HSFM-$\Sigma$nn: Combining a Feedforward Motion Prediction Network and Covariance Prediction

TL;DR

This paper introduces HSFM-$\Sigma$nn, a novel motion prediction method combining model-based transition functions with neural network covariance estimation, demonstrating improved precision and efficiency over classical and social-LSTM methods.

Contribution

The paper presents a new hybrid approach for motion prediction that integrates model-based and learning-based techniques for enhanced accuracy and efficiency.

Findings

Outperforms classical covariance estimation methods

More precise than social-LSTM in motion prediction

Demonstrates improved efficiency in predictions

Abstract

In this paper, we propose a new method for motion prediction: HSFM-$\Sigma$nn. Our proposed method combines two different approaches: a feedforward network whose layers are model-based transition functions using the HSFM and a Neural Network (NN), on each of these layers, for covariance prediction. We will compare our method with classical methods for covariance estimation showing their limitations. We will also compare with a learning-based approach, social-LSTM, showing that our method is more precise and efficient.