Patent Application
20110246067
The invention relates generally to a dynamic routing system and method for moving assets and, more specifically, to the use of real time data analysis for dynamic routing of moving assets.
As the world's economies become more and more interdependent, efficient distribution of goods becomes useful for many businesses that depend on such distribution. Goods are often distributed from central locations to many retail destinations. Efficient distribution of goods entails, among other things, a determination of routes and schedules for the fleet of vehicles so that total distribution costs are minimized, while various constraints are met.
Distributors or planners generally allocate resources such as trailers and drivers to deliver goods on time. When delivery delays occur, it is difficult to analyze whether any alternative actions could have prevented or reduced such delays. As the number of drivers and trailers grows for a particular fleet, coordination challenges increase. Currently, human dispatchers and drivers who have a knack for scheduling and planning use their knowledge for vehicle trip scheduling and routing. Computer software is sometimes used for in route optimization to select shorter or faster routes. However, these methods are not efficient or comprehensive enough to track all factors that may result in delay.
There is a need for an improved, automated transportation system.
In accordance with an embodiment of the present invention, a dynamic routing system comprising a data collection module for receiving real time trip data corresponding to a moving asset from a remote location is provided. The system further includes a static routing module to determine candidate routes from a source to a destination for the moving asset and an orientation module configured to gather publically available information associated with candidate routes. A learning module configured to generate a learned route database based on the publically available information from the orientation module and on the real time trip data from the data collection module is also provided in the system. The system also includes a route determination module to determine an optimized route for the moving asset based on the learned route database and a communication interface configured to transmit an optimized route signal.
In accordance with another embodiment of the present invention, a method for identifying dynamic routing for a moving asset is provided. The method includes receiving real time trip data corresponding to the moving asset and determining candidate routes from a source to a destination for the moving asset. The method also includes obtaining publically available information associated with candidate routes and generating a learned route database based on candidate routes and the publically available information. The method further includes estimating an optimized route for the moving asset based on the learned route database.
These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
When introducing elements of various embodiments of the present invention, the articles “a,” “an,” “the,” and “said” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements.
When data communication device 24 comprises a data satellite, the data satellite transmits a wireless signal 26 received from remote hub 16 to a gateway earth station 28. Wireless signal 26 transmitted by remote hub 16 may comprise information such as trailer location data, a corresponding time-stamp, trailer ignition data, trailer identification data, and combinations thereof. It may also comprise event data such as ‘trip start’, ‘trip end’, ‘door open’, ‘door close’, ‘cargo loaded’, and ‘cargo empty,’ for example. It may also include other sensor data such as tire pressure, anti-lock brake status, bearing vibration. Gateway earth station 28 is generally controlled by the satellite network provider. Data received from the data communication device through the Gateway earth station is processed by a back end control station 30. Back end control station 30 processes the data, which may include use of additional information such as internet data for performing data analytics, and then delivers the results such as asset location or optimized route to the end customer 32, either through the web or a direct data feed such as XML data exchange. In one embodiment, the end customer may be a driver.
Static routing module 54 determines candidate routes from the source to the destination for the routing data received from the data collection module. In one embodiment, static routing module 54 may include a map database such as Google Maps mapping service, MapQuest Inc mapping service, Yahoo! Map mapping service, or Environmental Systems Research Institute (ESRI) mapping service. Static routing module 54 further provides candidate routes to orientation module 56 for determining obstacles or disturbances on candidate routes. For example, if static routing module 54 receives information from data collection module 52 that a trailer A is at location X and need to go to a location Y, then static routing module 54 provides routes along the X to Y path to orientation module 56.
Orientation module 56 collects publically available information about the candidate routes and real time trip data from data collection module 52 and provides it as an input signal to learning module 58. In one embodiment, data collection module 52 may directly provide the real time trip data to learning module 58. The publically available information may include traffic conditions, road conditions, weather conditions, community events, department store sale or event conditions, concert or sporting event information, and fuel prices on the candidate routes, for example. The publically available information may further include information such as shipment departures from a local distribution center on the candidate route. The real time trip data may comprise data such as status of an anti-lock braking system for the moving asset or speed of the moving asset or delay in travel time to reach the destination or even information about a road construction on a candidate route. It may also comprise event data such as ‘trip start’, ‘trip end’, ‘door open’, ‘door close’, ‘cargo loaded’, and ‘cargo empty,’ for example.
Learning module 58 generates a learned route database based on the information from orientation module 56. The learning module may include predictors which enable route determination module 60 to better select optimal routes, based on the output of the predictors. In one embodiment, the predictor predicts delays on certain candidate routes based on obvious and non-obvious events obtained from the orientation module.
The obvious events may comprise information such as time of day, day of week, season, weather, and direction of travel. In one embodiment, the predictor may provide an indicator to avoid certain candidate routes or certain direction of travel on the candidate routes based on the time of day. For example, over time the predictor may have learned or the historical data may suggest that during morning time, a candidate route A has heavy traffic compared to the evening time. Thus, the predictor will give indication to avoid candidate route A during morning time. The predictor may utilize other obvious events such as slow movement of another vehicle being monitored by the dynamic routing system and output a warning of traffic jams or lane closures on a particular candidate route.
The non-obvious event may comprise information such as status (activation) of Anti-lock braking system of a moving asset combined with the trailer's location on a candidate route and the temperature or precipitation likelihood on the route. The predictor will then predict and output a warning of an icy road on that candidate route if the anti-lock braking system status is active and temperature is low or precipitation is high. Further, if the predictor senses traffic issues in a certain area, it will mine all the data input to the system to determine if there is correlation over time with other (seemingly unrelated) activities, such as shipment departure times from a local distribution center. Thus, in the future, if the predictor knows shipments are planned from that local distribution center, it will forecast potential issues and automatically alert a warning about the particular candidate route. In one embodiment, a less obvious predictor may be point of sale volume from a retailer center that would predict either increased traffic volume on access roads leaving that center or forecast increased traffic activity at the local distribution center within the next 24 hours window. It should be noted that the events mentioned above are only exemplary and similar other examples may be utilized to correlate various activities and to forecast obstacles on candidate routes. Thus, learning module 58 stores historical trip data of various trailers on a given route, analyzes the data and forecasts traffic conditions based on the analysis.
Route determination module 60 utilizes candidate routes and mashes them with the information from the orientation module and the output of predictors and determines the optimal routes for the moving asset. For example, the route determination module avoids all candidate routes on which warnings are sounded by predictors and selects an optimized route on which least travel time will be achieved. In one embodiment, route determination module 60 splits the route in multiple segments and checks whether there are any barriers on those segments based on the information from the learning module and then it determines an optimal route around the barrier. In one embodiment, route determination module 60 will determine a route which will result in least fuel price. Once an optimized route is identified, a communication network 62 communicates it to the respective user or the moving asset. For example, the communication network may send a real time signal to a driver to take the optimized route.
One of the advantages of the dynamic routing system is it allows efficient planning in the transportation sector of the supply chain. The dynamic routing system finds potential real time inefficiencies in the distribution system based on the status of predictors and suggest improvements. The dynamic routing system may be used to drive decisions for simple routing and also may learn from previous dynamic routing results so as to create models to explain the behavior and use these models to forecast optimal future routes based on the status of various predictors.
While only certain features of the invention have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.
