Wagner, Royden (KIT), Tas, Omer Sahin (FZI Research Center for Information Technology), Steiner, Marlon (Karlsruhe Institute of Technology), Konstantinidis, Fabian (CARIAD SE), Königshof, Hendrik (FZI Research Center for Information Technology), Klemp, Marvin (KIT), Fernandez Lopez, Carlos (Karlsruhe Institute of Technology (KIT)), Stiller, Christoph (Karlsruhe Institute of Technology)

SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecasts

Scheduled for presentation during the Regular Session "Sensing, Vision, and Perception II" (WeBT2), Wednesday, September 25, 2024, 15:30−15:50, Salon 5

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Abstract

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