PRIVATE CLOUD 106 is similar to public cloud 105, except that the computing resources are only available for use by a single enterprise. While private cloud 106 is depicted as being in communication with WAN 102, in other embodiments a private cloud may be disconnected from the internet entirely and only accessible through a local/private network. A hybrid cloud is a composition of multiple clouds of different types (for example, private, community or public cloud types), often respectively implemented by different vendors. Each of the multiple clouds remains a separate and discrete entity, but the larger hybrid cloud architecture is bound together by standardized or proprietary technology that enables orchestration, management, and/or data/application portability between the multiple constituent clouds. In this embodiment, public cloud 105 and private cloud 106 are both part of a larger hybrid cloud.

Component 150 may be connected to vehicle software that integrates real-time data regarding the driver, the vehicle, and the environment to optimize the in-vehicle experience. Component 150 may receive data from vehicle sensors and uses analytics and AI to understand driver behavior and link to other information systems in a cloud system, such as weather and traffic, to add context and situational awareness. In various embodiments, based on linked and integrated data, component 150 diagnoses safety risks or quality issues and takes immediate action. For example, connecting to real-time weather and traffic conditions to improve the effectiveness of a vehicle's collision avoidance system or rerouting the vehicle based on traffic and/or weather reports.

In various embodiments, component 150 monitors, via IoT sensor set 125, the change in ground vibration pattern along with other historically learned data related to soil, wind, tree age, tree fall history, and/or another metrics known and understood in the art from remote database 130 and/or storage 124 to predict if the surrounding area (i.e., predetermined area or radius from a predetermined point on the vehicle) is safe (i.e., outside of an identified fall zone where an identified object can damage the vehicle) from falling debris (e.g., a falling tree) and proactively moving the vehicle from a current position into a safe zone or predetermined area. A safe zone is an identified or predetermined area outside of an identified fall zone where an identified object can damage the vehicle. A fall zone is an identified area where an identified object may fall and damage the vehicle, wherein the fall zone comprises an identified radius of damage such as a fall radius. Component 150 may analyze a predetermined surrounding area of a vehicle for any potential threat that may fall upon or impact the vehicle and proactively move the vehicle into a safe zone based on received feedback from IoT sensor set 125 and retrieved historic data associated with an identified risk or predetermined area. An area or zone is considered safe when component 150 determines that the likelihood of a predetermined risk is below a predetermined threshold.

In various embodiments, component 150 (i) instructs and/or manages the movement of a vehicle from a high risk area (e.g., a location where component 150 identified one or more objects with a likelihood of falling and damaging the car above a predetermined threshold), (ii) parks the vehicle away from the identified risk related object(s) (i.e., safe zone), (iii) executes an electronic mapping for the identified risk object(s) and autonomously uploads risk to storage 124 and/or remote database 130, (iv) elevates the risk of the situation and any parking route changes, (v) utilizes weather data and soil parameters and soil data to evaluate and analyze the risk of the surrounding area to the vehicle, (vi) monitors, via IoT sensor set 125 vertical risk threats (e.g., branches, building debris, trees, street lights, etc.), (vii) proactively utilizes predetermined social and regional events to evaluate risk (e.g., scheduled holidays and events), and (viii) identifying a parking location risk based on external drivers (or the prediction thereof). In various embodiments, any risk evaluation may be conducted through one or more risk analysis/assessment methods and/or software known and understood in the art.

Component 150 may move a vehicle from a current position based on an identified risk (e.g., when a predetermined risk factor is identified above or within a predetermined radius of the vehicle). For example, if an autonomous vehicle is parked on the roadside and there are trees on one or both sides of the road, then with the sensors attached on the wheels or base of the vehicle, component 150, via the sensors associated with the vehicle, will continue to monitor the change in ground vibration pattern. In this example, component 150 compares the data collected from the ground vibration pattern monitoring with historic ground vibration patterns to predict if a tree is going to fall and damage the vehicle based on the changes in ground vibration patterns. In this example, if component 150 identifies a change in ground vibration patterns, then component 150 proactively instruct the vehicle to autonomously move to a predetermined safe zone. In various embodiments, component 150 compares current data with historic data to determine if the surrounding area is unsafe, wherein, predetermined or identified changes/discrepancies between the current and historic data triggers component 150 to identify the surrounding area as unsafe, and wherein unsafe is defined as the likelihood of an identified object falling and damaging or impacting the vehicle is above a predetermine range. If a surrounding area is identified as unsafe, then component 150 may proactively instruct the vehicle to autonomously move to a predetermined safe zone. In various embodiments, component 150 compares the data collected from the monitored ground vibration patterns to predict by comparing current collected ground vibration patterns with previous ground vibration patterns, wherein component 150 compares the collected ground vibration patterns in predetermined time intervals. In various embodiments, component 150 instructs and/or manages an autonomous vehicle to park away from the identified risk related object(s). For example, based on historical learning regarding the types of trees that have been known to fall or that have been recently falling, wind parameters, ground soil parameters, and/or any other factors known and understood in the art, component 150 identifies which road may be unsafe for parking or operating the vehicle, and accordingly, component 150 identifies the trees and keeps the vehicle a predetermined distance away from the identified trees.

