Granted Patent B2

US 12,405,124 · App. 17/476,676 · Granted Sep 2, 2025

Inventors: Tushar Agrawal (West Fargo, ND); Jeremy R. Fox (Georgetown, TX); Atul Mene (Morrisville, NC); Sarbajit K. Rakshit (Kolkata, IN)

Assignee: International Business Machines Corporation

G01C21/3484G01C21/3438G01C21/3461G01C21/3617

Abstract

Claims (66)

1. A computer implemented method, the method comprising:

receiving, by a processor, first object data associated with a first object to be transported to a final destination, wherein the final destination includes a plurality of different routes having one or more different weather conditions;

receiving vehicle data associated with a plurality of potential vehicles for transportation of the first object, wherein the vehicle data includes one or more different capabilities for each of the plurality of potential vehicles;

receiving context data associated with a context for the transportation of the first object;

maintaining historical data obtained from a previous transportation of the first object in a database, wherein the first object data, the vehicle data, and the context data are based at least in part on the historic data maintained in the database;

simulating an outcome of the transportation of the first object utilizing each of the plurality of potential vehicles using digital twin simulation based on the first object data, the vehicle data and the context data;

identifying a first vehicle and a second vehicle of the plurality of potential vehicles for transportation of the first object based on an optimization of an optimization factor associated with the outcome of the digital twin simulation;

determining a first transportation route portion, having a first particular weather condition for the first vehicle of the transportation of the first object based on at least one capability of the one or more different capabilities of the first vehicle and the first particular weather condition, wherein the first transportation route portion ends at a partial destination of the final destination of the first object; and

determining a second transportation route portion having a second particular weather condition for a second vehicle of the transportation of the first object based on at least one capability of the one or more different capabilities of the second vehicle and the second particular weather condition, wherein the second transportation route portion includes a route from an originating location of the second vehicle to the partial destination and from the partial destination to the final destination, wherein the digital twin simulation uses machine learning to simulate a respective digital twin of each of the plurality of potential vehicles, wherein each of the respective digital twins represents a virtual representation of each of the plurality of potential vehicles, wherein the processor is located in a cloud node of a cloud computing environment comprising a plurality of cloud computing nodes and generates the optimization factor associated with the outcome of the digital twin simulation, wherein the processor generates the optimization factor associated with the outcome of the digital twin simulation includes:

analyzing the digital twin simulation for one or more transportation impacts; and

selecting at least one of the one or more transportation impacts on which to base the optimization factor, wherein the optimization factor is selected from at least one of:

transportation cost, transportation time, and damage to vehicle,

and further comprising:

sending, by the processor located in the cloud node of the cloud computing environment, a command to a processor of the first vehicle, wherein the processor of the first vehicle controls timing and route of the first vehicle; and

scheduling, based on the command, transportation of the first object by the first vehicle.

2. The method of claim 1 , further comprising:

retrieving a previous digital twin simulation stored in a repository of simulations for a type of vehicle.

3. The method of claim 1 , further comprising:

receiving second object data associated with a second object to be transported;

simulating transportation of the second object using the digital twin simulation, wherein the simulation is based on a combination of first constraints associated with the first object data and second constraints associated with the second object data; and

selecting the first vehicle based on a combined optimization factor, wherein the combined optimization factor combines the first constraints associated with the first object data and the second constraints associated with the second object data.

4. The method of claim 3 , further comprising:

determining a first transportation route for the first object and a second transportation route for the second object based, at least in part, on the optimization of the optimization factor.

5. A system comprising:

a memory; and

a processor in communication with the memory, the processor being configured to perform operations comprising:

receiving first object data associated with a first object to be transported to a final destination, wherein the final destination includes a plurality of different routes having one or more different weather conditions;

receiving vehicle data associated with a plurality of potential vehicles for transportation of the first object, wherein the vehicle data includes one or more different capabilities for each of the plurality of potential vehicles;

receiving context data associated with a context for the transportation of the first object;

maintaining historical data obtained from a previous transportation of the first object in a database, wherein the first object data, the vehicle data, and the context data are based at least in part on the historic data maintained in the database;

simulating an outcome of the transportation of the first object utilizing each of the plurality of potential vehicles using digital twin simulation based on the first object data, the vehicle data and the context data;

identifying a first vehicle and a second vehicle of the plurality of potential vehicles for transportation of the first object based on an optimization of an optimization factor associated with the outcome of the digital twin simulation;

determining a first transportation route portion, having a first particular weather condition for the first vehicle of the transportation of the first object based on at least one capability of the one or more different capabilities of the first vehicle and the first particular weather condition, wherein the first transportation route portion ends at a partial destination of the final destination of the first object; and

