Trajectory Imputation and Generation using Simple Probabilistic Language Models
Trajectory Imputation and Generation using Simple Probabilistic Language Models
Trajectory data collected by GPS has found many critical applications. Unfortunately, most trajectory datasets have missing data due to technical problems or due to the sampling strategy used.
Trajectory imputation is the task of filling in the gaps in actual trajectories by computing points that fit "naturally" within existing trajectories. Considering that both (discretized) trajectories and natural language are essentially sequences of symbols, we explore the use of probabilistic language models for trajectory imputation.
Using a grid-based representation of the space, we convert trajectory points into tokens corresponding to the grid cell where they appear and train models of different sizes. We report experiments on a real dataset of over 500,000 taxi trips, showing that we can accurately fill gaps of up to 2km between GPS observations with 83% precision. These results are comparable to approaches using much more computationally demanding Large Language Models based on transformers.
Time permitting, we will also show how the approach for trajectory imputation can be extended to generate arbitrarily large realistic trajectory datasets using real trajectory samples, which can then be used, for instance, for training machine learning models.
* Research done in cooperation with Hayat Sultan Mohammed and Denilson Barbosa and presented at IEEE MDM 2024 and ACM SIGSPATIAL 2024 GeoSim Workshop.
Speaker
Mario Nascimento
Mario Nascimento’s primary research interests lie in the domain of spatiotemporal data management. He has authored over 100 publications, accruing more than 5,200 citations with an h-index of 35 as of late 2025. Currently, he serves as Professor Emeritus at the University of Alberta, where he previously served as Department Chair for 6 years.
Throughout his academic career, Mario has mentored over 50 graduate students and postdoctoral fellows and held visiting professorships in Germany, Brazil, Singapore, and Denmark. His extensive academic service includes various roles within the database community. Most recently, he served as the Program co-Chair for ACM SIGSPATIAL (2022–2023) and as its General co-Chair in 2024.
Monash University values the privacy of every individual's personal information and is committed to the protection of that information from unauthorised use and disclosure except where permitted by law. For information about the handling of your personal information please see Data Protection and Privacy Procedure and the relevant Data Protection and Privacy Collection Statement that applies to you depending on the nature of your interaction with us.
If you have any questions about how Monash University is collecting and handling your personal information, please contact our Data Protection and Privacy Office at dataprotectionofficer@monash.edu.