Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features
IEEE In this work, we propose a novel approach for integrating rules into traffic agent trajectory prediction. Consideration of rules is important for understanding how people behave --- yet, it cannot be assumed that rules are always followed. To address this challenge, we evaluate different approa...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135520 |
| _version_ | 1826202790144245760 |
|---|---|
| author | Li, Xiao Rosman, Guy Gilitschenski, Igor Vasile, Cristian-Ioan DeCastro, Jonathan A Karaman, Sertac Rus, Daniela |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Li, Xiao Rosman, Guy Gilitschenski, Igor Vasile, Cristian-Ioan DeCastro, Jonathan A Karaman, Sertac Rus, Daniela |
| author_sort | Li, Xiao |
| collection | MIT |
| description | IEEE In this work, we propose a novel approach for integrating rules into traffic agent trajectory prediction. Consideration of rules is important for understanding how people behave --- yet, it cannot be assumed that rules are always followed. To address this challenge, we evaluate different approaches of integrating rules as inductive biases into deep learning-based prediction models. We propose a framework based on generative adversarial networks that uses tools from formal methods, namely signal temporal logic and syntax trees. This allows us to leverage information on rule obedience as features in neural networks and improves prediction accuracy without biasing towards lawful behavior. We evaluate our method on a real-world driving dataset and show improvement in performance over off-the-shelf predictors. |
| first_indexed | 2024-09-23T12:19:02Z |
| format | Article |
| id | mit-1721.1/135520 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:19:02Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1355202023-02-23T16:30:48Z Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features Li, Xiao Rosman, Guy Gilitschenski, Igor Vasile, Cristian-Ioan DeCastro, Jonathan A Karaman, Sertac Rus, Daniela Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Laboratory for Information and Decision Systems IEEE In this work, we propose a novel approach for integrating rules into traffic agent trajectory prediction. Consideration of rules is important for understanding how people behave --- yet, it cannot be assumed that rules are always followed. To address this challenge, we evaluate different approaches of integrating rules as inductive biases into deep learning-based prediction models. We propose a framework based on generative adversarial networks that uses tools from formal methods, namely signal temporal logic and syntax trees. This allows us to leverage information on rule obedience as features in neural networks and improves prediction accuracy without biasing towards lawful behavior. We evaluate our method on a real-world driving dataset and show improvement in performance over off-the-shelf predictors. 2021-10-27T20:23:49Z 2021-10-27T20:23:49Z 2021 2021-04-30T18:05:04Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/135520 en 10.1109/LRA.2021.3062807 IEEE Robotics and Automation Letters Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Other repository |
| spellingShingle | Li, Xiao Rosman, Guy Gilitschenski, Igor Vasile, Cristian-Ioan DeCastro, Jonathan A Karaman, Sertac Rus, Daniela Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features |
| title | Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features |
| title_full | Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features |
| title_fullStr | Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features |
| title_full_unstemmed | Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features |
| title_short | Vehicle Trajectory Prediction Using Generative Adversarial Network With Temporal Logic Syntax Tree Features |
| title_sort | vehicle trajectory prediction using generative adversarial network with temporal logic syntax tree features |
| url | https://hdl.handle.net/1721.1/135520 |
| work_keys_str_mv | AT lixiao vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures AT rosmanguy vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures AT gilitschenskiigor vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures AT vasilecristianioan vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures AT decastrojonathana vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures AT karamansertac vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures AT rusdaniela vehicletrajectorypredictionusinggenerativeadversarialnetworkwithtemporallogicsyntaxtreefeatures |