MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs
(2023) In IEEE Transactions on Intelligent Vehicles 8(9). p.4223-4236- Abstract
- Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art... (More)
- Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7b1a49ab-63af-4e32-aef1-4d8d8176c7eb
- author
- Westny, Theodor ; Oskarsson, Joel ; Olofsson, Björn LU and Frisk, Erik
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- in
- IEEE Transactions on Intelligent Vehicles
- volume
- 8
- issue
- 9
- pages
- 4223 - 4236
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85161553735
- ISSN
- 2379-8858
- DOI
- 10.1109/TIV.2023.3282308
- project
- ELLIIT B14: Autonomous Force-Aware Swift Motion Control
- RobotLab LTH
- language
- English
- LU publication?
- yes
- id
- 7b1a49ab-63af-4e32-aef1-4d8d8176c7eb
- alternative location
- https://arxiv.org/abs/2302.00735
- date added to LUP
- 2023-06-27 12:19:09
- date last changed
- 2024-02-11 04:06:01
@article{7b1a49ab-63af-4e32-aef1-4d8d8176c7eb, abstract = {{Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics.}}, author = {{Westny, Theodor and Oskarsson, Joel and Olofsson, Björn and Frisk, Erik}}, issn = {{2379-8858}}, language = {{eng}}, number = {{9}}, pages = {{4223--4236}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Transactions on Intelligent Vehicles}}, title = {{MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs}}, url = {{http://dx.doi.org/10.1109/TIV.2023.3282308}}, doi = {{10.1109/TIV.2023.3282308}}, volume = {{8}}, year = {{2023}}, }