Component 150 may execute and managed an electronic map based on the historical data (e.g., previous incidents and/or accidents, type of object, type of structure) and data collected while the vehicle is driving, wherein component 150 collaborates and updates the electronic map. In a simplistic example, component 150 creates and manages an electronic map based on historical data associated with tree fallings and the type of trees that have been known to fall (e.g., name of trees, height, size, color, size, shape, and/or other metrics known and understood in the art), wherein component 150 updates the electronic map based on the types of trees and the vulnerability of the tree to fall. In this simplistic example, component 150 may generate and issue notifications to the driver/owner of the vehicle, a city administrator and/or vehicle service provider to alert them of the identified risk.

Component 150 may elevate risk situations and parking route changes, based on the updated map or electronic/digital map comprising the location of identified risk objects (e.g., vulnerable trees on the roadside) and the weather parameters (e.g., weather forecast: wind, rain, snowing, etc.), to identify which road is unsafe, and identify a route to a new parking location where the risk situation is below a predetermined threshold. In various embodiments, if a vehicle needs to park on the roadside, then based on the types of tree and soil parameters, component 150 determines if the vehicle can be parked in the current location, wherein the types of tree and soil parameters are measured through image capturing, IoT sensor set 125, and data repository in a knowledge corpus. In various embodiments, if component 150 determines the current location is dangerous (i.e., identifies a potential risk of damage to the vehicle above a predetermined threshold) then component 150 identifies a safe secondary parking location or retrieves a predetermined safe zone.

In various embodiments, while the autonomous vehicle is operating on the road, component 150, via IoT sensor set 126, identifies objects that line the roadside (i.e., roadside specification) of the current road that the vehicle is traveling and identifies whether there is potential vertical risk object that might damage the roof of the vehicle or the vehicle in general. For example, if there are trees, buildings, lamp posts, highway signs, streetlights, and/or any other vertical structures or objects known and understood in the art that could fall and damage the vehicle or can accumulated objects that could fall and damage or impact the vehicle such as but not limited to as accumulated snow and/or construction material. In various embodiments, component 150 considers one or more local holidays or other cultural events wherein the traffic patterns change based on the local holiday or cultural events (e.g., more cars congregating and/or operating in certain areas that could increase the chance of other vehicles parking on the side of the road and getting damaged). In another example, component 150 considers local garbage collection or snow plowing types of events that increase the activity on a roadside and increase the potential of damage to the vehicle.

FIG. 1B is a functional block diagram illustrating a distributed data processing environment, generally designated 100, in accordance with one embodiment of the present invention. The term “distributed” as used in this specification describes a computer system that includes multiple, physically distinct devices that operate together as a single computer system. FIG. 1B provides only an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environment may be made by those skilled in the art without departing from the scope of the invention as recited by the claims. Distributed data processing environment 100 includes predetermined area 158, vehicle 160, client computer 101, and remote server 104 interconnected WAN 102.

In the depicted embodiment, via UI device set 123, component 150 issues and/or receives permission from a user/owner of vehicle 160 to track and/or monitor vehicle 160 and predetermined area 158 (i.e., receive opt-in response 161), wherein predetermined area 158 is a predetermine area surrounding vehicle 160. Component 150 may generate knowledge corpus 162 through iterative usage of collecting and storing data associated with predetermined risk factors of predefined risks. Component 150 utilizes IoT sensor set 125 to identify and monitor object 159 while the vehicle is driving or stationary. For example, component 150 identifies, via cameras, radar, ultrasonic, seismic, and LiDAR sensors, and stores the location of trees, street lights, light posts, telephone wires, pot holes, buildings, and other structures or objects (collectively referred to as objects) that component 150 detects and identifies while the vehicle is driving and utilizes global positioning system (GPS) to correspond the identified objects to a location on a map based on the proximity of the object from the vehicle. In various embodiments, knowledge corpus 162 is a public knowledge corpus that any autonomous vehicle that has opt-in can reference to assess risk-based situation(s).

