SITUATION-DEPENDENT CONTROLLED ENERGY HARVESTING SYSTEM

Abstract

A system for situationally-aware energy harvesting (SAGEH) in vehicles includes a cloud computing server and sensors that collect information about a host vehicle and remote vehicles and their surroundings. The vehicles and the server each have a controller executing a SAGEH application that triggers the collection of information from the host vehicle and remote vehicles and surroundings, continuously monitors a traffic signal and the traffic situation along a host vehicle path along a road segment, generates an estimate of a time period for the traffic signal to change status and generates an estimated time period for the host vehicle to stop at the traffic signal, and generates a control output command in response to one or more of the estimated time periods.The control output command causes the base vehicle to dynamically, automatically and adaptively recover energy by activating a stop-start system and / or a regenerative braking system.

Description

INTRODUCTION

[0001] The present disclosure relates to energy conservation systems in motor vehicles, and more particularly to energy harvesting in vehicles employing regenerative braking and / or automatic stop-start systems for internal combustion engines (ICEs). Environmental friendliness and fuel or energy efficiency are increasingly critical to the operation of vehicles, including automatic stop-start systems for ICEs and energy harvesting, such as regenerative braking in electrified vehicle powertrains. To effectively control energy consumption and recuperation, static control sets are often used to regulate the performance of automatic stop-start systems and regenerative braking systems of ICEs. As a result, automatic ICE stop-start systems often result in the ICE being shut down in situations where vehicle drivers desire immediate acceleration.Likewise, regenerative braking systems can operate with limited adjustability. In ICE automatic stop / start and / or regenerative braking systems based on static control sets, energy harvesting processes can manifest as sudden acceleration and / or deceleration, causing unnecessary vehicle vibration and discomfort to passengers, while reducing the overall efficiency of the system.

[0002] Therefore, although current systems and methods for energy conservation systems in motor vehicles serve their purpose, there is a need for a new and improved system and method for situation-dependent energy harvesting in vehicles that utilizes existing hardware, maintains or reduces the complexity of the system components and the computational complexity, while improving the comfort and satisfaction of the vehicle driver and reducing the energy consumption of the vehicles equipped with the system. SUMMARY

[0003] According to several aspects of the present disclosure, a system for situationally directed energy harvesting in a vehicle includes a host vehicle and one or more remote vehicles. The system further includes one or more sensors that collect information about the host vehicle and the remote vehicle and collect environmental information about the environment of the host vehicle and the one or more remote vehicles. The system further includes a cloud computing server communicatively coupled to the host vehicle and the one or more remote vehicles. The host vehicle, the one or more remote vehicles, and the cloud computing server each include a controller. The controller includes a processor, memory, and one or more input / output (I / O) ports. The I / O ports are communicatively coupled to the one or more sensors.The memory stores programmatic control logic. The processor executes the programmatic control logic. The programmatic control logic includes a situation awareness guided energy harvesting (SAGEH) application. The SAGEH application includes at least first, second, third, fourth, and fifth control logic. The first control logic triggers the collection of information about the host vehicle, information about the remote vehicle, and information about the environment from the one or more sensors. The second control logic continuously monitors a traffic signal and the traffic situation along a navigation path of the host vehicle on a road segment. The third control logic generates a first estimated time until the traffic signal changes state and a second estimated time during which the host vehicle stops at the traffic signal.The fourth control logic generates a control output command in response to one or more of the first and second estimated time periods. The fifth control logic causes a vehicle driver to generate feedback about the control output command. The control output command causes the vehicle to dynamically, automatically, and adaptively activate an internal combustion engine (ICE) stop-start system and / or a regenerative braking system to dynamically, automatically, and adaptively harvest energy.

[0004] In another aspect of the present disclosure, the first control logic further includes detecting position information of the base and remote vehicles, navigation information of the base vehicle, and environmental information in the data from the one or more sensors. The one or more sensors further include one or more of: cameras, LiDAR (Light Detection and Ranging) sensors, RADAR (Radio Detection and Ranging) sensors, SONAR (Sound Navigation and Ranging) sensors, ultrasonic sensors, motion sensors, inertial measurement units (IMUs), GPS (Global Positioning System) sensors, cell tower sensors, and traffic light sensors. The first control logic also determines that a situation of the base vehicle has changed from the position information of the base and remote vehicles, the navigation information of the base vehicle, and the environmental information.The first control logic further enables the collection of data specific to the road segment, including collecting from the one or more sensors: camera data, time of day (ToD) information, seasonal information, traffic information, and GPS positioning and navigation information. The first control logic further includes control logic for deriving parametric information from the road segment-specific data, updating the road segment-specific data with the parametric information, and sending the updated information about the road segment to the cloud computing server.

[0005] In yet another aspect of the present disclosure, the first control logic further comprises: control logic for accessing crowd-sourced data stored in the memory of the cloud computing server and obtained from sensors of the one or more remote vehicles, wherein the sensors are located on infrastructure including: traffic lights, GPS satellites, and cell towers. The first control logic further comprises control logic for normalizing the road segment-specific data to determine at least time-based traffic wait times and traffic light duration information along the road segment.

[0006] In yet another aspect of the present disclosure, the second control logic further includes control logic for activating a power harvesting function of the host vehicle and for executing stop-and-go estimation control logic. The stop-and-go estimation control logic operates while the power harvesting function is activated. The stop-and-go estimation control logic performs continuous situation information collection, including: monitoring the host vehicle's navigation route, monitoring GPS data, monitoring camera data, monitoring traffic information, and monitoring the periodicity of traffic signals.

[0007] In yet another aspect of the present disclosure, the second control logic further comprises control logic for processing data collected by the stop and proceed estimation control logic to calculate and derive parametric information about the road segment, the parametric information including: highway information, city street information, single or multi-lane information, straight road information, left turn information, right turn information, roundabout information, lane information, yield sign information, stop sign information, lane-specific traffic signal and status information, other traffic signal and status information, crosswalk information, and determining a number of pedestrians.The second control logic further comprises a control logic for performing a status quo analysis of a focus area to define a current situation of the base vehicle along the road section.

[0008] In yet another aspect of the present disclosure, the third control logic further comprises control logic for calculating the first and second estimated time periods based on a current traffic light status, a number of distant vehicles ahead of the base vehicle, a time of day, a static rule set, and crowd-sourced data comprising: a GPS position of the base vehicle, a traffic light identifier, current and historical time-based traffic wait times, and current and historical traffic light durations.

[0009] In yet another aspect of the present disclosure, the fourth control logic further comprises control logic for utilizing a static rule set, vehicle parameters including the current speed of the host vehicle and the current state of charge of the host vehicle, and an estimated traffic signal behavior to dynamically, automatically, and adaptively generate a control output command for a regenerative braking system and / or an automatic stop-start system of the host vehicle.

[0010] In yet another aspect of the present disclosure, generating the control output command for the regenerative braking system of the host vehicle further comprises dynamically, automatically, and adaptively adjusting an intensity of the regenerative braking based on: a speed of the host vehicle, a distance between the host vehicle and the traffic signal, a traffic condition on the road segment, and an estimated traffic signal behavior.

