Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors

Sushant Veer, Apoorva Sharma, Marco Pavone

Keywords: trajectory prediction, rule-based planning

TL;DR: We present an approach that combines learning- and rule-based trajectory predictors via recursive Bayesian filtering and demonstrate its ability to deliver more consistent performance than the standalone predictors.

Abstract: Trajectory prediction modules are key enablers for safe and efficient planning of autonomous vehicles (AVs), particularly in highly interactive traffic scenarios. Recently, learning-based trajectory predictors have experienced considerable success in providing state-of-the-art performance due to their ability to learn multimodal behaviors of other agents from data. In this paper, we present an algorithm called multi-predictor fusion (MPF) that augments the performance of learning-based predictors by imbuing them with motion planners that are tasked with satisfying logic-based rules. MPF probabilistically combines learning- and rule-based predictors by mixing trajectories from both standalone predictors in accordance with a belief distribution that reflects the online performance of each predictor. In our results, we show that MPF outperforms the two standalone predictors on various metrics and delivers the most consistent performance.

Student First Author: no

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)