In the depicted embodiment, component 150, via risk monitoring module 164, utilizes IoT sensor set 125 to monitor identified object 159 while the vehicle is driving and/or stationary. Component 150 may monitor, via IoT sensor set 125, object 159 in predetermined area 158 while vehicle 160 is stationary. In various embodiments, component 150, based on identified object 159 in predetermined area 159, component 150 assess the risk of object 159 damaging vehicle 160 prior to enabling vehicle 160 to park in predetermined area 158 and/or while vehicle 160 is parked in predetermined area 158. For example, prior to enabling an autonomous vehicle from parking in an identified parking space, component 150 will assess the risk of the palm trees, lamp post, and telephone pole falling and damaging the autonomous vehicle. Component 150 may ingest omnidirectional input data from IoT sensor set 125 to observe and identify objects in predetermined area 158 and vertical space 157, wherein vertical space 157 is a predetermined area above the vehicle 160 (e.g., a predetermined range from the roof of vehicle 160 and the surrounding area above the roof).

In the depicted embodiment, component 150 receives input from IoT sensor set 125 and identifies object 159 in predetermined area 158 and/or vertical space 157 that represent a potential risk to vehicle 160. For example, component 150 identifies trees, shrubberies, construction equipment, building apparatus, overhead based cabling, and powerlines next to and above the autonomous vehicle. Component 150 may utilize knowledge corpus 162 to calculate and/or assign risk score 169. In the depicted embodiment, component 150, via risk analysis module 168, compares captured data from IoT sensor set 125 with data stored in knowledge corpus 162 to calculate and/or assign risk score 169 to object 159. In various embodiments, if the assigned risk score of one or more objects is above a predetermined threshold, then component 150 issues an audible and/or physical alert or alarm, a responsive prompt to warn the user the potential risk, and/or restrict the user from parking the vehicle in the current or predetermined area.

In the depicted embodiment, component 150 matches object 159 with learned data in knowledge corpus 162 to assign object 159 an overall risk score (risk score 169) and quantify the overall risk to vehicle 160. Component 150 may quantify risk score 169 as a low-risk event, moderate risk event, and high-risk event, wherein a low-risk event corresponds to risk score 169 being below a predetermined threshold, a moderate risk event corresponds to risk score 169 being withing a predetermined range, and a high-risk event corresponds to risk score 169 being above a predetermined threshold. Lower risk situations (objects with a risk score lower than a predetermined threshold) are a minimal risk and will not likely impede a vehicle parking or pulling over. For example, a vehicle parking near a building with an overhead “flag” that extends from the building. The flag mounted to the building might be quantified and scored as a low lever vertical risk, thus an acceptable risk, and no further action would be required, and the autonomous vehicle would be permitted to park in this location. In a different example, vehicle 160 is attempting to park at a local public park; however, component 150 identifies a leaning tree within a predetermined radius of vehicle 160. In this example, component 150 quantifies the risk event as high and sends a notification to vehicle 160, via command module 166, to not park within the identified high-risk area due to a vertical risk.

Additionally, in this example, component 150, via command module 166, issues a command to component 150 to continue to locate a parking space that is not within the predetermine risk area. In various embodiments, if component 150 identifies object 159 as being a high-risk event, then component 150, via command module 166, executes a command for vehicle 160 to autonomously move to predetermined safe area 170. In various embodiments, component 150 may monitor object 159 while vehicle 160 is parked, via IoT sensor set 125, and dynamically adjust the risk score and quantification of the risk score based on any received changes to object 159, vertical space 157 and/or predetermined area 158. For example, if component 150 identifies a leaning tree in park as a moderate risk and the vehicle parks in the moderate risk area then component 150, via IoT sensor set 125, monitors the change in ground vibration pattern along with other historically learned data related to soil, ground vibration, wind, tree age, and tree fall history. In this example, if component 150 detects ground vibration and/or wind then component 150 elevates the identified leaning tree from a moderate risk event to a high-risk event and executes a command for the vehicle to autonomously move from the current parking space to a secondary parking location with no risk events or a low-risk events, wherein component 150 identifies the secondary parking location based on the collected and monitored data. In some embodiments, the secondary parking location can be a predetermined located selected by a user. In various embodiments, component 150, via object recognition and natural language processing, identifies posted signs. In various embodiments, if component 150 identifies a warning, danger, or caution sign then component 150 infers an overhead hazard or danger and identifies the area as having a high-risk event.