[0011] In yet another aspect of the present disclosure, generating the control output command for the automatic stop-start system of the host vehicle further comprises: dynamically, automatically, and adaptively adjusting an ICE stop-start system to selectively stop an ICE of the host vehicle based on a speed of the host vehicle, a distance between the host vehicle and the traffic signal, a traffic condition on the road segment, and an estimated traffic signal behavior.

[0012] In yet another aspect of the present disclosure, the fifth control logic further comprises: control logic that collects temporally consecutive actions of a vehicle driver during a time window; and control logic that compares expected and actual behavior to a threshold. If it is determined that the actual behavior is greater than the threshold, the fifth control logic marks a current position of the host vehicle with a difference between the actual and expected behavior. The fifth control logic also triggers a change request for the crowd-sourced data stored in the memory of the cloud computing server.When a number of change requests reaches or exceeds a change request threshold, the control logic triggers a change in the expected behavior, and when the number of change requests is below the change request threshold, the control logic triggers additional data collection.

[0013] In several additional aspects of the present disclosure, a method for situationally directed energy harvesting in a vehicle comprises sensing information about a host vehicle and one or more remote vehicles using one or more sensors and sensing environmental information about the environment of the host vehicle and the one or more remote vehicles. The method further comprises using a cloud computing server communicatively coupled to the host vehicle and the one or more remote vehicles, and using one or more controllers disposed in each of the host vehicle, the one or more remote vehicles, and the cloud computing server. Each of the controllers includes a processor, memory, and one or more input / output (I / O) ports.The I / O ports communicate with the one or more sensors. Programmatic control logic is stored in memory. The processor executes the programmatic control logic. The programmatic control logic includes a situation-aware energy harvesting (SAGEH) application.The SAGEH application includes: triggering the collection of information about the host vehicle, information about the remote vehicle, and environmental information from the one or more sensors; continuously observing a traffic light and the traffic situation along a navigation path of the host vehicle on a road segment; generating a first estimated time period until the traffic light changes status and a second estimated time period during which the host vehicle stops at the traffic light; generating a control output command in response to the first and / or second estimated time period; and causing a vehicle driver to generate feedback about the control output command.The control output command causes the vehicle to dynamically, automatically, and adaptively activate an internal combustion engine (ICE) stop-start system and / or a regenerative braking system to dynamically, automatically, and adaptively harvest energy.

[0014] In yet another aspect of the present disclosure, the method further comprises detecting position information of the base and remote vehicles, navigation information of the base vehicle, and environmental information in the data from the one or more sensors, wherein the one or more sensors further comprise one or more of: cameras, LiDAR sensors, RADAR sensors, SONAR sensors, ultrasonic sensors, motion sensors, inertial measurement units (IMUs), GPS sensors, cell tower sensors, and traffic light sensors. The method further comprises determining from the position information of the base and remote vehicles, the navigation information of the base vehicle, and the environmental information that a situation of the base vehicle has changed.The method further comprises enabling a collection of data specific to the road segment, comprising collecting from the one or more sensors: camera data, time-of-day (ToD) information, seasonal information, traffic information, and GPS positioning and navigation information. The method further comprises deriving parametric information from the road segment-specific data and updating the road segment-specific data with the parametric information and sending the updated information about the road segment to the cloud computing server.

[0015] In yet another aspect of the present disclosure, the method further comprises accessing crowd-sourced data stored in the memory of the cloud computing server and obtained from sensors of the one or more remote vehicles, from sensors located on infrastructure including: traffic lights, GPS satellites, and cell towers, and normalizing the road segment-specific data to determine at least time-based traffic wait times and traffic light duration information along the road segment.

[0016] In yet another aspect of the present disclosure, the method further comprises activating a power harvesting function of the host vehicle and executing stop-and-go estimation control logic. The stop-and-go estimation control logic operates while the power harvesting function is activated. The stop-and-go estimation control logic performs continuous situation information collection, including monitoring the host vehicle's navigation route, monitoring GPS data, monitoring camera data, monitoring traffic information, and monitoring the periodicity of traffic signals.

[0017] In yet another aspect of the present disclosure, the method further comprises processing data collected by the stop-and-go estimation control logic to calculate and derive parametric information about the road segment, wherein the parametric information includes: highway information, city street information, single or multi-lane information, straight-ahead road information, left-turn information, right-turn information, roundabout information, lane information, yield sign information, stop sign information, lane-specific traffic signal and status information, other traffic signal and status information, crosswalk information, and determining a number of pedestrians. The method further comprises performing a status quo analysis of a focus area to define a current situation of the base vehicle along the road segment.

[0018] In yet another aspect of the present disclosure, the method further comprises calculating the first and second estimated time periods based on a current traffic light status, a number of distant vehicles ahead of the base vehicle, a time of day, a static rule set, and crowd-sourced data comprising: a GPS position of the base vehicle, a traffic light identifier, current and historical time-based traffic wait times, and current and historical traffic light durations.

[0019] In yet another aspect of the present disclosure, the method further comprises using a static rule set, vehicle parameters including the current speed of the host vehicle and the current state of charge of the host vehicle, and an estimated traffic light behavior to dynamically, automatically, and adaptively generate a control output command for a regenerative braking system and / or an automatic stop-start system of the host vehicle.

[0020] In yet another aspect of the present disclosure, generating the control output command for the regenerative braking system of the host vehicle further comprises dynamically, automatically, and adaptively adjusting an intensity of the regenerative braking based on: a speed of the host vehicle, a distance between the host vehicle and the traffic light, a traffic condition on the road segment, and an estimated traffic light behavior, and dynamically, automatically, and adaptively adjusting an ICE stop-start system for selectively stopping an ICE of the host vehicle based on a speed of the host vehicle, a distance between the host vehicle and the traffic light, a traffic condition on the road segment, and an estimated traffic light behavior.

[0021] In yet another aspect of the present disclosure, the method further comprises collecting temporally consecutive actions of a vehicle driver during a time window and comparing an expected and an actual behavior to a threshold. If the actual behavior is determined to be greater than the threshold, a current position of the host vehicle is marked with a difference between the actual and expected behavior; and a change request is triggered for the crowd-sourced data stored in the memory of the cloud computing server. If a number of change requests reaches or exceeds a threshold of change requests, the method triggers a change to the expected behavior, and if the number of change requests is below the threshold, the method triggers additional data collection.

