Method and system for providing demand-responsive dispatching of a fleet of transportation vehicles, and a mobility-activity processing module for providing a mobility trace database

• US 9,953,539 B1
• Filed: 03/28/2017
• Issued: 04/24/2018
• Est. Priority Date: 03/28/2017
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Gkiotsalitis, Konstantinos, Alesiani, Francesco, Maslekar, Nitin
• Primary Examiner(s): Alharbi, Adam M
• Application Number:
  US15/470,957
• Time in Patent Office: 392 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: G08G 1/133 within the vehicle ; Indicators inside the vehicles or at stops
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

A method for providing a demand-responsive transportation system includes receiving mobility trace data of collaborative individuals. Clusters of individuals are generated and mobility-activity models for the clusters are defined. Non-collaborative individuals are assigned to the clusters using a combinatorial optimization problem. An Origin-Destination (OD) demand is determined from the clusters. Non-collaborative individuals are re-allocated to different ones of the clusters using an approximation function that learns from an observed OD and the mobility trace data. The mobility-activity models are trained based on the re-allocation of the non-collaborative individuals to different ones of the clusters. An OD database (OD-DB) is maintained to be queried with a geographic location and time so as to receive information from the OD-DB about the current OD demand for the geographic location and time. Control actions are issued to vehicles in a fleet of the transportation system based thereon.

Claims

1. A method for providing a demand-responsive transportation system, the method comprising:

receiving mobility trace data of collaborative individuals;

generating clusters of individuals based on mobility-activity patterns of the collaborative individuals and defining a mobility-activity model for each of the clusters;

assigning non-collaborative individuals to the clusters using a combinatorial optimization problem;

determining an Origin-Destination (OD) demand from the clusters including the collaborative and the non-collaborative individuals;

re-allocating at least some of the non-collaborative individuals to different ones of the clusters using an approximation function that learns from an observed OD and the mobility trace data of the collaborative users;

training the mobility-activity models based on the re-allocation of the non-collaborative individuals to different ones of the clusters;

maintaining an OD database (OD-DB) including a current OD demand determined from the trained mobility-activity models;

querying the OD-DB with a geographic location and time so as to receive information from the OD-DB about the current OD demand for the geographic location and time; and

issuing control actions to vehicles in a fleet of the transportation system using real-time information about the fleet and the information about the current OD demand from the OD-DB.

2. The method according to claim 1, further comprising modifying an allocation of the vehicles in the fleet.

3. The method according to claim 1, further comprising introducing a new service line and dispatching an additional vehicle for the new service line based on the current OD demand not being serviceable by the fleet.

4. The method according to claim 1, wherein the control actions include sending instructions to an on-board unit of one of the vehicles in the fleet with a new time and location for a passenger pick-up or drop-off.

5. The method according to claim 1, wherein the re-allocating and the training are performed continuously or iteratively using the observed OD that is updated continuously or iteratively based on sensor data and additional mobility trace data received for the collaborative individuals.

6. The method according to claim 5, wherein the mobility-activity models of the clusters are continuously or iteratively updated using the additional mobility trace data received for the collaborative individuals.

7. The method according to claim 1, wherein the mobility trace data of the collaborative individuals includes at least one of social media data or smartcard data of the transportation system.

8. A demand-responsive transportation system, the transportation system comprising:

a mobility-activity processing module including one or more processors which, alone or in combination, are configured to provide for the following steps;

receiving mobility trace data of collaborative individuals;

generating clusters of individuals based on mobility-activity patterns of the collaborative individuals and defining a mobility-activity model for each of the clusters;

assigning non-collaborative individuals to the clusters using a combinatorial optimization problem;

determining an Origin-Destination (OD) demand from the clusters including the collaborative and the non-collaborative individuals;

re-allocating at least some of the non-collaborative individuals to different ones of the clusters using an approximation function that learns from an observed OD and the mobility trace data of the collaborative users;

training the mobility-activity models based on the re-allocation of the non-collaborative individuals to different ones of the clusters; and

maintaining an OD database (OD-DB) including a current OD demand determined from the trained mobility-activity models, and

an Automated Fleet Dispatcher (AFD) including one or more processors which, alone or in combination, are configured to provide for the following steps;

querying the OD-DB with a geographic location and time so as to receive information from the OD-DB about the current OD demand for the geographic location and time; and

issuing control actions to vehicles in a fleet of the transportation system using real-time information about the fleet and the information about the current OD demand from the OD-DB.

9. The transportation system according to claim 8, further comprising the fleet of transportation vehicles which communicate with the AFD.

10. The transportation system according to claim 9, wherein the AFD is configured to modify an allocation of the vehicles as one of the control actions.

11. The transportation system according to claim 9, wherein the AFD is configured to introduce a new service line and dispatch an additional vehicle for the new service line based on the current OD demand not being serviceable by the fleet as one of the control actions.

12. The transportation system according to claim 9, wherein the control actions include sending instructions to an on-board unit of one of the vehicles in the fleet with a new time and location for a passenger pick-up or drop-off.

13. The transportation system according to claim 8, wherein the re-allocating and the training are performed continuously or iteratively using the observed OD that is updated continuously or iteratively based on sensor data and additional mobility trace data received for the collaborative individuals.

14. The transportation system according to claim 13, wherein the mobility-activity models of the clusters are continuously or iteratively updated using the additional mobility trace data received for the collaborative individuals.

15. A system for maintaining a mobility trace database, the system comprising one or more processors which, alone or in combination, are configured to provide for the following steps:

receiving mobility trace data of collaborative individuals;

generating clusters of individuals based on mobility-activity patterns of the collaborative individuals and defining a mobility-activity model for each of the clusters;

assigning non-collaborative individuals to the clusters using a combinatorial optimization problem;

determining an Origin-Destination (OD) demand from the clusters including the collaborative and the non-collaborative individuals;

re-allocating the non-collaborative individuals to different ones of the clusters using an approximation function that learns from an observed OD and the mobility trace data of the collaborative users;

training the mobility-activity models based on the re-allocation of the non-collaborative individuals to different ones of the clusters; and

maintaining the database including a current OD demand determined from the trained mobility-activity models.