# US 11,442,457 B2 · Navigation via predictive task scheduling interruption for autonomous vehicles > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,442,457 B2 - Document ID: US11442457B2 - Status: Granted - Kind: B2 - Application number: 16/202,154 - Filed: 2018-11-28 - Published: 2020-05-28 - Granted: 2022-09-13 - Earliest claimed: 2018-11-28 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Shikhar Kwatra; Florian Pinel; Jeremy R. Fox; Mauro Marzorati - Web page: https://patentgrep.com/patent/US11442457B2 ## CPC - G05D 1/0221: {involving a learning process} - G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)} - G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues} - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/08: Learning methods - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract According to one embodiment, a method, computer system, and computer program product for navigating driverless vehicles is provided. The present invention may include ingesting data pertaining to the operation of the driverless vehicle, utilizing that data to predict tasks, which are driverless vehicle service tasks such as parking, maintenance, fueling, et cetera. The invention may further include determining the risk that a user may have need of the driverless vehicle, and scheduling the tasks to provide a balanced combination of convenience to the user, effective maintenance of the driverless vehicle, cost, and time. The method further includes navigating the driverless vehicle to accomplish the scheduled tasks. ## Claims ### Claim 1 A processor-implemented method, the method comprising: quantifying an availability risk associated with one or more predicted events on a user's schedule, wherein quantifying the availability risk comprises utilizing a data normalization function to generate a normalized time-based location matrix of the user's planned destinations based on real-time GPS location data; predicting a next fueling time and location of a driverless vehicle based on a battery threshold of the driverless vehicle; finding an availability window for scheduling each of the one or more predicted events on the user's schedule, wherein the scheduling is based at least on the availability risk and a buffer time that is based on environmental data, wherein the environmental data comprises traffic data and weather data; navigating the driverless vehicle based on scheduling at least one time to perform at least one predicted task, wherein the performing includes automatically returning to the location from which the driverless vehicle departed; comparing parking and energy costs to pick a best parking location when arriving at or returning from a task; and receiving user feedback to assess and refine accuracy of future availability risk calculations, together with task predicting and scheduling. ### Claim 2 (depends on 1) The method of claim 1, wherein the availability risk is a likelihood that the user will need to use the driverless vehicle at a given time. ### Claim 3 (depends on 1) The method of claim 1, wherein the availability risk is quantified based on prompting the user for information regarding when the user expects to use the driverless vehicle. ### Claim 4 (depends on 1) The method of claim 1, wherein the availability risk is assigned to one or more of the one or more events occurring within a window of time within which the driverless vehicle will require servicing or refueling. ### Claim 5 (depends on 1) The method of claim 1, wherein the buffer time comprises a time before the driverless vehicle departs to complete the predicted task or after the predicted task is completed. ### Claim 6 (depends on 1) The method of claim 1, further comprising: inferring the presence of one or more unscheduled events based on one or more past trends in the location of the driverless vehicle. ### Claim 7 A computer system the computer system comprising: one or more driverless vehicles, one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: quantifying an availability risk associated with one or more predicted events on a user's schedule, wherein quantifying the availability risk comprises utilizing a data normalization function to generate a normalized time-based location matrix of the user's planned destinations based on real-time GPS location data; predicting a next fueling time and location of a driverless vehicle based on a battery threshold of the driverless vehicle; finding an availability window for scheduling each of the one or more predicted events on the user's schedule, wherein the scheduling is based at least on the availability risk and a buffer time that is based on environmental data, wherein the environmental data comprises traffic data and weather data; and navigating the driverless vehicle based on scheduling at least one time to perform at least one predicted task, wherein the performing includes automatically returning to the location from which the driverless vehicle departed; comparing parking and energy costs to pick a best parking location when arriving at or returning from a task; and receiving user feedback to assess and refine accuracy of future availability risk calculations, together with task predicting and scheduling. ### Claim 8 (depends on 7) The computer system of claim 7, wherein the availability risk is a likelihood that the user will need to use the driverless vehicle at a given time. ### Claim 9 (depends on 7) The computer system of claim 7, wherein the availability risk is quantified based on prompting the user for information regarding when the user expects to use the driverless vehicle. ### Claim 10 (depends on 7) The computer system of claim 7, wherein the availability risk is assigned to one or more of the one or more events occurring within a window of time within which the driverless vehicle will require servicing or refueling. ### Claim 11 (depends on 7) The computer system of claim 7, wherein the buffer time comprises a time before the driverless vehicle departs to complete the predicted task or after the predicted task is completed. ### Claim 12 (depends on 7) The computer system of claim 7, further comprising: inferring the presence of one or more unscheduled events based on one or more past trends in the location of the driverless vehicle. ### Claim 13 A computer program product, the computer program product comprising: one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor to cause the processor to perform a method comprising: quantifying an availability risk associated with one or more predicted events on a user's schedule, wherein quantifying the availability risk comprises utilizing a data normalization function to generate a normalized time-based location matrix of the user's planned destinations based on real-time GPS location data; predicting a next fueling time and location of a driverless vehicle based on a battery threshold of the driverless vehicle; finding an availability window for scheduling each of the one or more predicted events on the user's schedule, wherein the scheduling is based at least on the availability risk and a buffer time that is based on environmental data, wherein the environmental data comprises traffic data and weather data; and navigating the driverless vehicle based on scheduling at least one time to perform at least one predicted task, wherein the performing includes automatically returning to the location from which the at least one the driverless vehicle departed; comparing parking and energy costs to pick a best parking location when arriving at or returning from a task; and receiving user feedback to assess and refine accuracy of future availability risk calculations, together with task predicting and scheduling. ### Claim 14 (depends on 13) The computer program product of claim 13, wherein the availability risk is a likelihood that the user will need to use the driverless vehicle at a given time. ### Claim 15 (depends on 13) The computer program product of claim 13, wherein the availability risk is quantified based on prompting the user for information regarding when the user expects to use the driverless vehicle. ### Claim 16 (depends on 13) The computer program product of claim 13, wherein the availability risk is assigned to one or more of the one or more events occurring within a window of time within which the driverless vehicle will require servicing or refueling. ### Claim 17 (depends on 13) The computer program product of claim 13, wherein the buffer time comprises a time before the driverless vehicle departs to complete the predicted task or after the predicted task is completed. ### Claim 18 (depends on 13) The computer program product of claim 13, further comprising: inferring the presence of one or more unscheduled events based on one or more past trends in the location of the driverless vehicle.