[0022] In several additional aspects of the present disclosure, a method for situationally directed energy harvesting in a vehicle comprises sensing information about a host vehicle and one or more remote vehicles using one or more sensors and sensing environmental information about the environment of the host vehicle and the one or more remote vehicles; and utilizing a cloud computing server communicatively coupled to the host vehicle and the one or more remote vehicles. The method further comprises utilizing one or more controllers disposed respectively in the host vehicle, the one or more remote vehicles, and the cloud computing server. Each of the controllers includes a processor, memory, and one or more input / output (I / O) ports.The I / O ports are communicatively coupled to the one or more sensors. Programmatic control logic is stored in the memory. The processor executes the programmatic control logic. The programmatic control logic includes a situation-aware energy harvesting (SAGEH) application. The SAGEH application includes control logic for: triggering the collection of information about the base vehicle, information about the remote vehicle, and environmental information from the one or more sensors, including: detecting position information of the base and remote vehicles, navigation information of the base vehicle, and environmental information in the data from the one or more sensors.The SAGEH application further includes control logic for determining from the position information of the base and remote vehicles, the navigation information of the base vehicle, and the environmental information that a situation of the base vehicle has changed, enabling a collection of data specific to the road segment, comprising collecting from the one or more sensors of: camera data, time of day (ToD) information, seasonal information, traffic information, and GPS position and navigation information, and deriving parametric information in the road segment specific data.The SAGEH application further includes updating the road segment-specific data with the parametric information and sending the updated information about the road segment to the cloud computing server; and accessing crowd-sourced data stored in the cloud computing server's memory and obtained from sensors of the one or more remote vehicles, wherein the sensors are located on infrastructure including traffic lights, GPS satellites, and cell towers. The sensors further include one or more of: cameras, LiDAR sensors, RADAR sensors, SONAR sensors, ultrasonic sensors, motion sensors, inertial measurement units (IMUs), GPS sensors, cell tower sensors, and traffic light sensors.The SAGEH application further comprises control logic for normalizing the road segment-specific data to determine at least time-based traffic wait times and traffic light duration information along the road segment. The SAGEH application further comprises continuously monitoring a traffic light and the traffic situation along a navigation path of the base vehicle on a road segment, comprising: activating an energy harvesting function of the base vehicle and executing stop-and-go estimation control logic. The stop-and-go estimation control logic operates while the energy harvesting function is activated.The stop-and-continue estimation control logic continuously collects situational information, including monitoring the base vehicle's navigation route, monitoring GPS data, monitoring camera data, monitoring traffic information, and monitoring the periodicity of traffic lights. The SAGEH application further includes control logic for processing the data collected by the stop-and-continue estimation control logic to calculate and derive parametric information about the road section.The parametric information includes: highway information, city street information, single or multi-lane information, straight road information, left turn information, right turn information, roundabout information, lane information, yield sign information, stop sign information, lane-specific traffic light and status information, other traffic light and status information, pedestrian crossing information, and determining a count of pedestrians.The SAGEH application further comprises control logic for performing a status quo analysis of a focus area to define a current situation of the host vehicle at the road segment and for generating a first estimated time period until the traffic light changes status and a second estimated time period in which the host vehicle stops at the traffic light, comprising: calculating the first and second estimated time periods based on a current traffic light status, a number of distant vehicles ahead of the host vehicle, a time of day, a static rule set, and crowd-sourced data comprising: a GPS position of the host vehicle, a traffic light identifier, current and historical time-based traffic wait times, and current and historical traffic light durations.In response to one or more of the first and second estimated time periods, the SAGEH application generates a control output command comprising: utilizing a static rule set, vehicle parameters including the current speed of the base vehicle and the current state of charge of the base vehicle, and an estimated traffic signal behavior to dynamically, automatically, and adaptively generate a control output command for a regenerative braking system and / or an automatic stop-start system of the base vehicle.Generating the control output command for the regenerative braking system of the base vehicle further comprises: dynamically, automatically, and adaptively adjusting an intensity of the regenerative braking based on: a speed of the base vehicle, a distance between the base vehicle and the traffic light, a traffic condition on the road section, and an estimated traffic light behavior, and dynamically, automatically, and adaptively adjusting an ICE stop-start system for selectively stopping an ICE of the base vehicle based on a speed of the base vehicle, a distance between the base vehicle and the traffic light, a traffic condition on the road section, and an estimated traffic light behavior.The method further comprises causing a vehicle driver to generate feedback via the control output command, comprising: executing control logic of the SAGEH application that collects temporally consecutive actions of a vehicle driver during a time window; control logic that compares an expected and an actual behavior to a threshold, and if it determines that the actual behavior is greater than the threshold, marks a current position of the host vehicle with a difference between the actual and expected behavior; and control logic that triggers a change request for the crowd-sourced data stored in the memory of the cloud computing server.If the number of change requests reaches or exceeds a threshold, the control logic triggers a change in the expected behavior. If the number of change requests is below the threshold, the control logic triggers additional data collection. The control output command causes the vehicle to dynamically, automatically, and adaptively activate an internal combustion engine (ICE) stop-start system and / or a regenerative braking system to dynamically, automatically, and adaptively harvest energy.

[0023] Further areas of applicability will become apparent from the description provided herein. It should be understood that the description and specific examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described in this document are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way. Fig. 1 is a schematic diagram showing a situation-dependent energy harvesting system according to an exemplary embodiment; Fig. 2 is a flowchart showing the logical flow of control logic of the situation-dependent energy harvesting system of Fig. 1 according to an exemplary embodiment; Fig. 3 is a flowchart showing the logical flow of control logic for a portion of the situational energy harvesting system of Fig. 1 shows triggered data collection and template-like data transfer according to an exemplary embodiment; Fig. 4 is a flowchart showing the logical flow of control logic for a portion of the situational energy harvesting system of Fig. 1 with continuous traffic monitoring according to an exemplary embodiment; Fig. 5 is a flowchart showing the logical flow of control logic for calculating and estimating a traffic light change and the time to stop at a traffic light of the situation-dependent energy harvesting system of Fig. 1 according to an exemplary embodiment; Fig. 6 is a flowchart showing the logical flow of control logic for calculating a control output of the situation-dependent energy harvesting system of Fig. 1 according to an exemplary embodiment; and Fig. 7 is a flowchart showing the logical flow of control logic for a portion of the situational energy harvesting system of Fig. 1 according to an exemplary embodiment with feedback from a vehicle driver. DETAILED DESCRIPTION

[0025] The following description is merely exemplary and is not intended to limit the present disclosure, application, or uses.

[0026] With reference to Fig. 1 and Fig. 2, a system 10 for situationally directed energy harvesting is shown. The system 10 generally includes a base vehicle 12 and one or more remote vehicles 12', a remote cloud computing server 13, and may further include infrastructure such as one or more cell towers 14, GPS (Global Positioning System) satellites 16, traffic signal devices 18, or the like. Although the vehicles 12' shown include passenger vehicles and buses, it should be appreciated that the vehicles 12' may be any of a variety of vehicles 12', including autonomous and manually operated vehicles, including, but not limited to: cars, trucks, sport utility vehicles (SUVs), buses, semi-trailer trucks, tractors used in agriculture or construction, or the like, watercraft, aircraft such as airplanes or helicopters, or the like, without departing from the scope or intent of the present disclosure.

