Abstract: 

Sim2Real transfer, particularly for manipulation policies relying on RGB images, remains a critical challenge in robotics due to the significant domain shift between synthetic and real-world visual data. In this work, we propose SplatSim, a novel framework that leverages Gaussian Splatting as the primary rendering primitive to reduce the Sim2Real gap for RGB-based manipulation policies. By replacing traditional mesh representations with Gaussian Splats in simulators, SplatSim produces highly photorealistic synthetic data while maintaining the scalability and cost-efficiency of simulation. We demonstrate the effectiveness of our framework by training manipulation policies within SplatSim and deploying them in the real world in a zero-shot manner, achieving an average success rate of 86.25%, compared to 97.5% for policies trained on real-world data.

Committee:
Prof. George Kantor (advisor)
Prof. Abhisesh Silwal (co-advisor)
Prof. Shubham Tulsiani
John (Chung Hee) Kim