paper-with-me

Papers

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

2024-10-10 · Haoyi Zhu, Honghui Yang, Yating Wang, Jiange Yang, LiMin Wang, Tong He

In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla Vision Transformer (ViT) with intrinsic spatial understanding. We present the most comprehensive evaluation of embodied representation learning to date, covering 268 tasks across 8 simulators with diverse policies in both single-task and language-conditioned multi-task scenarios. The results are compelling: SPA consistently outperforms more than 10 state-of-the-art representation methods, including those specifically designed for embodied AI, vision-centric tasks, and multi-modal applications, while using less training data. Furthermore, we conduct a series of real-world experiments to confirm its effectiveness in practical scenarios. These results highlight the critical role of 3D spatial awareness for embodied representation learning. Our strongest model takes more than 6000 GPU hours to train and we are committed to open-sourcing all code and model weights to foster future research in embodied representation learning. Project Page: https://haoyizhu.github.io/spa/.

📄 PDF Abstract BibTeX arXiv:2410.08208

Code (1)

haoyizhu/realrobot 공식 구현 pytorch

Tasks

GPUNeural RenderingRepresentation Learning

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence

2026-07-14 · Zhishan Zou, Guoyan Sun, Zhiwei Wei, Jiancheng Pan 외 arxiv

Autonomous UAV systems increasingly rely on multimodal large language models (MLLMs) to operate in complex real-world environments. Such embodied scenarios require not only understanding the surrounding space but also ma…

SPAN-Nav: Generalized Spatial Awareness for Versatile Vision-Language Navigation

2026-03-10 · Jiahang Liu, Tianyu Xu, Jiawei Chen, Lu Yue 외 arxiv

Recent embodied navigation approaches leveraging Vision-Language Models (VLMs) demonstrate strong generalization in versatile Vision-Language Navigation (VLN). However, reliable path planning in complex environments rema…

Vision-Language Navigation

Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning

2025-08-21 · Yijun Liu, Yuwei Liu, Yuan Meng, Jieheng Zhang 외 arxiv

Vision-centric hierarchical embodied models have demonstrated strong potential. However, existing methods lack spatial awareness capabilities, limiting their effectiveness in bridging visual plans to actionable control i…

Spatial ReasoningVideo Generation

XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments

2026-04-20 · Kangan Qian, ChuChu Xie, Yang Zhong, Jingrui Pang 외 arxiv

Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud pipelines rely on generic vision-langua…

Reinforcement LearningSpatial Reasoning

CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment

2026-04-07 · Li Kang, Yutao Fan, Rui Li, Heng Zhou 외 arxiv

Multi-agent embodied systems hold promise for complex collaborative manipulation, yet face critical challenges in spatial coordination, temporal reasoning, and shared workspace awareness. Inspired by human collaboration …