[0027] The vehicles 12' and the remote cloud computing server 13 each include one or more controllers 20. The controllers 20 are non-general electronic control devices that include a pre-programmed digital computer or processor 22, a non-transitory computer-readable medium or memory 24 for storing data such as control logic, software applications, instructions, computer code, data, lookup tables, etc., and a transceiver or input / output (I / O) ports 26. Computer-readable media includes any type of media accessible by a computer, such as read-only memory (ROM), random access memory (RAM), hard disk drive, compact disc (CD), digital video disc (DVD), or any other type of storage.A "non-transitory" computer-readable memory 24 excludes wired, wireless, optical, or other communication connections that carry transitory electrical or other signals. A non-transitory computer-readable memory 24 includes media on which data can be permanently stored and media on which data can be stored and later overwritten, such as a rewritable optical disk or an erasable storage device. Computer code includes all types of program code, including source code, object code, and executable code. The processor 22 is configured to execute the code or instructions. In the vehicles 12', the controller 20 may be a dedicated Wi-Fi controller or a dedicated engine control module, transmission control module, body control module, infotainment control module, etc.The I / O ports 26 are configured to communicate wirelessly using IEEE 802.11x Wi-Fi protocols, cellular protocols such as Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Wireless in Local Loop (WLL), Vehicle-to-Vehicle (V2V) and Vehicle-to-Everything (V2X) systems, General Packet Radio Services (GPRS), 1G, 2G, 3G, 4G Long Term Evolution (LTE), 5G, or the like.

[0028] One or more applications 28 may be stored in the memory 24. An application 28 is a software program configured to perform a particular function or set of functions. The application 28 may include one or more computer programs, software components, instruction sets, sequences, functions, objects, classes, instances, associated data, or a portion thereof suitable for implementation in suitable computer-readable program code. The applications 28 may be stored in the memory 24 of the on-board controllers 20 in the vehicles 12' or in additional or separate memory, for example, in a memory 24 of a cloud computing device such as the cloud computing server 13. Examples of the applications 28 include audio or video streaming services, games, browsers, social media, and a situation-aware directed energy harvesting (SAGEH) application 30.

[0029] The system 10, utilizing the SAGEH application 30, collects and / or generates operational information from a variety of sources, including V2V and V2X, including, but not limited to: one or more sensors 32 disposed on the vehicles 12, 12' that collect information of the vehicle 12, 12', including telematics and communications information of the vehicle 12, 12', such as speed of the vehicle 12, 12', position information of the vehicle 12, 12', altitude of the vehicle 12, 12', and the like. In several aspects, the sensors 32 disposed on the base vehicle 12 may include a variety of sensor types, including, but not limited to, sensors 32 for collecting optical or electromagnetic information about the vehicles 12, 12', an environment surrounding the vehicles 12, 12', and the like. The sensors 32 may include, among others, cameras 34, LiDAR sensors, RADAR sensors, SONAR sensors, ultrasonic sensors, or combinations thereof.Sensors 32 may further include motion sensors such as inertial measurement units (IMUs). IMUs measure and report attitude or position, linear velocity, acceleration, and angular velocities relative to a global reference frame using a combination of some or all of accelerometers, gyroscopes, and magnetometers. In some examples, IMUs may also use GPS data to indirectly measure the attitude or position, velocity, acceleration, and angular velocities of the one or more vehicles 12'.

[0030] In further examples, the base vehicle 12, the remote vehicles 12', and / or the infrastructure-based sensors 32 may collect environmental data about the area around the vehicle 12', such as traffic condition information, road condition and road surface information, weather information, and the like, from remote sensor sources 32, such as infrastructure sensors 32 including GPS satellites 16, cell towers 14, traffic signal devices 18, or roadside sensing devices such as speed or traffic detection cameras, and the like.

[0031] In several aspects, the system 10 collects data from a number of different sources of sensors 32, including the cameras 34, the traffic signal devices 18, GPS satellites 16, and the like. The data acquired from the various sensors of the sensors 32 may include optical data, time of day (ToD) information, traffic density, traffic volume, traffic speed, the periodicity of the traffic signals 18, information about the physical position of the vehicles 12, 12', one or more intersections 36 on a road segment 38, and the like.The data from the sensors 32 may be collected and transmitted continuously by the sensors 32, or it may be transmitted periodically to the cloud computing server 13 via the I / O ports of the various controllers 20, or it may be collected and / or transmitted only upon the occurrence of a triggering event, without departing from the scope or spirit of the present disclosure. In the controller 20 of the cloud computing server 13, the data received from the various sensors 32 of the vehicles, infrastructure, and the like is aggregated and analyzed to determine time-based traffic wait times and information about the duration of the traffic signals 18.

[0032] With specific reference now to Fig. 2 and further reference to Fig. 1, the SAGEH 30 application is schematically illustrated as a series of control logic steps. The SAGEH 30 generally comprises a data collection portion 100 and a functional flow portion 150, which communicate with each other via a series of control logic subroutines. The data collection portion 100 includes several dedicated subroutines, in particular, a first control logic 102 that collects data from the sensors 32, including data from the camera 34, time-of-day information, traffic information, periodicity of the traffic lights 18, GPS position information, lane information, and the like. The data collection portion 100 then proceeds to block 104, where the triggered data collection and template-based transmission from the vehicle(s) 12 to the cloud computing server 13 occurs. The data from the camera 34, the time of the data, and other estimation parameters are included in the triggered and template-based data transmission.

[0033] With specific reference now to Fig. 3 and further reference to Fig. 1 and Fig. 2, the process of triggered and template-based data transfer is described in block 104 of Fig. 2. Starting at block 200, one or more of the sensors 32 generate data about the situation of the base vehicle 12. The data from the sensors 32 may indicate that the base vehicle 12 encounters a new traffic signal 18, a new situation on the road segment 38 or an environmental change has occurred, or that the data generated by the sensors 32 or received from the cloud computing server 13 is out of synchronization. In block 202, the system 10 initiates a new request. In block 204, the cloud computing server 13 generates a navigation-based data request that causes the base vehicle 12 to utilize an on-board navigation system that may interface with one or more of the cell towers 14 and GPS satellites 16 to determine a position of the base vehicle 12 and / or one or more remote vehicles 12'.In block 206, the SAGEH application 30 causes the system 10 to enable data collection at a particular location or along a particular road segment 38. The data collected in block 206 is presented in block 208 and may include data from the camera 34, time of day information, seasonal information, traffic information, GPS position and navigation information, and the like. From block 206, the SAGEH application 30 proceeds to block 210, where the data from the sensors 32 is processed to calculate and derive parametric information and to time-synchronize the received data. The processed data from the sensors 32 is then transmitted to the cloud computing server 13. In several aspects, the data processing includes analyzing and extracting the parametric data of the road segment 38, including the data presented in block 212.In several aspects, the data in block 212 includes, among other things, a number of lanes on the road segment 38, a current lane of the base vehicle 12 on the road segment 38, the time of day, the seasonal status, a holiday status, whether the base vehicle 12 is a school bus or another special vehicle 12, a duration of the traffic signal 18, traffic conditions (heavy to light), time and distance to reach a traffic signal 18 from a particular location, average speed of the vehicle 12, an estimated number of vehicles 12' ahead of the base vehicle 12 based on: a distance from the traffic signal 18, or the like. From block 210, the SAGEH application 30 proceeds to block 106, where the template-based data from the sensors 32 is compared with and / or added to the crowd-sourced data hosted on the cloud computing server 13.In several aspects, the comparison in block 106 includes feature approximation and normalization processes that enable information extraction from the crowd-sourced data and from the template-based data from the sensors 32, including time-based traffic information, traffic wait times, and information regarding the duration of the traffic lights 18. In one example, a regular travel time during peak traffic from a current location to a traffic light 18 for a distance of thirty-five (35) meters or less to the traffic light 18 may require approximately forty seconds. In contrast, for a distance of more than thirty-five meters to the traffic light 18, the same vehicle 12 may require ninety (90) seconds or more to travel to the traffic light 18 at the same time of day during peak traffic.