determining a second transportation route portion having a second particular weather condition for a second vehicle of the transportation of the first object based on at least one capability of the one or more different capabilities of the second vehicle and the second particular weather condition, wherein the second transportation route portion includes a route from an originating location of the second vehicle to the partial destination and from the partial destination to the final destination, wherein the digital twin simulation uses machine learning to simulate a respective digital twin of each of the plurality of potential vehicles, wherein each of the respective digital twins represents a virtual representation of each of the plurality of potential vehicles, wherein the processor is located in a cloud node of a cloud computing environment comprising a plurality of cloud computing nodes and generates the optimization factor associated with the outcome of the digital twin simulation, wherein the processor generates the optimization factor associated with the outcome of the digital twin simulation includes:

analyzing the digital twin simulation for one or more transportation impacts; and

selecting at least one of the one or more transportation impacts on which to base the optimization factor, wherein the optimization factor is selected from at least one of: transportation cost, transportation time, and damage to vehicle, and the processor configured to perform further operations comprising:

sending, by the processor located in the cloud node of the cloud computing environment, a command to a processor of the first vehicle, wherein the processor of the first vehicle controls timing and route of the first vehicle; and

scheduling, based on the command, transportation of the first object by the first vehicle.

6. The system of claim 5 , further comprising:

retrieving a previous digital twin simulation stored in a repository of simulations for a type of vehicle.

7. The system of claim 5 , the processor configured to perform further operations comprising:

receiving second object data associated with a second object to be transported;

simulating transportation of the second object using the digital twin simulation, wherein the simulation is based on a combination of first constraints associated with the first object data and second constraints associated with the second object data; and

selecting the first vehicle based on a combined optimization factor, wherein the combined optimization factor combines the first constraints associated with the first object data and the second constraints associated with the second object data.

8. The system of claim 7 , the processor configured to perform further operations comprising:

determining a first transportation route for the first object and a second transportation route for the second object based, at least in part, on the optimization of the optimization factor.

9. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations, the operations comprising:

receiving first object data associated with a first object to be transported to a final destination, wherein the final destination includes a plurality of different routes having one or more different weather conditions;

receiving vehicle data associated with a plurality of potential vehicles for transportation of the first object, wherein the vehicle data includes one or more different capabilities for each of the plurality of potential vehicles;

receiving context data associated with a context for the transportation of the first object;

maintaining historical data obtained from a previous transportation of the first object in a database, wherein the first object data, the vehicle data, and the context data are based at least in part on the historic data maintained in the database;

simulating an outcome of the transportation of the first object utilizing each of the plurality of potential vehicles using digital twin simulation based on the first object data, the vehicle data and the context data;

identifying a first vehicle and a second vehicle of the plurality of potential vehicles for transportation of the first object based on an optimization of an optimization factor associated with the outcome of the digital twin simulation;

determining a first transportation route portion, having a first particular weather condition for the first vehicle of the transportation of the first object based on at least one capability of the one or more different capabilities of the first vehicle and the first particular weather condition, wherein the first transportation route portion ends at a partial destination of the final destination of the first object; and

determining a second transportation route portion having a second particular weather condition for a second vehicle of the transportation of the first object based on at least one capability of the one or more different capabilities of the second vehicle and the second particular weather condition, wherein the second transportation route portion includes a route from an originating location of the second vehicle to the partial destination and from the partial destination to the final destination, wherein the digital twin simulation uses machine learning to simulate a respective digital twin of each of the plurality of potential vehicles, wherein each of the respective digital twins represents a virtual representation of each of the plurality of potential vehicles, wherein the processor is located in a cloud node of a cloud computing environment comprising a plurality of cloud computing nodes and generates the optimization factor associated with the outcome of the digital twin simulation, wherein the processor generates the optimization factor associated with the outcome of the digital twin simulation includes:

analyzing the digital twin simulation for one or more transportation impacts; and

selecting at least one of the one or more transportation impacts on which to base the optimization factor, wherein the optimization factor is selected from at least one of:

transportation cost, transportation time, and damage to vehicle, and the processor configured to perform further operations comprising:

sending, by the processor located in the cloud node of the cloud computing environment, a command to a processor of the first vehicle, wherein the processor of the first vehicle controls timing and route of the first vehicle; and

scheduling, based on the command, transportation of the first object by the first vehicle.

10. The computer program product of claim 9 , further comprising:

retrieving a previous digital twin simulation stored in a repository of simulations for a type of vehicle.

11. The computer program product of claim 9 , the processor configured to perform further operations comprising:

receiving second object data associated with a second object to be transported;

simulating transportation of the second object using the digital twin simulation, wherein the simulation is based on a combination of first constraints associated with the first object data and second constraints associated with the second object data; and

selecting the first vehicle based on a combined optimization factor, wherein the combined optimization factor combines the first constraints associated with the first object data and the second constraints associated with the second object data.

Assignments (1)

Continuity (1)

References Cited (21)