SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecasting
For autonomous driving systems requiring real-time motion forecasting, this work improves robustness to heterogeneous observation windows, a practical bottleneck in streaming settings.
The paper proposes SHARP, a streaming-based motion forecasting framework that maintains accurate predictions under varying observation lengths. It achieves state-of-the-art streaming inference performance on Argoverse 2 with minimal latency.
In dynamic traffic environments, motion forecasting models must be able to accurately estimate future trajectories continuously. Streaming-based methods are a promising solution, but despite recent advances, their performance often degrades when exposed to heterogeneous observation lengths. To address this, we propose a novel streaming-based motion forecasting framework that explicitly focuses on evolving scenes. Our method incrementally processes incoming observation windows and leverages an instance-aware context streaming to maintain and update latent agent representations across inference steps. A dual training objective further enables consistent forecasting accuracy across diverse observation horizons. Extensive experiments on Argoverse 2, nuScenes, and Argoverse 1 demonstrate the robustness of our approach under evolving scene conditions and also on the single-agent benchmarks. Our model achieves state-of-the-art performance in streaming inference on the Argoverse 2 multi-agent benchmark, while maintaining minimal latency, highlighting its suitability for real-world deployment.