[0034] With reference again to Fig. 2 and with further reference to Fig. 1 and Fig. 3, after the function approximation and normalization processes for information extraction in block 106, the SAGEH application 30 proceeds to function flow portion 150. In particular, the function flow portion 150 begins in block 152, where an energy harvesting function is activated. The automatic energy harvesting functions of each vehicle 12 may vary, but it should be appreciated that energy harvesting functions for vehicles 12' may include automatic regenerative braking and / or automatic stop-start systems for internal combustion engines (ICE), combinations thereof, or similar such energy storage or energy harvesting functions for vehicles 12'. In block 154, the SAGEH application 30 uses the sensors 32, including the cameras 34, to continuously or intermittently observe the traffic signal 18 and the situation status relative to the navigation path of the base vehicle 12.The data used from the sensors 32 is schematically displayed in block 156 and may include data from the camera 34, LiDAR data, SONAR data, data from the ultrasonic sensors 32 or the like, as well as ToD information, traffic information, the periodicity of the traffic lights 18, GPS position and navigation path information and the like.

[0035] With reference now to Fig. 4 and with further reference to Fig. 1-3, the continuous monitoring of block 154 is illustrated in more detail. The continuous monitoring 154 typically includes a stop-and-go estimation subroutine 300, which has several additional control logic subroutines. In particular, when the energy harvesting function 152 is activated, the stop-and-go estimation subroutine 300 is also activated. The sensors 32, including the cameras 34, collect data from the camera 34, traffic information, information about the periodicity of the traffic lights 18, GPS information, and information about the navigation path. In block 302, the stop-and-go estimation subroutine 300 continuously monitors the data from the sensors 32 and collects situational information about the host vehicle 12, the road segment 38, the traffic lights 18, and the like.In several aspects, the information collected and stored in memory 24 may include navigation route selections, GPS data, camera 34 data, and the like. The stop-and-go estimation subroutine 300 then proceeds to block 304, where a route-based focus area determination is made. The route-based focus area may include a variety of different data types, but should generally include map information based on: GPS information, current and / or historical route selections of the navigation system, and the like. From block 304, the stop-and-go estimation subroutine 300 proceeds to block 306, where the data from block 304 is processed to calculate and derive parametric information, including the content presented in block 308.In particular, in block 308, the parametric information may include designations for various types of road segments 38, such as highways, city streets, two-lane, single-lane, multi-lane, or the like. Other parametric information may include characteristics of the road segment 38, such as whether the road segment 38 is straight, has a left or right turn, a roundabout, and / or lane information. Likewise, traffic signals 18 and / or signage may be included in the parametric information. In some examples, the information regarding the traffic signals 18 and / or signage may include yield signs, stop signs, lane-specific traffic signals 18 and status information, the status of other traffic signals 18, the presence or absence of pedestrian crossings, and the presence and / or number of pedestrians, physical obstacles, curbs, traffic cones, and the like.

[0036] From block 306, the stop and proceed estimation subroutine 300 defines and analyzes a center of gravity region status quo in block 310. In several aspects, the center of gravity region status quo information is presented in block 312 and may include several different parameter sets, each defining a particular situation.

[0037] In a first example 314, a first status quo focus area may include that a traffic light 18 is currently red; that, with the current driving style of the base vehicle 12, it takes approximately thirty seconds for the base vehicle 12 to reach the red traffic light 18; that there are approximately four other vehicles 12' in front of the base vehicle 12, constituting approximately twenty meters between the base vehicle 12 and the red traffic light 18; that there is at least one reference vehicle, such as a large SUV in black color; that a color of the traffic light 18 for traffic crossing the road segment 38 at an intersection 36 is yellow; that a crosswalk is present at the intersection 36 or at the road segment 38; that there are three pedestrians in the path of the base vehicle 12; and / or that there are six pedestrians on the opposite side of the path of the base vehicle 12.

[0038] In a second example 316, a second status quo focus area may include that at the current time, a traffic light 18 is red; that with the current driving style of the base vehicle 12, it takes approximately zero seconds for the base vehicle 12 to reach the red traffic light 18 (i.e.that the base vehicle 12 has reached the traffic light 18); that there are approximately four other vehicles 12' in front of the base vehicle 12, accounting for approximately twenty meters between the base vehicle 12 and the red traffic light 18; that there is at least one reference vehicle, such as a large SUV in black color; that one color of the traffic light 18 for traffic crossing the road segment 38 at an intersection 36 is yellow; that a pedestrian crossing is present at the intersection 36 or at the road segment 38; that there are three pedestrians in the path of the base vehicle 12; and / or that there are six pedestrians on the opposite side of the path of the base vehicle 12.

[0039] In a third example 318, a third status quo focus area may include that a traffic light 18 is currently green; that, with the current driving style of the base vehicle 12, it takes approximately sixty seconds for the base vehicle 12 to reach the green traffic light 18; that there are no distant vehicles 12' in front of the base vehicle 12; that there is at least one reference vehicle, such as a white sedan of a certain color; that a color of the traffic light 18 for traffic crossing the road segment 38 at an intersection 36 is red; that there is a pedestrian crossing the intersection 36 or the road segment 38; that there are no pedestrians in the path of the base vehicle 12; and / or that there are two pedestrians on an opposite side of the path of the base vehicle 12.It should be appreciated, however, that the first, second, and third examples of status quo focus areas are intended as non-limiting examples of the types of data that may be found or determined by the status quo focus area analysis in block 310 without departing from the scope or spirit of the present disclosure.

[0040] Once the continuous observation 154 is completed, with further reference to Fig. 2, the application SAGEH 30 proceeds to block 158, where the SAGEH 30 calculates an estimate of a time duration for switching the traffic light 18 as well as an estimate of a time for the base vehicle 12 to stop at the traffic light 18. In several aspects, the estimate from block 158 uses both static rules 160 and dynamic rules to determine the time for switching the traffic light 18 and the time until stopping at the traffic light 18. The calculation and estimation of block 158 is particularly in Fig. 5 is presented in more detail.