FIG. 2 illustrates operational steps of component 150, generally designated 200, in communication with client computer 101, remote server 104, private cloud 106, EUD 103, and/or public cloud 105, within distributed data processing environment 100, for implementing impact prevention in autonomous vehicles, in accordance with an embodiment of the present invention. FIG. 2 provides an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environment may be made by those skilled in the art without departing from the scope of the invention as recited by the claims.

In step 202, component 150 receives permission to track and monitor a vehicle. In various embodiments, via UI device set 126, component 150 issues and/or receives permission from a user/owner of a vehicle to track and/or monitor the vehicle and in a predetermined area (i.e., receive opt-in response), wherein a predetermined area is a predetermine area surrounding the vehicle.

In step 204, component 150 monitors a predetermined area surrounding the vehicle. In various embodiments, component 150, via IoT sensor set 125, monitors a predetermined area surrounding the vehicle while the vehicle is in motion or while the vehicle is stationary. In various embodiments, component 150 may monitor one or more objects, within a predetermined distance from the vehicle, while the vehicle is parked, via IoT sensor set 125, and dynamically adjust the risk score and quantification of the risk score based on any received changes to the object, vertical space, and/or predetermined area.

In step 206, component 150 generates a knowledge corpus. In various embodiments, component 150 generates a knowledge corpus based on the data received from the monitoring. Component 150 may generate knowledge corpus 162 through iterative usage of collecting and storing data associated with predetermined risk factors of predefined risks.

In step 208, component 150 identifies a risk object. In various embodiments, component 150, via IoT sensor set 125 and the generated corpus, identifies a risk object in a predetermined area. In various embodiments, while the autonomous vehicle is operating on the road, component 150, via IoT sensor set 126, identifies objects that line the roadside (i.e., roadside specification) of the current road that the vehicle is traveling and identifies whether there is potential vertical risk object that might damage the roof of the vehicle or the vehicle in general. In various embodiments, component 150, via risk monitoring module 164, utilizes IoT sensor set 125 to monitor identified object 159 while the vehicle is driving and/or stationary.

In step 210, component 150 tracks the risk object. In various embodiments, component 150, via IoT sensor set, tracks/monitors the identified risk object. In the depicted embodiment, via UI device set 123, component 150 issues and/or receives permission from a user/owner of vehicle 160 to track and/or monitor vehicle 160 and predetermined area 158 (i.e., receive opt-in response 161), wherein predetermined area 158 is a predetermine area surrounding vehicle 160. For example, if component 150 identifies a tree leaning while the vehicle is stopped at a local park then component 150 flags the leaning tree as a moderate risk and that the vehicle is stopped in the moderate risk area. In this example component 150, via IoT sensor set 125, monitors the change in ground vibration pattern along with other historically learned data related to soil, ground vibration, wind, tree age, and tree fall history to dynamically adjust the risk score based on the monitored data.

In step 212, component 150 determines if the risk object exceeds a predetermined danger threshold. In various embodiments, component 150 matches the object with learned data in the knowledge corpus to assign an object an overall risk score (risk score) and quantify the overall risk to the vehicle. Component 150 may quantify the risk score as a low-risk event, moderate risk event, and high-risk event, wherein a low-risk event corresponds to the risk score being below a predetermined threshold, a moderate risk event corresponds to the risk score being withing a predetermined range, and a high-risk event corresponds to the risk score being above a predetermined threshold. Lower risk situations (objects with a risk score lower than a predetermined threshold) are a minimal risk and will not likely impede a vehicle parking or pulling over.

In step 214, component 150 moves the vehicle. In various embodiments, responsive to the risk-score being above a predetermined threshold (high-risk event), component 150 issues command to the vehicle to autonomously move the vehicle to a predetermined safe location.

FIG. 3 illustrates operational steps of component 150, generally designated