DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning

Chiho Choi, Srikanth Malla, Abhishek Patil, Joon Hee Choi
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:49-63, 2021.

Abstract

We propose a Deep RObust Goal-Oriented trajectory prediction Network (DROGON) for accurate vehicle trajectory prediction by considering behavioral intentions of vehicles in traffic scenes. Our main insight is that the behavior (i.e., motion) of drivers can be reasoned from their high level possible goals (i.e., intention) on the road. To succeed in such behavior reasoning, we build a conditional prediction model to forecast goal-oriented trajectories with the following stages: (i) relational inference where we encode relational interactions of vehicles using the perceptual context; (ii) intention estimation to compute the probability distributions of intentional goals based on the inferred relations; and (iii) behavior reasoning where we reason about the behaviors of vehicles as trajectories conditioned on the intentions. To this end, we extend the proposed framework to the pedestrian trajectory prediction task, showing the potential applicability toward general trajectory prediction.

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-choi21a, title = {DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning}, author = {Choi, Chiho and Malla, Srikanth and Patil, Abhishek and Choi, Joon Hee}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {49--63}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/choi21a/choi21a.pdf}, url = {https://proceedings.mlr.press/v155/choi21a.html}, abstract = {We propose a Deep RObust Goal-Oriented trajectory prediction Network (DROGON) for accurate vehicle trajectory prediction by considering behavioral intentions of vehicles in traffic scenes. Our main insight is that the behavior (i.e., motion) of drivers can be reasoned from their high level possible goals (i.e., intention) on the road. To succeed in such behavior reasoning, we build a conditional prediction model to forecast goal-oriented trajectories with the following stages: (i) relational inference where we encode relational interactions of vehicles using the perceptual context; (ii) intention estimation to compute the probability distributions of intentional goals based on the inferred relations; and (iii) behavior reasoning where we reason about the behaviors of vehicles as trajectories conditioned on the intentions. To this end, we extend the proposed framework to the pedestrian trajectory prediction task, showing the potential applicability toward general trajectory prediction.} }
Endnote
%0 Conference Paper %T DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning %A Chiho Choi %A Srikanth Malla %A Abhishek Patil %A Joon Hee Choi %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-choi21a %I PMLR %P 49--63 %U https://proceedings.mlr.press/v155/choi21a.html %V 155 %X We propose a Deep RObust Goal-Oriented trajectory prediction Network (DROGON) for accurate vehicle trajectory prediction by considering behavioral intentions of vehicles in traffic scenes. Our main insight is that the behavior (i.e., motion) of drivers can be reasoned from their high level possible goals (i.e., intention) on the road. To succeed in such behavior reasoning, we build a conditional prediction model to forecast goal-oriented trajectories with the following stages: (i) relational inference where we encode relational interactions of vehicles using the perceptual context; (ii) intention estimation to compute the probability distributions of intentional goals based on the inferred relations; and (iii) behavior reasoning where we reason about the behaviors of vehicles as trajectories conditioned on the intentions. To this end, we extend the proposed framework to the pedestrian trajectory prediction task, showing the potential applicability toward general trajectory prediction.
APA
Choi, C., Malla, S., Patil, A. & Choi, J.H.. (2021). DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:49-63 Available from https://proceedings.mlr.press/v155/choi21a.html.

Related Material