KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Tasks

TL;DR

This paper introduces KARNet, a neural network architecture augmented with Kalman filtering to improve learning of world models in autonomous driving, demonstrating enhanced performance in simulation and real-world scenarios.

Contribution

The paper proposes a novel Kalman filter augmented recurrent neural network that integrates physics-based vehicle models into deep learning for better world modeling in autonomous driving.

Findings

Improved accuracy in traffic flow prediction.

Enhanced performance in imitation and reinforcement learning tasks.

Effective use of real-world and simulated datasets.

Abstract

Autonomous driving has received a great deal of attention in the automotive industry and is often seen as the future of transportation. The development of autonomous driving technology has been greatly accelerated by the growth of end-to-end machine learning techniques that have been successfully used for perception, planning, and control tasks. An important aspect of autonomous driving planning is knowing how the environment evolves in the immediate future and taking appropriate actions. An autonomous driving system should effectively use the information collected from the various sensors to form an abstract representation of the world to maintain situational awareness. For this purpose, deep learning models can be used to learn compact latent representations from a stream of incoming data. However, most deep learning models are trained end-to-end and do not incorporate any prior knowledge (e.g., from physics) of the vehicle in the architecture. In this direction, many works have explored physics-infused neural network (PINN) architectures to infuse physics models during training. Inspired by this observation, we present a Kalman filter augmented recurrent neural network architecture to learn the latent representation of the traffic flow using front camera images only. We demonstrate the efficacy of the proposed model in both imitation and reinforcement learning settings using both simulated and real-world datasets. The results show that incorporating an explicit model of the vehicle (states estimated using Kalman filtering) in the end-to-end learning significantly increases performance.