Cycle-Consistent World Models for Domain Independent Latent Imagination

TL;DR

This paper introduces Cycle-Consistent World Models, a novel model-based reinforcement learning approach that learns a shared latent space for different modalities, enabling effective domain adaptation from simulation to real-world autonomous driving.

Contribution

It proposes a new model that embeds multiple modalities in a shared latent space, allowing training on one domain and inference in another, improving domain transfer in autonomous driving.

Findings

Outperforms state-of-the-art domain adaptation methods in CARLA simulations.

Can decode latent representations into semantically coherent observations.

Enables training in simulation and effective inference in real-world scenarios.

Abstract

End-to-end autonomous driving seeks to solve the perception, decision, and control problems in an integrated way, which can be easier to generalize at scale and be more adapting to new scenarios. However, high costs and risks make it very hard to train autonomous cars in the real world. Simulations can therefore be a powerful tool to enable training. Due to slightly different observations, agents trained and evaluated solely in simulation often perform well there but have difficulties in real-world environments. To tackle this problem, we propose a novel model-based reinforcement learning approach called Cycleconsistent World Models. Contrary to related approaches, our model can embed two modalities in a shared latent space and thereby learn from samples in one modality (e.g., simulated data) and be used for inference in different domain (e.g., real-world data). Our experiments using different modalities in the CARLA simulator showed that this enables CCWM to outperform state-of-the-art domain adaptation approaches. Furthermore, we show that CCWM can decode a given latent representation into semantically coherent observations in both modalities.