements and the frequency of V2X information updates.

[0043] The implementation of the rollout algorithm (approximate dynamic programming or ADP) will now be described. In one implementation, the rollout algorithm uses deterministic or stochastic predictions of future events to solve for the problem extended to the prediction time domain N. H The optimization problem involves steps (rather than the N steps of the complete route) and implementation methods such as... Figure 4 The immediate step-level decision is shown. Figure 4 This is a schematic diagram 400 used to describe various aspects of applying multi-time-domain optimization to vehicle dynamics and powertrain control.

[0044] Figure 4A method for applying the rollout algorithm to a given time domain is shown. The rollout algorithm is a continuous short-time-domain optimization technique that relies on a basic policy / heuristic. For example... Figure 4 As shown, the basic heuristic assumption is the value function obtained after solving (usually evaluated before the trip) the long-time domain (full route) optimization problem, and serves as the basis for each N in the short-time domain optimization framework. H The terminal cost is imposed at the end of the time domain.

[0045] The exemplary global optimization problem is for a route with N steps, and the corresponding exemplary rolling temporal optimization is in N... H <<Formulated at N step levels.

[0046] Consider a dynamic control problem discretized in the spatial domain, which takes the form:

[0047]

[0048] Where s is a discrete location or grid point along the route, It's a state. It is input or control, and f s It is a function that describes the dynamics of a state.

[0049] Constraints are applied to control and state, and constraint functions are defined. Represented as:

[0050]

[0051] The permissible control chart at position s is shown in Figure 1. Make:

[0052]

[0053] The set of permissible control charts is used This indicates that it is called the controller's strategy.

[0054] The controller is designed to minimize cost, as given by the following formula:

[0055]

[0056] in, This is the cost function for each stage. The cost function can be defined based on one or more objectives, including but not limited to fuel consumption, driving time, or other performance and driving performance metrics. For use in the back-inductive optimization algorithm 175, the cost function can be rewritten as:

[0057]

[0058] in Indicates any permitted strategy And for each s = 1, ..., N-1. This definition is related to... Figure 4 Consistent. Solved using the rollout algorithm. Figure 4 The cost function of the rolling time-domain optimization problem is defined as:

[0059]

[0060] Where N H It is the length of the rolling time domain. The problem is formulated as follows: Figure 4 The representations in the text are consistent. Here, a key challenge addressed by the proposed rollout algorithm is defining appropriate terminal costs and / or terminal state constraints.

[0061] In this formula, the signal phase information for each traffic light is deterministically incorporated into the initialization process before the journey begins. However, the varying timing information (i.e., the time of each phase) cannot be used in the full-route optimization routine. To address this issue, this work can be extended to include green-passage models that handle maneuvers at signalized intersections.

[0062] Figure 5 Exemplary computing environments are shown, in which exemplary implementation schemes and aspects can be implemented. The computing device environment is merely one example of a suitable computing environment and is not intended to imply any limitation on the scope of use or functionality.

[0063] Many other general-purpose or special-purpose computing system environments or configurations may be used. Examples of well-known computing devices, environments, and / or configurations that may be suitable for use include, but are not limited to: personal computers, server computers, handheld or laptop computers, multiprocessor systems, microprocessor-based systems, network personal computers (PCs), minicomputers, mainframe computers, embedded systems, distributed computing environments including any of the above systems or devices, etc.

[0064] Computer-executable instructions, such as program modules, can be used. Typically, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. A distributed computing environment can be used, where tasks are performed by remote processing devices linked via communication networks or other data transmission media. In a distributed computing environment, program modules and other data can reside on local and remote computer storage media (including memory storage devices).

[0065] refer to Figure 5Exemplary systems for implementing the aspects described herein include computing devices, such as computing device 500. In its most basic configuration, computing device 500 typically includes at least one processing unit 502 and memory 504. Depending on the exact configuration and type of the computing device, memory 504 may be volatile (such as random access memory (RAM)), non-volatile (such as read-only memory (ROM), flash memory, etc.), or a combination of both. This most basic configuration in Figure 5 It is shown in the middle by the dashed line 506.

[0066] The computing device 500 may have additional features / functionality. For example, the computing device 500 may include additional storage devices (removable and / or non-removable), including but not limited to disks, optical discs, magnetic tapes, or optical discs. Such additional storage devices... Figure 5 The image is shown in the form of a removable storage device 508 and a non-removable storage device 510.

[0067] Computing device 500 typically includes various computer-readable media. Computer-readable media can be any available media accessible by device 500, and includes volatile and non-volatile media, removable and non-removable media.

