Socially Aware Kalman Neural Networks for Trajectory Prediction
This work addresses trajectory prediction challenges in autonomous navigation, representing an incremental/hybrid method combining neural networks with Kalman filtering.
The paper tackles trajectory prediction for robots and autonomous vehicles by proposing Socially Aware Kalman Neural Networks (SAKNN), which embed interaction and Kalman layers to learn from high-variance sensor input and generate low-variance outcomes. On the NGSIM dataset, SAKNN achieves state-of-the-art prediction effectiveness in long-term horizons and significantly improves the signal-to-noise ratio of predicted signals.
Trajectory prediction is a critical technique in the navigation of robots and autonomous vehicles. However, the complex traffic and dynamic uncertainties yield challenges in the effectiveness and robustness in modeling. We purpose a data-driven approach socially aware Kalman neural networks (SAKNN) where the interaction layer and the Kalman layer are embedded in the architecture, resulting in a class of architectures with huge potential to directly learn from high variance sensor input and robustly generate low variance outcomes. The evaluation of our approach on NGSIM dataset demonstrates that SAKNN performs state-of-the-art on prediction effectiveness in a relatively long-term horizon and significantly improves the signal-to-noise ratio of the predicted signal.