Sensor Fusion: Gated Recurrent Fusion to Learn Driving Behavior from Temporal Multimodal Data

TL;DR

This paper introduces Gated Recurrent Fusion Units (GRFU), a novel method for end-to-end multimodal sensor fusion that improves understanding of driver behavior in complex urban scenarios, enhancing autonomous navigation accuracy.

Contribution

The paper presents the first end-to-end fusion approach combining sensor and driver policy learning using GRFU, outperforming existing baselines in autonomous driving tasks.

Findings

10% improvement in mAP score for driver behavior classification

20% reduction in mean squared error for steering regression

Superior performance over multimodal and temporal baselines

Abstract

The Tactical Driver Behavior modeling problem requires understanding of driver actions in complicated urban scenarios from a rich multi modal signals including video, LiDAR and CAN bus data streams. However, the majority of deep learning research is focused either on learning the vehicle/environment state (sensor fusion) or the driver policy (from temporal data), but not both. Learning both tasks end-to-end offers the richest distillation of knowledge, but presents challenges in formulation and successful training. In this work, we propose promising first steps in this direction. Inspired by the gating mechanisms in LSTM, we propose gated recurrent fusion units (GRFU) that learn fusion weighting and temporal weighting simultaneously. We demonstrate it's superior performance over multimodal and temporal baselines in supervised regression and classification tasks, all in the realm of autonomous navigation. We note a 10% improvement in the mAP score over state-of-the-art for tactical driver behavior classification in HDD dataset and a 20% drop in overall Mean squared error for steering action regression on TORCS dataset.