Adaptive Output Steps: FlexiSteps Network for Dynamic Trajectory Prediction

TL;DR

The paper presents FlexiSteps Network, a flexible trajectory prediction model that dynamically adjusts output steps based on context, improving accuracy and efficiency for autonomous systems.

Contribution

Introduces FSN with an Adaptive Prediction Module and Dynamic Decoder for dynamic, context-aware trajectory prediction.

Findings

Outperforms fixed-step models on Argoverse and INTERACTION datasets.

Demonstrates improved prediction accuracy and adaptability.

Uses Fréchet distance for geometric similarity evaluation.

Abstract

Accurate trajectory prediction is vital for autonomous driving, robotics, and intelligent decision-making systems, yet traditional models typically rely on fixed-length output predictions, limiting their adaptability to dynamic real-world scenarios. In this paper, we introduce the FlexiSteps Network (FSN), a novel framework that dynamically adjusts prediction output time steps based on varying contextual conditions. Inspired by recent advancements addressing observation length discrepancies and dynamic feature extraction, FSN incorporates an pre-trained Adaptive Prediction Module (APM) to evaluate and adjust the output steps dynamically, ensuring optimal prediction accuracy and efficiency. To guarantee the plug-and-play of our FSN, we also design a Dynamic Decoder(DD). Additionally, to balance the prediction time steps and prediction accuracy, we design a scoring mechanism, which not only introduces the Fr\'echet distance to evaluate the geometric similarity between the predicted trajectories and the ground truth trajectories but the length of predicted steps is also considered. Extensive experiments conducted on benchmark datasets including Argoverse and INTERACTION demonstrate the effectiveness and flexibility of our proposed FSN framework.