SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915039852625920 |
|---|---|
| author | Wagner, Royden Tas, Ömer Sahin Steiner, Marlon Konstantinidis, Fabian Königshof, Hendrik Klemp, Marvin Fernandez, Carlos Stiller, Christoph |
| author_facet | Wagner, Royden Tas, Ömer Sahin Steiner, Marlon Konstantinidis, Fabian Königshof, Hendrik Klemp, Marvin Fernandez, Carlos Stiller, Christoph |
| contents | Self-driving vehicles rely on multimodal motion forecasts to effectively interact with their environment and plan safe maneuvers. We introduce SceneMotion, an attention-based model for forecasting scene-wide motion modes of multiple traffic agents. Our model transforms local agent-centric embeddings into scene-wide forecasts using a novel latent context module. This module learns a scene-wide latent space from multiple agent-centric embeddings, enabling joint forecasting and interaction modeling. The competitive performance in the Waymo Open Interaction Prediction Challenge demonstrates the effectiveness of our approach. Moreover, we cluster future waypoints in time and space to quantify the interaction between agents. We merge all modes and analyze each mode independently to determine which clusters are resolved through interaction or result in conflict. Our implementation is available at: https://github.com/kit-mrt/future-motion |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01537 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts Wagner, Royden Tas, Ömer Sahin Steiner, Marlon Konstantinidis, Fabian Königshof, Hendrik Klemp, Marvin Fernandez, Carlos Stiller, Christoph Computer Vision and Pattern Recognition Robotics Self-driving vehicles rely on multimodal motion forecasts to effectively interact with their environment and plan safe maneuvers. We introduce SceneMotion, an attention-based model for forecasting scene-wide motion modes of multiple traffic agents. Our model transforms local agent-centric embeddings into scene-wide forecasts using a novel latent context module. This module learns a scene-wide latent space from multiple agent-centric embeddings, enabling joint forecasting and interaction modeling. The competitive performance in the Waymo Open Interaction Prediction Challenge demonstrates the effectiveness of our approach. Moreover, we cluster future waypoints in time and space to quantify the interaction between agents. We merge all modes and analyze each mode independently to determine which clusters are resolved through interaction or result in conflict. Our implementation is available at: https://github.com/kit-mrt/future-motion |
| title | SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2408.01537 |