paper-with-me

홈 › Papers

SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting

2024-09-16 · Mohammad Nomaan Qureshi, Sparsh Garg, Francisco Yandun, David Held, George Kantor, Abhisesh Silwal

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 paper, 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. Videos can be found on our project page: https://splatsim.github.io

📄 PDF Abstract BibTeX arXiv:2409.10161

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation

2024-07-05 · Yuxuan Kuang, Junjie Ye, Haoran Geng, Jiageng Mao 외

This work proposes a retrieve-and-transfer framework for zero-shot robotic manipulation, dubbed RAM, featuring generalizability across various objects, environments, and embodiments. Unlike existing approaches that learn…

Human-Object Interaction DetectionRetrieval

Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

2026-06-30 · Zixing Wang, Kausik Sivakumar, Jinghuan Shang, Yafei Hu 외 arxiv

Bridging the sim-to-real gap is a core challenge in deploying learned manipulation policies. Sim-to-real learning is attractive because it can replace expensive real robot demonstrations with scalable synthetic data, yet…

Motion Planning

Local Policies Enable Zero-shot Long-horizon Manipulation

2024-10-29 · Murtaza Dalal, Min Liu, Walter Talbott, Chen Chen 외

Sim2real for robotic manipulation is difficult due to the challenges of simulating complex contacts and generating realistic task distributions. To tackle the latter problem, we introduce ManipGen, which leverages a new …

Motion Planning

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

2026-03-17 · Abhay Deshpande, Maya Guru, Rose Hendrix, Snehal Jauhri 외 arxiv

A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific fine-tuning to bridge the…

NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos

2025-10-09 · Hongyu Li, Lingfeng Sun, Yafei Hu, Duy Ta 외 arxiv

Enabling robots to execute novel manipulation tasks zero-shot is a central goal in robotics. Most existing methods assume in-distribution tasks or rely on fine-tuning with embodiment-matched data, limiting transfer acros…

Video Generation