[0041] To calculate and estimate the time required for traffic light 18 to change from one color to another, the SAGEH application 30 uses data from several different sources. In particular, at block 400, the SAGEH application 30 obtains or generates a parameterized information template comprising current and historical data from sensors 32 and from the cloud computing server 13, including, among other things: a current GPS position of the base vehicle 12, an identifier of traffic light 18. In several aspects, the traffic light identifier 18 is a unique identifier that defines which traffic light 18 is currently relevant to the base vehicle 12 given the currently planned path of the vehicle 12. The information template 400 also includes information about the traffic light 18 pattern associated with the subject traffic light 18.The traffic signal 18 pattern information may include a time period during which the traffic signal 18 is programmed to be green (e.g., 180 seconds), red (e.g., 120 seconds), yellow (e.g., 5 seconds), a green arrow (e.g., 90 seconds), or the like. In further examples, the traffic signal 18 pattern information may also include information about regular peak traffic hours based on ToD data. In some examples, during a regular peak traffic ToD, when a vehicle 12 is up to thirty-five meters from the traffic signal 18, the information template 400 may indicate that the typical travel time for the base vehicle 12 to reach the traffic signal 18 is approximately forty seconds, while the time for the base vehicle 12 to arrive at the traffic signal 18 may be approximately ninety seconds when the base vehicle 12 is more than thirty-five meters from the traffic signal 18.The information template 400 may be obtained at least in part from crowdsources 106, including current and historical time-based traffic wait times and traffic signal 18 durations obtained from other vehicles 12' in block 402. In block 160, the application SAGEH 30 obtains the static rule set 160.

[0042] The static rule set 160 may include any of a number of different operating rules for the base vehicle 12. For example, many base vehicles 12 employ static rules that establish a basic set of behaviors for energy harvesting through regenerative braking, automatic stop-start operation of the engines of the ICE vehicle 12, and the like. For example, the static rule set in block 160 may include rules that cause the ICE of a vehicle 12 to shut down when the base vehicle 12 is stopped, the brake pedal is applied, the accelerator pedal is in a zero-throttle position, and the HVAC system of the base vehicle 12 is in the "off" state.The rules may also include determining whether a temperature of the ICE is at an optimal threshold temperature, and if the ICE is operating at a temperature below the threshold temperature, not specifying shutdown of the ICE, and if the threshold temperature is reached or exceeded, selectively specifying shutdown of the ICE. Similarly, a regenerative braking system in an at least partially hybridized or fully electric vehicle 12 may be activated when it is determined that the driver of the base vehicle 12 is decelerating at a predefined rate, at or below a predefined speed, or the like.In block 406, the SAGEH application 30 determines focal area-relevant parameters, such as a current status of the traffic light 18, an estimated time to reach the traffic light 18, a number of distant vehicles 12' in front of the base vehicle 12, the presence or absence of a pedestrian crossing, and the like. During the calculation and estimation in block 158, the focal area-relevant parameters from block 406, the static rule set from block 160, the crowd-sourced data from block 402, and the information from the information template from block 400 are used in block 408 as inputs to an AI (artificial intelligence), ML (machine learning), or rule-based engine.

[0043] The AI, ML, or rule-based engine may utilize a variety of different AI, ML, and / or rule-based applications 28 or control logic subroutines to define estimates of the behavior of traffic signals 18 along the planned path of the host vehicle 12. The AI, ML, and / or rule-based techniques may include, but are not limited to, linear regression models, deep neural networks, logistic regressions, decision trees, linear discriminant analysis trained using crowd-sourced data, and the like, without departing from the scope or spirit of the present disclosure. In one example of a rule-based engine, the SAGEH application 30 may utilize control logic according to the following logic flow pattern: If (traffic light 18 == red) && (path == straight) && (number of vehicles 12' in front of the vehicle >=3) && (time == average traffic volume) && (estimated time to reach traffic light 18 <= 40% of the duration of traffic light 18) → estimated waiting time at traffic light 18 < 30 seconds when traffic light 18 is red.

[0044] It should be noted, however, that the logical flow presented above is intended to be only a non-limiting example of the rule-based approach, and that deviations therefrom are intended to be within the scope and intended coverage of the present disclosure.

[0045] The AI, ML, and / or rule-based engine performs the calculation and estimation in block 158 in block 408 to generate an estimate of the behavior of traffic signal 18 in block 410. In several aspects, the behavior of traffic signal 18 estimated in block 410 varies considerably from situation to situation and from application to application.

[0046] In a first example 412, assuming that the nearest traffic light 18 is currently "red" and that there are four (4) vehicles 12' ahead of the base vehicle 12 at the current time of day, and that the base vehicle 12 takes approximately fifteen seconds to reach the traffic light 18, the traffic light 18 may turn "green" within approximately twenty (20) seconds. Therefore, given the situation defined in the first example, the base vehicle 12 may selectively activate an ICE and / or EV control system to change a behavior of the ICE and / or EV control system of the base vehicle 12.

[0047] In a second example 414, if the nearest traffic light 18 is currently green and there are zero vehicles 12' in front of the base vehicle 12 at the current time of day, and the base vehicle 12 takes approximately twenty seconds to reach the traffic light 18, the traffic light 18 may turn red within approximately twenty (20) seconds. Therefore, given the situation defined in the first example, the base vehicle 12 may selectively activate an ICE and / or EV control system to change a behavior of the ICE and / or EV control system of the base vehicle 12.

[0048] With reference again to Fig. 2 and with further reference to Fig. 1 and 3-5, once the SAGEH 30 application has calculated and generated an estimated time period in which the traffic signal 18 will change from one color to another and / or has calculated an estimated stop time at the traffic signal 18 in block 158, the SAGEH 30 application proceeds to block 162 where the system 10 generates an ICE and / or EV control system output.

[0049] The ICE and / or EV tax system output calculations are Fig. 6. In several aspects, the ICE and / or control system output calculations in block 162 utilize inputs from a number of sources, including data acquired from the various sensors 32. More specifically, in block 500, the parameters of the host vehicle 12 are acquired from the sensors 32. The parameters of the host vehicle 12 may include a number of pieces of information about the movement, the position on the road segment 38, and the GPS position of the host vehicle 12. In some non-limiting examples, the parameters of the host vehicle 12 may include an X-direction speed of the host vehicle 12, a Y-direction speed of the host vehicle 12, a current state of charge (SOC) of a traction battery of an electric or electrified vehicle 12, and the like.

