System and method for collaborative vehicle crash planning and sequence deployment

• US 9,108,582 B1
• Filed: 02/25/2014
• Issued: 08/18/2015
• Est. Priority Date: 02/25/2014
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Pickover, Clifford Alan, Kozloski, James R, Lynar, Timothy Michael, Wagner, John Michael
• Primary Examiner(s): Camby, Richard
• Application Number:
  US14/189,165
• Publication Number:
  US 20150239413A1
• Time in Patent Office: 539 Days
• Field of Search: 701/301
• US Class Current: 1/1
• CPC Class Codes: B60R 21/0132 responsive to vehicle motion parameters , e.g. to vehicle longitudinal or transversal deceleration or speed value
• CPC Class Codes: B60R 21/0134 responsive to imminent contact with an obstacle , e.g. using radar systems
• CPC Class Codes: G06F 2111/02 CAD in a network environment, e.g. collaborative CAD or distributed simulation
• CPC Class Codes: G06F 30/00 Computer-aided design [CAD]
• CPC Class Codes: G06F 30/15 Vehicle, aircraft or watercraft design
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

A system and method for collaborative vehicle crash planning employs a model-based approach for mitigating damage and injuries resulting from a vehicle collision. A real-time crash model is generated to determine an optimal crash sequence within a parallel computing environment.

Claims

1. A method for real-time crash modeling, comprising:

using a processor device operatively coupled with at least one sensor in a parallel computing environment, performing;

deriving a likelihood of an impact occurring between a first vehicle and a second vehicle;

negotiating a crash modeling protocol between the first and the second vehicle by performing;

defining a secure communication path for quick and secure transfer of information;

comparing onboard modeling facilities;

setting the collaborative crash parameters;

partitioning the parallel computing environment into partitions between

computing nodes representing the first and second vehicles, each partition comprising the variable simulation state for its associated vehicle;

determining a time before impact; and

determining a number of time steps before impact; and

determining an optimal crash sequence that minimizes possible injury and damage by iteratively performing the following within time step boundaries;

exchanging information with the first and second vehicles according to the crash modeling protocol, said information comprising a variable simulation state of each vehicle indicating a state of collaborative crash parameters;

collaboratively computing a crash model prior to the impact, using the exchanged information, said crash model comprising differential actions for each vehicle to take in order to minimize injury and damage; and

exchanging the computed crash model.

2. The method of claim 1 further comprising deploying the optimal crash sequence by making requisite changes to the collaborative crash parameters, as provided by the crash model, in order to minimize the possible injury and damage.

3. The method of claim 1 wherein exchanging the information with the first and second vehicles comprises determining the possible injury and damage depth and likelihood as a function of at least one factor selected from a group consisting of:

landscape geography, inferred driver ability, vehicle data, local property data, local pedestrian data, vehicle passenger data, and whiplash likelihood and severity.

4. The method of claim 3 wherein collaboratively computing the crash model comprises:

receiving from the computing nodes on time step boundaries the variable simulation state from a previous time step;

wherein each computing node updates the variable simulation state in its partition according to the state of the collaborative crash parameters from the previous time step, such that the crash model includes effects of a contingent update to the one of the first and second vehicles'"'"' variable simulation state computed on a time step.

5. The method of claim 1 wherein setting the collaborative crash parameters comprises selecting parameters from a group consisting of:

braking, speed, direction of travel, gear, horsepower, deployment of supplemental restraints, airbag deployment, traction control, activation of retraction of steering wheel, alteration in direction of steering wheel, sending a signal to traffic control lights within a radius R, and a real-time deployment of road surface material.

6. The method of claim 1 wherein determining the optimal crash sequence is performed by the computing node of the first vehicle.

7. The method of claim 1 wherein determining the optimal crash sequence is performed by a peer device in communication with the two vehicles.

8. The method of claim 3 wherein exchanging the information with the first and second vehicles comprises performing an alternating gradient ascent to optimal crash parameters such that the computing nodes take turns updating the variable simulation state for each vehicle while the other computing node holds its variable simulation state constant.

