Browse Prior Art Database

Method and Apparatus for Completing Logistics Vehicle's Trajectory with Very Large GPS's Interval Disclosure Number: IPCOM000244803D
Publication Date: 2016-Jan-18
Document File: 5 page(s) / 141K

Publishing Venue

The Prior Art Database


Many manufacturing and logistics companies monitor the trajectories of their shipment to better manage the logistics services provided to their customers. GPS data is key to form a shipping trajectory. Sometimes the GPS data is missing due to the malfunction of the equipment or incorrect human operations and the resulting shipping trajectories may contain unknown sections. This disclosure discloses a method for completing shipping trajectories with missing positioning data. Historical trajectory data and Hidden Markov Model are used to recover the missing position point.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 5

Method and Apparatus for Completing Logistics Vehicle

Method and Apparatus for Completing Logistics Vehicle' ''s Trajectory with Very Large GPS

s Trajectory with Very Large GPS s Trajectory with Very Large GPS' ''s Interval

s Interval

Today, transportation visualization is adopted by many manufacturing or logistics companies. They monitor the trajectories of their fleets to better manage their logistics services. GPS and GIS are two key techniques in transportation visualization. More specifically a group of GPS spatial-temporal data on the geographic map forms a trajectory. However, some GPS data of a real shipping trajectory may be missing due to malfunction of equipment or incorrect human operation. The resulting trajectory may contain an unknown section (Figure 1.a., 1.b.) and people can not tell where the vehicle has been to in the time interval corresponding to the unknown section. What is more, further analyses such as cost evaluation can not be done.

To recover the trajectory, the most intuitive thought is to find a path to connect the two ends of the unknown section and there are lots of algorithms (e.g., shortest path algorithms) to build such a path. These algorithms are all based on some objectives. Take shortest path algorithm for example, as the name suggests it tries to find the closest path between an origin-destination (O-D) pair. But the real shipping trajectory may not adhere to these objectives. The vehicle may take a detour to deliver goods to a specific customer located nearby. To resolve this issue, this disclosure discloses a method to complete the shipping trajectory with missing GPS data by using historical data and customers' location data.


Page 02 of 5

The main idea of the method can be illustrated by Figure 2. First, one should select from all incomplete trajectories those should be completed by the disclosed method. This disclosure proposes the following guideline for the selection. One should select those with more than one route between the two ends of the unknown section and having customers located nearby. Then, Hidden Markov Model (HMM) is used to analyze the historical data and predict the missi...