[0050] In block 502, the SAGEH application 30 obtains a current static rule set and calibration along with obstacle interruption detection along the road segment 38. In some non-limiting examples 503, the static rule set and calibration for an ICE-equipped vehicle 12 may include rules that prevent engine shutdown when the fuel level of the base vehicle 12 is below or equal to a predetermined minimum capacity threshold, when the outside temperature is below one threshold or above a second threshold, or the like.In some specific, non-limiting examples, the predetermined minimum fuel capacity threshold may be a fuel level less than or equal to 1% of the fuel capacity of the vehicle 12, the outside temperature thresholds may be above 90° Fahrenheit or below 15° Fahrenheit, or the like. For an electric vehicle (EV), the static rule set and calibration may include rules that prevent regenerative braking from activating when the EV is traveling in traffic at a speed below a threshold, such as below 20 mph, when no stopping point or exit is available, when the driver of the base vehicle 12 indicates a desire for the EV to coast, or the like.In further examples, the static rule set, calibration, and obstacle interruption detection are recalculated when the sensors 32 detect a change in circumstances or situation to adapt to the changed circumstances.

[0051] The estimate of the behavior of the traffic signal 18 from block 410 is retrieved and used, along with the base vehicle parameters from block 500 and the current static rule set from block 502, as input to the ICE and / or EV control output calculations in block 504. In several aspects, the ICE and / or EV control output calculations in block 504 include calculations for generating control signals in block 506 that regulate the performance of the ICE and / or EV systems in the vehicles 12'.

[0052] By way of non-limiting example, for ICE systems, the control output calculations in block 506 generate control outputs 508 that cause the engine in an ICE-equipped vehicle 12 to remain on or to automatically shut down when one or more threshold conditions are met. More specifically, for an ICE-equipped vehicle 12, the control output calculation may determine that the internal combustion engine of the vehicle 12 is shut down when the amount of time the base vehicle 12 is stopped is greater than or equal to a threshold amount of time.

[0053] Subsequently, based on the predicted dwell time of traffic signal 18, i.e., the time until the color changes from red to green, the control output calculation in block 504 starts the ICE approximately one second before the predicted dwell time of traffic signal 18 expires. By anticipating the color change of traffic signal 18 in this way, the time period during which the base vehicle 12 is stationary with the ICE turned off while traffic signal 18 is green is significantly reduced. By anticipating the color change of traffic signal 18, the time period that the driver of vehicle 12 must wait before using the ICE to accelerate is significantly reduced or even eliminated entirely, resulting in smoother traffic flow and increased customer satisfaction and confidence in base vehicle 12.

[0054] In another non-limiting example relating to EV vehicles 12', the control output calculations generate control outputs 508 that cause the regenerative braking system of a fully or partially electric vehicle 12 to change its performance when one or more threshold conditions are met. More specifically, for such a fully or partially electric vehicle 12 or EV, the control output calculation may determine which of several different regenerative braking modes to activate. For example, a Level 1 coasting mode may be activated that gradually, dynamically, automatically, and adaptively increases the amount of regeneration based on: the distance to be traveled, the presence of obstacles, and / or the distance to and / or the current color and estimated time until the color change of a particular traffic signal 18.The intensity of regenerative braking during coasting may also be dynamically, automatically, and adaptively increased until the EV comes to a stop at red light 18. In some specific, but non-limiting, examples, above a threshold distance of approximately fifty meters from a red or predicted red traffic light 18, the base vehicle 12 activates regenerative braking at approximately 25% capacity. Subsequently, when the base vehicle 12 reaches the fifty-meter threshold distance, the base vehicle 12 increases regenerative braking to approximately 65%, and when the base vehicle 12 is within ten meters of the red traffic light 18, the regenerative braking is increased to 90% intensity or 90% capacity or greater, thereby bringing the base vehicle 12 to a stop at an appropriate position relative to the red traffic light 18, crosswalks, and the like.

[0055] By anticipating the color change of the traffic light 18 in this way, the smoothness of the regenerative braking operations is improved, along with a reduction in the intervention of the driver of the vehicle 12 in braking, coasting, and acceleration operations, along with overall improvements through smoother traffic flow and increased customer satisfaction and confidence in the base vehicle 12. It should be appreciated that the example control output calculations may vary significantly from application to application and situation to situation without departing from the scope or spirit of the present disclosure.

[0056] With reference again to Fig. 2 and with further reference to Fig. 1 and 3-6, once the control outputs 508 have been sent to the control systems of the vehicle 12, including one or more of an ICE and a regenerative braking system, the SAGEH application 30 proceeds to block 164, where a driver of the vehicle 12 may provide feedback on the control outputs 508. More specifically, the driver of the base vehicle 12 may provide feedback on the control outputs 508 relative to the vehicle 12 responses desired by the driver of the vehicle 12. The SAGEH application 30 utilizes the feedback from the driver of the base vehicle 12 to adjust future control output calculations through a federated learning mechanism.

[0057] With reference now to Fig. 7 and with further reference to Fig. 1-6, the feedback from the driver of the base vehicle 12 is shown in detail in flowchart form in block 164. The driver feedback portion 164 of the SAGEH application 30 begins in block 600. In block 602, once the SAGEH application 30 has determined an energy harvesting strategy in block 508, sequential actions of the driver of the base vehicle 12 during a specific time window are collected. For example, data from sensors 32 regarding braking, acceleration, lane changes, etc. are collected. A trigger check is performed in block 604. The trigger check compares the expected behavior of vehicle 12 and traffic signal 18 with the actual recorded behavior of vehicle 12 and traffic signal 18.If the difference between expected and actual behavior is greater than a threshold difference, the driver feedback portion 164 triggers a driver feedback request for the vehicle 12 and prepares to generate it. In several aspects, the trigger check in block 604 uses a trigger rule set that can cause the system 10 to trigger periodically, continuously, after a predetermined number of events occur, or the like. In some non-limiting examples, the trigger rule set can cause the trigger check in block 604 to occur once a month, upon reaching ten or more events, or the like.

[0058] In block 606, the driver feedback portion 164 generates a trigger for a feedback request from the driver of the vehicle 12. The trigger in block 606 uses the trigger rule set set in block 604 to establish the boundaries of the threshold values ​​for the expected versus actual behavior of the vehicle 12 and the traffic signal 18. In block 608, the driver feedback portion 164 prepares a time sequence of expected and actually performed actions, as well as feedback information. In several aspects, the data prepared in block 606 includes information regarding decisions for the control outputs of the automatic energy harvesting system and the like.

[0059] In block 610, the driver feedback portion 164 determines when actual and expected actions match within a predetermined time period. If it is determined that the actual and expected actions match during the predetermined time period, the driver feedback portion 164 proceeds to block 612, where the current GPS position of the base vehicle 12 is marked as "good" or otherwise correct.However, if the actual and expected actions do not match in block 610, the driver feedback portion 164 of the SAGEH 30 application proceeds to block 614, and the current GPS position of the base vehicle 12 is marked with the difference between the actual and expected actions. The resulting information is transmitted via the I / O ports to the cloud computing server 13, where a database is updated accordingly with the difference between the actual and expected information. If the actual and expected actions do not match, the driver feedback portion 164 proceeds to block 616, where a consistency check is performed. The consistency check in block 616 causes the system 10 to monitor a set of change requests and determine whether the requested differences are greater than or equal to a change threshold.If the change requests exceed the threshold, consistency check 616 causes additional data to be collected. However, if the requested differences are below the change threshold, driver feedback portion 164 triggers an update and causes the differences to be implemented in memory 24 of cloud computing server 24. From block 612 or block 614, driver feedback portion 164 proceeds to block 618, where the driver feedback portion ends. Driver feedback portion 618 may operate continuously, periodically, or upon the occurrence of one or more events during operation of vehicle 12, returning to block 600 and running again.

