HanoiWorld : A Joint Embedding Predictive Architecture BasedWorld Model for Autonomous Vehicle Controller

TL;DR

HanoiWorld introduces a JEPA-based world model for autonomous vehicles that leverages RNNs for long-term planning, improving safety and planning effectiveness in highway environments, with promising results compared to state-of-the-art methods.

Contribution

The paper presents HanoiWorld, a novel JEPA-based world model utilizing RNNs for improved long-term planning and safety in autonomous driving.

Findings

Effective long-term planning demonstrated in highway environments

Improved safety-awareness compared to baseline methods

Competitive collision rates with state-of-the-art approaches

Abstract

Current attempts of Reinforcement Learning for Autonomous Controller are data-demanding while the results are under-performed, unstable, and unable to grasp and anchor on the concept of safety, and over-concentrating on noise features due to the nature of pixel reconstruction. While current Self-Supervised Learningapproachs that learning on high-dimensional representations by leveraging the JointEmbedding Predictive Architecture (JEPA) are interesting and an effective alternative, as the idea mimics the natural ability of the human brain in acquiring new skill usingimagination and minimal samples of observations. This study introduces Hanoi-World, a JEPA-based world model that using recurrent neural network (RNN) formaking longterm horizontal planning with effective inference time. Experimentsconducted on the Highway-Env package with difference enviroment showcase the effective capability of making a driving plan while safety-awareness, with considerablecollision rate in comparison with SOTA baselines