VEHICLE STATE PREDICTION SYSTEM

• US 20160225201A1
• Filed: 01/11/2016
• Published: 08/04/2016
• Est. Priority Date: 02/02/2015
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: HIROKI, Daisuke
• Granted Patent: US 9,818,238 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 2050/0014 Adaptive controllers
• CPC Class Codes: B60W 2050/0026 Lookup tables or parameter maps
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2050/0095 Automatic control mode change
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: B60W 50/06 Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
• CPC Class Codes: G07C 5/02 Registering or indicating driving, working, idle, or waiting time only apparatus forming part of taximeters G07B13/00
• CPC Class Codes: G07C 5/08 Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
• 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 state predicting circuitry predicts a route showing a future change in the vehicle state from among a plurality of routes from a first node to a second node. The first node corresponds to the current vehicle state. The second node corresponds to the vehicle state after having transitioned a predetermined number of times from the first node. The state predicting circuitry predicts a route in which at least one of an accumulated value of the node that exists in the routes and an accumulated value of the link that exists in the routes is greatest, from among the plurality of routes.

Claims

1. A vehicle state prediction system comprising:

an encoding circuitry, which is configured to encode a vehicle state by use of time-series information of one or more vehicle signals;

a network generating circuitry, which is configured to define symbols representing the encoded vehicle state as nodes in order of appearance, wherein the network generating circuitry defines transitions between the nodes as links and generates a network structure by accumulating a number of appearances of the nodes and a number of passages of the links; and

a state predicting circuitry, which is configured to predict a route showing a future change in the vehicle state from among a plurality of routes from a first node to a second node, wherein

the first node corresponds to the current vehicle state,

the second node corresponds to the vehicle state after transitioning a predetermined number of times from the first node,

the state predicting circuitry is configured to predict, as the route showing the future change in the vehicle state, a route in which at least one of an accumulated value of the node that exists in the plurality of routes and an accumulated value of the link that exists in the plurality of routes is greatest, from among the plurality of routes.

2. The vehicle state prediction system according to claim 1, wherein the state predicting circuitry is configured to predict, as the route showing a future change in the vehicle state, a route that is greatest in the number of passages of the links existing in the plurality of routes from the first node to the second node.

3. The vehicle state prediction system according to claim 1, wherein

existing nodes form the network structure, and

when the vehicle state does not transition to a vehicle state corresponding to the existing nodes even if a certain period of time elapses from a point in time at which the vehicle state does not correspond to any of the existing nodes, the state predicting circuitry is configured to predict the route showing a future change in the vehicle state while setting, as a starting point, a node corresponding to a vehicle state that has a least difference from that of a present point in time among the existing nodes.

4. The vehicle state prediction system according to claim 1, further comprising:

a plurality of audio databases, in which voice pattern groups that differ from each other are stored; and

a voice processing circuitry, which enables a transition of a vehicle state through a voice recognition process,

wherein the voice processing circuitry is configured to

perform the voice recognition process by collating an input voice with an audio database selected from among the audio databases, and

perform switching from the audio database to another audio database suitable for a vehicle state included in a route predicted by the state predicting circuitry.

5. The vehicle state prediction system according to claim 4, wherein, if a route predicted by the state predicting circuitry includes a node corresponding to a vehicle state that has undergone a transition through the voice recognition process, the voice processing circuitry is configured to switch the audio database.

6. The vehicle state prediction system according to claim 5, wherein the state predicting circuitry is configured to predict the route showing a future change in the vehicle state by defining, as the second node, a node corresponding to a vehicle state that underwent a transition through the voice recognition process in the past, and

the voice processing circuitry is configured to perform switching from the audio database to an audio database that was used for the transition to the second node in the route predicted by the state predicting circuitry.

7. The vehicle state prediction system according to claim 6, wherein

when there are a plurality of nodes each of which corresponds to a vehicle state that has undergone a transition through the voice recognition process, the state predicting circuitry is configured to set and give the plurality of nodes a priority higher in proportion to a decrease in node-to-node distance,

the audio database is used for a transition to the node, and

the voice processing circuitry is configured to perform switching among audio database used for the voice recognition process sequentially from the audio database that has been used for the transition to the node having a high priority given by the state predicting circuitry.

8. The vehicle state prediction system according to claim 5, wherein

the vehicle signal is different between the first node and the second node, and

the voice processing circuitry is configured to perform switching between the audio databases under a condition that the vehicle signal is operable through the voice recognition process.

