Abstract-In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundation …

Robotics: Science and Systems XXI SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models Delin Qu, Haoming Song, Qizhi Chen, Yuanqi Yao, Xinyi Ye, …

Robotics: Science and Systems XVI Spatial Action Maps for Mobile Manipulation Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Johnny Lee, Szymon Rusinkiewicz, Thomas …

References to abstract concepts in the context of spatial and numeric information like “horizontal line of four blocks”, “farthest three blocks”, “row of blocks in front”, “group of eight blocks”, “ …

In this paper, we investigate spatial mid-level representations that bridge the gap between high-level inputs (e.g., language commands or simple object markers) and the low-level action …

Robotics: Science and Systems XII Efficient Grounding of Abstract Spatial Concepts for Natural Language Interaction with Robot Manipulators Rohan Paul, Jacob Arkin, Nicholas Roy, …

Robotics: Science and Systems XVIII Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization Nathan Hughes, Yun Chang, Luca Carlone Abstract: 3D …

Fig. 8. Training curves for the LargeDivider environment. Our agent trained with spatial action maps (blue) is significantly more sample efficient compared to the baseline that uses steering …

This process of spatial label propagation allows the system to learn view-invariant classifications of scenes and objects. Finally, we use a ring buffer to simulate short term memory.

In the context of spatial environments, different types of problems such as localisation, mapping, navigation or autonomous exploration are typically adressed with specialised methods, often …