[0068] Computer storage media includes volatile and non-volatile media, as well as removable and non-removable media, implemented in any method or technology, for storing information such as computer-readable instructions, data structures, program modules, or other data. Memory 504, removable storage device 508, and non-removable storage device 510 are examples of computer storage media. Computer storage media include, but are not limited to, RAM, ROM, electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage devices, magnetic cassettes, magnetic tape, disk storage devices or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by computing device 500. Any such computer storage medium may be part of computing device 500.

[0069] The computing device 500 may include a communication connection 512 that allows the device to communicate with other devices. The computing device 500 may also have an input device 514, such as a keyboard, mouse, pen, voice input device, touch input device, etc. It may also include an output device 516, such as a display, speaker, printer, etc. All these devices are well known in the art and need not be described in detail herein.

[0070] In one embodiment, a method for applying multi-time-domain optimization to vehicle dynamics and powertrain control is provided. The method includes: performing long-time-domain optimization on the vehicle's travel; determining an optimal value function based on the long-time-domain optimization; receiving data from one or more components of the vehicle, from one or more powertrain or connectivity features; performing short-time-domain optimization on the travel using a rollout algorithm, the optimal value function, and the received data; and adjusting the vehicle's operation using the results of the short-time-domain optimization.

[0071] The implementation may include some or all of the following features: Performing long-term optimization at least once before or during the trip. Performing long-term optimization includes using route information and a back-inductive optimization algorithm. The method further includes storing an optimal value function in vehicle-associated memory. Receiving data from one or more powertrain or connectivity features after the trip begins and during the trip. The data includes at least one of traffic conditions, vehicle operating status, and V2X information. One or more components of the vehicle include at least one of a vehicle powertrain with an electronic control unit (ECU), a vehicle-to-the-world (V2X) module, an engine, a hybrid electric drive system, and a vehicle speed control device. Vehicle operation includes vehicle dynamics and powertrain control.

[0072] In one embodiment, a method is provided for applying multi-time-domain optimization to vehicle dynamics and powertrain control. The method includes: performing initial optimization of the vehicle's journey at the start of the journey or during the journey; determining an optimal value function based on the initial optimization; storing the optimal value function in vehicle-associated memory; and performing short-time-domain optimization of the journey using updated route information obtained from at least one of a vehicle-to-infrastructure / vehicle-to-vehicle (V2I / V2V) module or a cloud-based service provider.

[0073] The implementation may include some or all of the following features. Performing initial optimization includes performing long-term optimization using the vehicle's long-term optimization module. Performing long-term optimization uses route information received from a cloud-based service provider and a smart digital map, and employs a back-inductive optimization algorithm. Determining the optimal value function is performed by the vehicle's deterministic optimization module. The method further includes using the optimal value function to provide an approximate optimized trajectory for vehicle speed and powertrain control setpoints along the entire route of the journey. The method further includes using the results of short-term optimization to adjust the vehicle's operation. Performing short-term optimization further utilizes a rollout algorithm and the optimal value function.

[0074] In one embodiment, a system for a vehicle is provided. The system includes: a long-time domain optimization module configured to perform long-time domain optimization on a vehicle's trip; a deterministic optimization module configured to determine an optimal value function; and a short-time domain optimization module configured to perform short-time domain optimization on the trip using a rollout algorithm, the optimal value function, and data from one or more powertrain or connectivity features of one or more components of the vehicle.

[0075] The implementation may include some or all of the following features. The system further includes a processor configured to adjust vehicle operation using the results of short-time domain optimization. Long-time domain optimization and short-time domain optimization modules are included within the vehicle. Vehicle components include at least one of an automotive powertrain with an electronic control unit (ECU), an engine, a hybrid electric drive system, a vehicle speed control device, or a vehicle-to-the-world (V2X) module. The long-time domain optimization module is further configured to perform long-time domain optimization using route information and a back-inductive optimization algorithm at least once before or during the trip.

[0076] As used herein, the singular forms “a,” “an,” and “the” include plural indicators unless the context clearly indicates otherwise.

[0077] As used herein, the terms “may,” “can,” “optionally,” “optionally,” and “may optionally” are used interchangeably and are intended to include both cases where the condition occurs and cases where the condition does not occur.

[0078] A range herein may be expressed as "about" a particular value, and / or "about" another particular value. When such a range is expressed, another embodiment includes from said one particular value and / or to said other particular value. Similarly, when a value is expressed as an approximation using the antecedent "about," it should be understood that a specific value forms another embodiment. It should be further understood that the endpoints of each range are valid relative to, and independent of, another endpoint. It should also be understood that many numerical values ​​are disclosed herein, and each numerical value herein is also disclosed as "about" that particular value in addition to the numerical value itself. For example, if the numerical value "10" is disclosed, then "about 10" is also disclosed.

