CORTEXA
← Browse
arxivcs.RO2026-07-19

BoxTwin: Learning Elastoplastic Articulated Object Dynamics from Videos

Heng Zhang, Gehan Zheng, Kaifeng Zhang, Jay Song, Shivansh Patel, Sonny Hu, Yunzhu Li, Changxi Zheng, Peter Yichen Chen

Digital twins enable robots to anticipate and adapt to physical interactions, but existing models struggle with elastoplastic articulated objects (EAOs) that exhibit nonlinear elasticity, plastic yielding, and damage accumulation. We present BoxTwin, an interactive digital twin framework that learns the full dynamics of EAOs from videos. Our pipeline reconstructs the scene, identifies a physics aware constitutive model for each EAO. Experiments on manual folding and dual arm manipulation of EAOs show that BoxTwin accurately tracks joint trajectories and reproduces post contact plastic behavior over long horizons. By integrating video driven reconstruction with elastoplastic damage modeling, BoxTwin advances digital twins toward predictive, adaptive control of deformable articulated objects in unstructured environments.

View free PDFSource page

Related papers

arxivcs.AIcs.RO2026-07-31

LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

Manith Adikari, Bei Peng, Samuele Vinanzi, Angelo Cangelosi

Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, competing objectives, such as performance versus efficiency, where ground-truth reward functions are…

View free PDFSource page
arxivcs.ROcs.AIcs.CV2026-07-15

Learning Physics-Guided Residual Dynamics for Deformable Object Simulation

Shivansh Patel, Kaifeng Zhang, Sanjay Pokkali, Svetlana Lazebnik, Yunzhu Li

Simulating deformable objects is essential for a wide range of robotic manipulation applications, yet accurately predicting their dynamics remains challenging. We propose Physics-Guided Residual Dynamics (PGRD), a hybrid simulation framework that combines the advantages of physic…

View free PDFSource page
arxivcs.ROcs.CV2026-06-30

3D Point World Models: Point Completion Enables More Accurate Dynamics Learning

Skand Peri, Hung Nguyen, Chanho Kim, Li Fuxin, Stefan Lee

Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. However, large video-based dynamics models lack explicit 3D spatial structure and suffer from geometrically inconsistent long-term ro…

View free PDFSource page
arxivcs.ROcs.CV2026-07-08

Dynamic Object Detection and Tracking in Construction: A Fisheye Camera and LiDAR Sensor Fusion Model

Yilong Chen, Huili Huang, Yong K. Cho

Robust dynamic object detection and tracking are essential for enabling robots to operate safely and effectively alongside humans in complex environments such as construction sites. While LiDAR-based SLAM and occupancy grid methods offer viable solutions for detecting and trackin…

View free PDFSource page
arxivcs.RO2026-06-28

Learning Transferable Dynamics Priors from Action to World Modeling

Ze Huang, Jiahui Zhang, Hairuo Liu, Chenxi Zhang, Ran Cheng, Li Zhang

We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive visual scene evolution, the resulting world model captures reusable interaction dynamics beyond appearance-le…

View free PDFSource page
arxivcs.RO2026-07-09

AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning

Iaroslav Kolomiets, Miguel Altamirano Cabrera, Artem Lykov, Jeffrin Sam, Dmitrii Iarchuk, Yara Mahmoud, et al.

Human egocentric video is a scalable supervision source for humanoid policy learning, but current pipelines struggle with hand-object occlusion, oversimplified motion, or specialized capture hardware. We introduce AgenticFocus, a Mixed Reality synthesis pipeline that converts ord…

View free PDFSource page