9. An information processing system for real-time crash modeling, comprising:

a processor device operatively coupled with at least one sensor; and

a memory operably coupled with the processor device and having computer-executable instructions stored thereon, said computer-executable instructions comprising;

deriving a likelihood of an impact occurring between a first vehicle and a second vehicle;

negotiating a crash modeling protocol between the first and the second vehicle by performing;

defining a secure communication path for quick and secure transfer of information;

comparing onboard modeling facilities;

setting the collaborative crash parameters;

partitioning the parallel computing environment into partitions between computing nodes representing the first and second vehicles, each partition comprising the variable simulation state for its associated vehicle;

determining a time before impact; and

determining a number of time steps before impact; and

determining an optimal crash sequence that minimizes possible injury and damage by iteratively performing the following within time step boundaries;

exchanging information with the first and second vehicles according to the crash modeling protocol, said information comprising a variable simulation state of each vehicle indicating a state of collaborative crash parameters;

collaboratively computing a crash model prior to the impact, using the exchanged information, said crash model comprising differential actions for each vehicle to take in order to minimize injury and damage; and

exchanging the computed crash model.

10. The information processing system of claim 9 wherein exchanging the information with the first and second vehicles comprises determining the possible injury and damage depth and likelihood as a function of at least one factor selected from a group consisting of:

landscape geography, inferred driver ability, vehicle data, local property data, local pedestrian data, vehicle passenger data, and whiplash likelihood and severity.

11. The information processing system of claim 9 wherein the computer-executable instructions for collaboratively computing the crash model comprise:

receiving from the computing nodes on time step boundaries the variable simulation state from a previous time step;

wherein each computing node updates the variable simulation state in its partition according to the state of the collaborative crash parameters from the previous time step, such that the crash model includes effects of a contingent update to the one of the first and second vehicles'"'"' variable simulation state computed on a time step.

12. The information processing system of claim 9 wherein the collaborative crash parameters are selected from a group consisting of:

braking, speed, direction of travel, gear, horsepower, deployment of supplemental restraints, airbag deployment, traction control, activation of retraction of steering wheel, alteration in direction of steering wheel, sending a signal to traffic control lights within a radius R, and a real-time deployment of road surface material.

13. The information processing system of claim 9 further comprising a peer device in communication with the vehicles, said peer device performing the optimal crash sequence.

14. A computer program product comprising a non-transitory computer-readable storage medium with computer-executable instruction stored therein, said computer-executable instructions performing real-time crash modeling by causing a computer to perform:

deriving a likelihood of an impact occurring between a first vehicle and a second vehicle;

negotiating a crash modeling protocol between the first and the second vehicle by performing;

defining a secure communication path for quick and secure transfer of information;

comparing onboard modeling facilities;

setting the collaborative crash parameters;

partitioning the parallel computing environment into partitions between computing nodes representing the first and second vehicles, each partition comprising the variable simulation state for its associated vehicle;

determining a time before impact; and

determining a number of time steps before impact; and

determining an optimal crash sequence that minimizes possible injury and damage by iteratively performing the following within time step boundaries;

exchanging information with the first and second vehicles according to the crash modeling protocol, said information comprising a variable simulation state of each vehicle indicating a state of collaborative crash parameters;

collaboratively computing a crash model prior to the impact, using the exchanged information, said crash model comprising differential actions for each vehicle to take in order to minimize injury and damage; and

exchanging the computed crash model.

15. The computer program product of claim 14 wherein the computer-executable instructions for collaboratively computing the crash model comprise:

receiving from the computing nodes on time step boundaries the variable simulation state from a previous time step;

wherein each computing node updates the variable simulation state in its partition according to the state of the collaborative crash parameters from the previous time step, such that the crash model includes effects of a contingent update to the one of the first and second vehicles'"'"' variable simulation state computed on a time step.

16. The computer program product of claim 14 wherein exchanging the information with the first and second vehicles comprises determining the possible injury and damage depth and likelihood as a function of at least one factor selected from a group consisting of:

landscape geography, inferred driver ability, vehicle data, local property data, local pedestrian data, vehicle passenger data, and whiplash likelihood and severity.

17. The computer program product of claim 15 wherein the collaborative crash parameters are selected from a group consisting of:

braking, speed, direction of travel, gear, horsepower, deployment of supplemental restraints, airbag deployment, traction control, activation of retraction of steering wheel, alteration in direction of steering wheel, sending a signal to traffic control lights within a radius R, and a real-time deployment of road surface material.