Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network
Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for safe and efficient operation of connected automated vehicles under complex driving situations. Two main challenges for this task are to handle the varying number of heterogeneous target agents and joi...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162966 |
| _version_ | 1824455385624346624 |
|---|---|
| author | Mo, Xiaoyu Huang, Zhiyu Xing, Yang Lv, Chen |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Mo, Xiaoyu Huang, Zhiyu Xing, Yang Lv, Chen |
| author_sort | Mo, Xiaoyu |
| collection | NTU |
| description | Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for safe and efficient operation of connected automated vehicles under complex driving situations. Two main challenges for this task are to handle the varying number of heterogeneous target agents and jointly consider multiple factors that would affect their future motions. This is because different kinds of agents have different motion patterns, and their behaviors are jointly affected by their individual dynamics, their interactions with surrounding agents, as well as the traffic infrastructures. A trajectory prediction method handling these challenges will benefit the downstream decision-making and planning modules of autonomous vehicles. To meet these challenges, we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT). Our framework is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, agents' dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edge-featured heterogeneous graph and processed by the designed HEAT network to extract interaction features. Besides, the map features are shared across all agents by introducing a selective gate-mechanism. And finally, the trajectories of multiple agents are predicted simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy. The achieved final displacement error (FDE@3sec) is 0.66 meter under urban driving, demonstrating the feasibility and effectiveness of the proposed approach. |
| first_indexed | 2025-02-19T03:37:22Z |
| format | Journal Article |
| id | ntu-10356/162966 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:37:22Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1629662022-11-14T02:35:38Z Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network Mo, Xiaoyu Huang, Zhiyu Xing, Yang Lv, Chen School of Mechanical and Aerospace Engineering Engineering::Mechanical engineering Trajectory Prediction Connected Vehicles Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for safe and efficient operation of connected automated vehicles under complex driving situations. Two main challenges for this task are to handle the varying number of heterogeneous target agents and jointly consider multiple factors that would affect their future motions. This is because different kinds of agents have different motion patterns, and their behaviors are jointly affected by their individual dynamics, their interactions with surrounding agents, as well as the traffic infrastructures. A trajectory prediction method handling these challenges will benefit the downstream decision-making and planning modules of autonomous vehicles. To meet these challenges, we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT). Our framework is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, agents' dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edge-featured heterogeneous graph and processed by the designed HEAT network to extract interaction features. Besides, the map features are shared across all agents by introducing a selective gate-mechanism. And finally, the trajectories of multiple agents are predicted simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy. The achieved final displacement error (FDE@3sec) is 0.66 meter under urban driving, demonstrating the feasibility and effectiveness of the proposed approach. Agency for Science, Technology and Research (A*STAR) Nanyang Technological University This work was supported in part by A*STAR Singapore under Grant W1925d0046 and in part by Start-Up Grant, Nanyang Technological University, Singapore. 2022-11-14T02:35:37Z 2022-11-14T02:35:37Z 2022 Journal Article Mo, X., Huang, Z., Xing, Y. & Lv, C. (2022). Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network. IEEE Transactions On Intelligent Transportation Systems, 23(7), 9554-9567. https://dx.doi.org/10.1109/TITS.2022.3146300 1524-9050 https://hdl.handle.net/10356/162966 10.1109/TITS.2022.3146300 2-s2.0-85124208718 7 23 9554 9567 en W1925d0046 IEEE Transactions on Intelligent Transportation Systems © 2022 IEEE. All rights reserved. |
| spellingShingle | Engineering::Mechanical engineering Trajectory Prediction Connected Vehicles Mo, Xiaoyu Huang, Zhiyu Xing, Yang Lv, Chen Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network |
| title | Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network |
| title_full | Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network |
| title_fullStr | Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network |
| title_full_unstemmed | Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network |
| title_short | Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network |
| title_sort | multi agent trajectory prediction with heterogeneous edge enhanced graph attention network |
| topic | Engineering::Mechanical engineering Trajectory Prediction Connected Vehicles |
| url | https://hdl.handle.net/10356/162966 |
| work_keys_str_mv | AT moxiaoyu multiagenttrajectorypredictionwithheterogeneousedgeenhancedgraphattentionnetwork AT huangzhiyu multiagenttrajectorypredictionwithheterogeneousedgeenhancedgraphattentionnetwork AT xingyang multiagenttrajectorypredictionwithheterogeneousedgeenhancedgraphattentionnetwork AT lvchen multiagenttrajectorypredictionwithheterogeneousedgeenhancedgraphattentionnetwork |