8 papers
SPEAR: A Simulator for Photorealistic Embodied AI Research
Mike Roberts, Renhan Wang, Rushikesh Zawar +10
Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited gene…
Robot Self-Improvement via Human-Video Dynamics Models
Hanzhi Chen, Anran Zhang, Simon Schaefer +5
A central question in robot learning is how to acquire skills from the kinds of data that humans learn from: passive observation, embodied practice, and the experience of failure.…
HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control
Simon Schaefer, Joshua Näf, Stefan Leutenegger
Robust and accurate perception of humans in their 3D scene context is essential for integrating robots into everyday environments. Existing approaches, however, often fail to predi…
OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
Gang Chen, Sebastián Barbas Laina, Stefan Leutenegger +1
Scene graph alignment establishes object correspondences between two 3D scene graphs constructed from partially overlapping observations. This enables efficient scene understanding…
GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement
Yao Zhong, Hanzhi Chen, Simon Schaefer +2
Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, wh…
Actron3D: Learning Actionable Neural Functions from Videos for Transferable Robotic Manipulation
Anran Zhang, Hanzhi Chen, Yannick Burkhardt +4
We present Actron3D, a framework that enables robots to acquire transferable 6-DoF manipulation skills from just a few monocular, uncalibrated, RGB-only human videos. At its core l…