paper-with-me

Papers

Bridging the Sim2Real Gap: Vision Encoder Pre-Training for Visuomotor Policy Transfer

2025-01-26 · Samuel Biruduganti, Yash Yardi, Lars Ankile

Simulation offers a scalable and efficient alternative to real-world data collection for learning visuomotor robotic policies. However, the simulation-to-reality, or "Sim2Real" distribution shift -- introduced by employing simulation-trained policies in real-world environments -- frequently prevents successful policy transfer. This study explores the potential of using large-scale pre-training of vision encoders to address the Sim2Real gap. We examine a diverse collection of encoders, evaluating their ability to (1) extract features necessary for robot control while (2) remaining invariant to task-irrelevant environmental variations. We quantitatively measure the encoder's feature extraction capabilities through linear probing and its domain invariance by computing distances between simulation and real-world embedding centroids. Additional qualitative insights are provided through t-SNE plots and GradCAM saliency maps. Findings suggest that encoders pre-trained on manipulation-specific datasets generally outperform those trained on generic datasets in bridging the Sim2Real gap. https://github.com/yyardi/Bridging-the-Sim2Real-Gap

📄 PDF Abstract BibTeX arXiv:2501.16389

Code (1)

yyardi/bridging-the-sim2real-gap 공식 구현 pytorch

Similar Papers 제목 키워드 기반

GaussFly: Contrastive Reinforcement Learning for Visuomotor Policies in 3D Gaussian Fields

2026-04-06 · Yuhang Zhang, Mingsheng Li, Yujing Shang, Zhuoyuan Yu 외 arxiv

Learning visuomotor policies for Autonomous Aerial Vehicles (AAVs) relying solely on monocular vision is an attractive yet highly challenging paradigm. Existing end-to-end learning approaches directly map high-dimensiona…

Representation LearningReinforcement Learning

CHOP: Counterfactual Human Preference Labels Improve Obstacle Avoidance in Visuomotor Navigation Policies

2026-03-02 · Gershom Seneviratne, Jianyu An, Vaibhav Shende, Sahire Ellahy 외 arxiv

Visuomotor navigation policies have shown strong perception-action coupling for embodied agents, yet they often struggle with safe navigation and dynamic obstacle avoidance in complex real-world environments. We introduc…

Contrastive Action-Image Pre-training for Visuomotor Control

2026-06-15 · Yuvan Sharma, Dantong Niu, Anirudh Pai, Zekai Wang 외 arxiv

Existing vision encoders for robotics face a fundamental bottleneck: robotic datasets lack the scale necessary for large-scale pre-training. Prior work circumvents this data scarcity by turning to internet-scale image an…

DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization

2025-11-27 · Yikai Tang, Haoran Geng, Jindou Jia, Yuxuan Hu 외 arxiv

Imitation learning has emerged as a crucial approach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy generalization. However, existing methods t…

Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling

2023-01-03 · Penghao Wu, Li Chen, Hongyang Li, Xiaosong Jia 외

Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit,…

Autonomous DrivingDecision Making