Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
This addresses the problem of deploying learned robot models in real-world urban navigation by reducing the sim-to-real gap, representing a novel method rather than an incremental improvement.
The paper tackles the sim-to-real gap in robot learning by introducing Vid2Sim, a framework that uses monocular video to create photorealistic and physically interactable 3D simulation environments, resulting in a 31.2% improvement in success rate for urban navigation in digital twins and 68.3% in the real world compared to prior methods.
Sim-to-real gap has long posed a significant challenge for robot learning in simulation, preventing the deployment of learned models in the real world. Previous work has primarily focused on domain randomization and system identification to mitigate this gap. However, these methods are often limited by the inherent constraints of the simulation and graphics engines. In this work, we propose Vid2Sim, a novel framework that effectively bridges the sim2real gap through a scalable and cost-efficient real2sim pipeline for neural 3D scene reconstruction and simulation. Given a monocular video as input, Vid2Sim can generate photorealistic and physically interactable 3D simulation environments to enable the reinforcement learning of visual navigation agents in complex urban environments. Extensive experiments demonstrate that Vid2Sim significantly improves the performance of urban navigation in the digital twins and real world by 31.2% and 68.3% in success rate compared with agents trained with prior simulation methods.