9. The vehicle state prediction system according to claim 1, further comprising a service executing circuitry, which is capable of executing one or more services accompanied by a transition of the vehicle state,

wherein the service executing circuitry is configured to execute the one or more services when a node included in the route predicted by the state predicting circuitry satisfies a predetermined service start-up condition.

10. The vehicle state prediction system according to claim 9, wherein the service executing circuitry is configured to determine the service start-up condition under a condition that an end terminal node in the route predicted by the state predicting circuitry coincides with a vehicle state for which a predetermined service has been executed.

11. The vehicle state prediction system according to claim 10, wherein

the vehicle signal determines the vehicle state for which a service has been executed, and

when an end terminal node in the route predicted by the state predicting circuitry coincides with the vehicle state for which a service has been executed in each of the plurality of services, the service executing circuitry is configured to determine the service start-up condition sequentially from a service that is greatest in number of the vehicle signals that determine the vehicle state for which a service has been executed.

12. The vehicle state prediction system according to claim 1, further comprising a power managing circuitry, which manages a power source of a sensor that detects a vehicle signal, wherein

an output value of a vehicle signal is acquired from each of the nodes, and

when the output value of the vehicle signal does not change between the nodes in the route predicted by the state predicting circuitry, the power managing circuitry is configured to set the power source of the sensor that detects the vehicle signal to OFF.

13. The vehicle state prediction system according to claim 12, wherein

a second route leads from a node corresponding to a past vehicle state to a node corresponding to the current vehicle state, and

the power managing circuitry is configured to set the power source of the sensor to OFF further under the condition that the output value of the vehicle signal does not change between nodes in the second route.

14. The vehicle state prediction system according to claim 1, further comprising a power managing circuitry, which manages a power source of a sensor that detects a vehicle signal, wherein

an output value of a vehicle signal is acquired from each of the nodes, and

when a node in the route predicted by the state predicting circuitry includes a vehicle signal showing an output value different from that of the current vehicle state, the power managing circuitry is configured to set the power source of the sensor that detects the vehicle signal to ON.

15. The vehicle state prediction system according to claim 1, further comprising a management center, which manages traveling information of a plurality of targeted vehicles through wireless communication, wherein

the network generating circuitry is located in the management center,

the network generating circuitry is configured to generate the network structure by defining vehicle states based on the current vehicle signals received from a plurality of vehicles as nodes, and

the network generating circuitry is configured to add accumulated values of the nodes in the plurality of vehicles to the accumulated values of the links in the network structure,

the state predicting circuitry is located in the management center,

the state predicting circuitry is configured to predict a route showing a future change in the vehicle state based on the network structure, and

the state predicting circuitry is configured to deliver the route predicted by the state predicting circuitry to each vehicle of the plurality of vehicles.

16. A vehicle state prediction system comprising:

at least one memory comprising computer executable instructions;

at least one processor configured to read and execute the computer executable instructions to perform;

encoding a vehicle state by compiling time-series information of one or more vehicle signals;

defining symbols representing the encoded vehicle state as nodes in order of appearance defining transitions between the nodes as links;

generating a network structure by accumulating a number of appearances of the nodes and a number of passages of the links; and

predicting a route showing a future change in the vehicle state from among a plurality of routes from a first node to a second node,

wherein the predicting comprises predicting the route in which at least one of an accumulated value of the node that exists in the plurality of routes and an accumulated value of the link that exists in the plurality of routes is greatest, from among the plurality of routes.

17. The vehicle state prediction system according to claim 16 wherein the predicting comprises predicting, as the route showing a future change in the vehicle state, a route that is greatest in the number of passages of the links existing in the plurality of routes from the first node to the second node.

18. The vehicle state prediction system according to claim 16, wherein the at least one processor is further configured to read and execute the computer executable instructions to perform:

when the vehicle state does not transition to a vehicle state corresponding to existing nodes in the network structure, predicting the route showing a future change in the vehicle state while setting, as a starting point, a node corresponding to a vehicle state that has a least difference from that of a present point in time among the existing nodes.

19. The vehicle state prediction system according to claim 16, further comprising:

a plurality of audio databases, in which voice pattern groups are stored, wherein the at least one processor is further configured to read and execute the computer executable instructions to perform;

enabling a transition of a vehicle state through a voice recognition process;

performing the voice recognition process by collating an input voice with an audio database selected from among the audio databases, and

performing switching from the audio database to another audio database suitable for a vehicle state included in the predicted route.

20. The vehicle state prediction system according to claim 16, wherein the at least one processor is further configured to read and execute the computer executable instructions to perform:

executing one or more services accompanied by a transition of the vehicle state when a node included in the route predicted by the state predicting circuitry satisfies a predetermined service start-up condition.