Vehicular driving actions in the presence of non-recurrent events

Patent metadata

Field	Value
Publication number	US-11222271-B2
Application number	US-201815956955-A
Country	US
Kind code	B2
Filing date	Apr 19, 2018
Priority date	Apr 19, 2018
Publication date	Jan 11, 2022
Grant date	Jan 11, 2022

Abstract

Embodiments for planning vehicular driving actions in the presence of non-recurrent events by a processor. One or more dynamics of non-recurrent events in a transport network may be learned according to one or more contextual factors. One or more vehicle-specific factors may be learned in relation to a historical journey and current journey of a vehicle. One or more action responses associated with the one or more non-recurrent events and the one or more vehicle-specific factors may be generated.

First claim

The invention claimed is:

1. A method, by a processor, for planning vehicular driving actions in the presence of non-recurrent events, comprising:
learning dynamics of one or more non-recurrent events in a transport network according to one or more contextual factors, wherein learning the dynamics includes intersecting an impact of the one or more non-recurrent events with a selected vehicle route in the transport network for both a selected time and location;
learning one or more vehicle-specific factors in relation to a historical journey and current journey of a vehicle; and
generating one or more action responses associated with the one or more non-recurrent events and the one or more vehicle-specific factors.

2. The method of claim 1 , further including:
detecting and learning the one or more contextual factors, wherein the one or more contextual factors include a static transport network, location of one or more events, duration of one or more events, a degree of intensity of the one or more events that impact the transport network, one or more traffic conditions, traffic predictions, traffic data, weather data, road conditions, or a combination thereof; and
detecting and learning the one or more vehicle-specific factors, wherein the one or more vehicle-specific factors include a tolerated loss time of one or more users of the transport network as a function of the contextual factors, a total time of driving by one or more users, predicted routes associated with the one or more users of the transport network, current routes associated with the one or more users of the transport network, travel itinerary of the one or more users, or a combination thereof.

3. The method of claim 1 , further including defining the one or more non-recurrent events as traffic congestion at one or more locations in the transport network, an accident, a temporary road closure, a temporary event causing a negative impact on traffic flow in the transport network, or combination thereof.

4. The method of claim 1 , further including suggesting one or more alternative routes of the transport network, an advanced departure time for using the transport network, an increase or decrease in vehicular speed of one or more vehicles, a stopover or termination of movement of the one or more vehicles in the transport network, an additional stopover at a location of interest to the vehicle, a change of transport mode, or a combination thereof.

5. The method of claim 1 , further including propagating the learned dynamics of one or more non-recurrent events in the transport network according to one or more contextual factors.

6. The method of claim 1 , further including:
selecting one or more mitigating actions as the one or more action responses to resolve a conflict between a route trajectory of a user and a route having the one or more non-recurrent events in the transport network;
selecting a device to receive the one or more mitigating actions, wherein the device is an Internet of Things (IoT) device; or
selecting a balanced driving action among the one or more mitigating actions for one or more users to avoid deteriorating the traffic conditions upon resolving a conflict of the one or more non-recurrent events for a plurality of users.

7. A system for planning vehicular driving actions in the presence of non-recurrent events, comprising:
one or more computers with executable instructions that when executed cause the system to:
learn dynamics of one or more non-recurrent events in a transport network according to one or more contextual factors, wherein learning the dynamics includes intersecting an impact of the one or more non-recurrent events with a selected vehicle route in the transport network for both a selected time and location;
learn one or more vehicle-specific factors in relation to a historical journey and current journey of a vehicle; and
generate one or more action responses associated with the one or more non-recurrent events and the one or more vehicle-specific factors.

8. The system of claim 7 , wherein the executable instructions further:
detect and learn the one or more contextual factors, wherein the one or more contextual factors include a static transport network, location of one or more events, duration of one or more events, a degree of intensity of the one or more events that impact the transport network, one or more traffic conditions, traffic predictions, traffic data, weather data, road conditions, or a combination thereof; and
detect and learn the one or more vehicle-specific factors, wherein the one or more vehicle-specific factors include a tolerated loss time of one or more users of the transport network as a function of the contextual factors, a total time of driving by one or more users, predicted routes associated with the one or more users of the transport network, current routes associated with the one or more users of the transport network, travel itinerary of the one or more users, or a combination thereof.

9. The system of claim 7 , wherein the executable instructions further define the one or more non-recurrent events as traffic congestion at one or more locations in the transport network, an accident, a temporary road closure, a temporary event causing a negative impact on traffic flow in the transport network, or combination thereof.

10. The system of claim 7 , wherein the executable instructions further suggest one or more alternative routes of the transport network, an advanced departure time for using the transport network, an increase or decrease in vehicular speed of one or more vehicles, a stopover or termination of movement of the one or more vehicles in the transport network, an additional stopover at a location of interest to the vehicle, a change of transport mode, or a combination thereof.

11. The system of claim 7 , wherein the executable instructions further propagate the learned dynamics of one or more non-recurrent events in the transport network according to one or more contextual factors.

12. The system of claim 7 , wherein the executable instructions further:
select one or more mitigating actions as the one or more action responses to resolve a conflict between a route trajectory of a user and a route having the one or more non-recurrent events in the transport network;
select a device to receive the one or more mitigating actions, wherein the device is an Internet of Things (IoT) device; or
select a balanced driving action among the one or more mitigating actions for one or more users to avoid deteriorating the traffic conditions upon resolving a conflict of the one or more non-recurrent events for a plurality of users.

13. A computer program product for planning vehicular driving actions in the presence of non-recurrent events by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that learns dynamics of one or more non-recurrent events in a transport network according to one or more contextual factors, wherein learning the dynamics includes intersecting an impact of the one or more non-recurrent events with a selected vehicle route in the transport network for both a selected time and location;
an executable portion that learns one or more vehicle-specific factors in relation to a historical journey and current journey of a vehicle; and
an executable portion that generates one or more action responses associated with the one or more non-recurrent events and the one or more vehicle-specific factors.

14.

Assignees

• IBM

Inventors

• Monteil Julien
• Dekusar Anton
• LASSOUED Yassine
• Ordonez-Hurtado Rodrigo H
• Russo Giovanni
• Mevissen Martin

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N20/20 Primary

  Ensemble learning · CPC title

• G06N5/048

  Fuzzy inferencing · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title