[0060] With reference again to Fig. 2 and with further reference to Fig.1 and 3-7, the SAGEH 30 application returns again to the data collection part 100 after the consistency check 616, and the crowd-sourced data 106 is updated with the results of the consistency check 616 during the next iteration while the SAGEH 30 application is executing.

[0061] A system and method for situationally directed energy harvesting in accordance with the present disclosure offers several advantages. These include situationally directed energy harvesting using existing hardware and maintaining or reducing the component and computational complexity of the system 10, while simultaneously improving the comfort and satisfaction of the driver of the base vehicle 12 and reducing the energy consumption of the vehicles 12, 12' equipped with the system 10.

[0062] The description of the present disclosure is merely exemplary, and variations that do not depart from the gist of the present disclosure are intended to be included within the scope of the present disclosure. Such variations should not be construed as a departure from the spirit and scope of the present disclosure.

Claims

[1] System for situation-dependent controlled energy generation in vehicles, comprising: a base vehicle and one or more remote vehicles; one or more sensors that collect information about the base vehicle and the remote vehicle and collect environmental information about the environment of the base vehicle and the one or more remote vehicles; and a cloud computing server in communication with the base vehicle and the one or more remote vehicles; wherein the base vehicle, the one or more remote vehicles, and the cloud computing server each comprise a controller, the controller comprising a processor, a memory, and one or more input / output (I / O) ports, the I / O ports communicatively coupled to the one or more sensors; wherein programmatic control logic is stored in the memory; wherein the processor executes the programmatic control logic; wherein the programmatic control logic comprises a situation-aware energy harvesting (SAGEH) application, the SAGEH application comprising: first control logic for triggering the collection of information about the base vehicle, information about the remote vehicle, and environmental information from the one or more sensors; a second control logic for continuously monitoring a traffic light and a traffic situation along a navigation path of the base vehicle on a road section; a third control logic for generating a first estimated time period until the traffic light changes its status and a second estimated time period in which the base vehicle stops at the traffic light. a fourth control logic for generating a control output command in response to one or more of the first and second estimated time periods; and a fifth control logic that causes a driver of the vehicle to generate feedback via the control output command, wherein the control output command causes the vehicle to dynamically, automatically, and adaptively activate an internal combustion engine (ICE) stop-start system and / or a regenerative braking system to dynamically, automatically, and adaptively harvest energy. [2] The system of claim 1, wherein the first control logic further comprises: Detecting position information of the base and remote vehicles, navigation information of the base vehicle, and environmental information in the data from the one or more sensors, wherein the one or more sensors further comprise one or more of: Cameras, LiDAR (Light Detection and Ranging) sensors, RADAR (Radio Detection and Ranging) sensors, SONAR (Sound Navigation and Ranging) sensors, ultrasonic sensors, motion sensors, inertial measurement units (IMUs), GPS (Global Positioning System) sensors, cell tower sensors, and traffic light sensors; Determining from the position information of the base vehicle and the remote vehicle, the navigation information of the base vehicle and the environmental information that a situation of the base vehicle has changed; Enabling a collection of data specific to the road segment, comprising collecting from the one or more sensors: camera data, time of day (ToD) information, seasonal information, traffic information, and GPS (Global Positioning System) positioning and navigation information; Deriving parametric information in the data specific to the road section; and Updating the road section-specific data with the parametric information and sending the updated road section information to the cloud computing server. [3] The system of claim 2, wherein the first control logic further comprises: Accessing crowd-sourced data stored in the memory of the cloud computing server and obtained from sensors of the one or more remote vehicles, wherein the sensors are located on infrastructure including: traffic lights, GPS satellites, and cell towers; and Normalizing the road segment specific data to determine at least time-based traffic wait times and traffic light duration information along the road segment. [4] The system of claim 1, wherein the second control logic further comprises: Activating an energy harvesting function of the base vehicle; and Executing a stop-and-go estimation control logic, wherein the stop-and-go estimation control logic operates while the energy harvesting function is enabled, and wherein the stop-and-go estimation control logic performs a continuous collection of situation information, comprising: monitoring the navigation route of the base vehicle, monitoring GPS data, monitoring camera data, monitoring traffic information, and monitoring the periodicity of traffic lights. [5] The system of claim 4, wherein the second control logic further comprises: Processing data collected by the stop-and-go estimation control logic to calculate and derive parametric information about the road section, the parametric information including: highway information, city street information, single or multi-lane information, straight-ahead road information, left-turn information, right-turn information, roundabout information, lane information, yield sign information, stop sign information, lane-specific traffic light and status information, other traffic light and status information, pedestrian crossing information, and determining a number of pedestrians; and Conducting a status quo analysis of a focus area to define a current situation of the base vehicle along the road section. [6] The system of claim 4, wherein the third control logic further comprises: Calculating the first and second estimated time periods based on a current traffic light status, a number of distant vehicles ahead of the base vehicle, a time of day, a static rule set, and crowd-sourced data comprising: a GPS position of the base vehicle, a traffic light identifier, current and historical time-based traffic wait times, and current and historical traffic light durations. [7] The system of claim 1, wherein the fourth control logic further comprises: Using a static rule set, vehicle parameters including the current speed of the base vehicle and the current state of charge of the base vehicle, and an estimated traffic light behavior to dynamically, automatically, and adaptively generate a control output command for one or more of a regenerative braking system and an automatic stop-start system of the base vehicle. [8] The system of claim 7, wherein generating the control output command for the regenerative braking system of the base vehicle further comprises: dynamic, automatic and adaptive adjustment of an intensity of regenerative braking based on: a speed of the base vehicle, a distance between the base vehicle and the traffic light, a traffic condition on the road section and an estimated traffic light behavior. [9] The system of claim 7, wherein generating the control output command for the automatic stop-start system of the base vehicle further comprises: dynamic, automatic and adaptive setting of an ICE stop-start system for selectively stopping an ICE of the base vehicle based on a speed of the base vehicle, a distance between the base vehicle and the traffic light, a traffic condition on the road section and an estimated traffic light behavior. [10] The system of claim 1, wherein the fifth control logic further comprises: Control logic that collects sequential actions of a vehicle driver during a time window; Control logic that compares an expected and an actual behavior with a threshold, and if it determines that the actual behavior is greater than the threshold, marks a current position of the base vehicle with a difference between the actual and the expected behavior; and Control logic that triggers a change request for the crowd-sourced data stored in the memory of the cloud computing server, wherein when a number of change requests reaches or exceeds a change request threshold, the control logic triggers a change in the expected behavior, and when the number of change requests is below the change request threshold, the control logic triggers additional data collection.

Images