[0079] It should be understood that the various techniques described herein may be implemented in combination with hardware components or software components, or a combination of both where appropriate. Exemplary types of hardware components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), etc. The methods and apparatuses of the subject matter disclosed herein, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in a tangible medium such as a floppy disk, CD-ROM, hard disk drive, or any other machine-readable storage medium, wherein when the program code is loaded into and executed by a machine (such as a computer), the machine becomes an apparatus for practicing the subject matter disclosed herein.

[0080] While exemplary embodiments may refer to the utilization of aspects of the subject matter of this disclosure within the context of one or more independent computer systems, the subject matter is not limited thereto, but can be implemented in conjunction with any computing environment, such as a networked or distributed computing environment. Furthermore, aspects of the subject matter of this disclosure may be implemented in or across multiple processing chips or devices, and similarly, storage may be implemented across multiple devices. For example, such devices may include personal computers, web servers, and handheld devices.

[0081] Although the subject matter has been described using language specifically used for structural features and / or methodological behaviors, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or behaviors described above. Rather, the specific features and behaviors described above are disclosed as exemplary forms of implementing the appended claims.

Claims

1. A method for applying multi-time-domain optimization to vehicle dynamics and powertrain control, the method comprising: At the beginning of the trip: Identify at least one route characteristic of a portion of the predetermined route based on the received route information; Long-term time-domain optimization is performed on the vehicle's journey based on at least one route characteristic of the portion of the predetermined route; as well as At the beginning of the journey, an optimal value function is determined based on the long-term optimization, wherein the optimal value function provides an optimized trajectory for vehicle speed and powertrain control setpoints along the entire predetermined route of the journey; and After the vehicle begins to move along the journey: During the journey, data identifying at least one route characteristic of the remaining portion of the predetermined route is periodically received from one or more components of the vehicle, based on powertrain and connectivity features. The rollout algorithm, the optimal value function, and the received data are used to perform short-time domain optimization on the trip; and The results of the short-time domain optimization are used during the trip to periodically adjust the vehicle's engine operation, hybrid electric drive system, and vehicle speed to improve fuel economy.

2. The method of claim 1, wherein performing the long-term optimization includes using route information and back-inductive optimization.

3. The method of claim 1, further comprising storing the optimal value function in a memory associated with the vehicle.

4. The method of claim 1, wherein the data includes at least one of traffic conditions, vehicle operating status, and vehicle information to the outside world.

5. The method of claim 1, wherein the operation of the vehicle includes vehicle dynamics and powertrain control of the vehicle.

6. The method of claim 1, further comprising: The route information associated with the trip is uncertain; as well as In response to this determination, the long-term optimization is re-executed.

7. The method of claim 1, wherein performing the long-term optimization includes using the route information and stochastic dynamic programming.

8. The method of claim 1, further comprising: If the route information of the trip changes, the long-term optimization is recalculated.

9. The method of claim 1, wherein, The at least one route characteristic of the portion of the predetermined route includes one of speed limits, traffic control signals or signs, traffic conditions, and altitude data.

10. A system for a vehicle, the system comprising: A long-term optimization module is configured to perform long-term optimization on the trip of the vehicle at the beginning of the trip using at least one route characteristic of a portion of a predetermined route of the trip; A deterministic optimization module is configured to determine an optimal value function based on long-time domain optimization at the beginning of the trip, wherein the optimal value function provides an optimized trajectory for vehicle speed and powertrain control setpoints along the predetermined route of the trip; A short-time domain optimization module is configured to periodically perform short-time domain optimization on the trip after the vehicle begins to move on the trip, using a rollout algorithm, the optimal value function, information identifying at least one route characteristic of the remaining portion of the predetermined route, and data from powertrain and connectivity characteristics received from one or more components of the vehicle during the trip; and A processor configured to periodically adjust the operation of the vehicle's engine, hybrid electric drive system, and vehicle speed using the results of the short-time domain optimization after the vehicle begins to move on the journey, during the journey, in order to improve fuel economy.

11. The system of claim 10, wherein the long-time domain optimization module and the short-time domain optimization module are included within the vehicle.

12. The system of claim 10, wherein the components of the vehicle include at least one of an automotive powertrain having an electronic control unit, the engine, the hybrid electric drive system, a vehicle speed control device, or a vehicle external communication module.

13. The system of claim 10, wherein the long-term optimization module is further configured to perform the long-term optimization using route information and back-inductive optimization.

14. The system of claim 10, wherein if the route information of the trip changes, the long-term optimization module recalculates the long-term optimization.

15. The system of claim 10, wherein the at least one route characteristic of the portion of the predetermined route includes one of speed limit, traffic control signals or signs, traffic conditions, and altitude data.

Images