Cover Image

Act, Sense, Act: Learning Non-Markovian Active Perception Strategies from Large-Scale Egocentric Human Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jialiang, Qiao, Yi, Guo, Yunhan, Chen, Changwen, Lian, Wenzhao
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo
by: Pu, Guo, et al.
Published: (2026)

BridgeACT: Bridging Human Demonstrations to Robot Actions via Unified Tool-Target Affordances
by: Han, Yifan, et al.
Published: (2026)

Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
by: Wang, Jing, et al.
Published: (2025)

Microscopic Robots That Sense, Think, Act, and Compute
by: Lassiter, Maya M., et al.
Published: (2025)

Behavior Cloning for Active Perception with Low-Resolution Egocentric Vision
by: Bilic, Anthony, et al.
Published: (2026)

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
by: As, Yarden, et al.
Published: (2024)

SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
by: Li, Jialiang, et al.
Published: (2025)

Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation
by: Wang, Guokang, et al.
Published: (2024)

EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
by: Zheng, Ruijie, et al.
Published: (2026)

EMMA: Scaling Mobile Manipulation via Egocentric Human Data
by: Zhu, Lawrence Y., et al.
Published: (2025)

Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop
by: Kerr, Justin, et al.
Published: (2025)

ActLoc: Learning to Localize on the Move via Active Viewpoint Selection
by: Li, Jiajie, et al.
Published: (2025)

TesserAct: Learning 4D Embodied World Models
by: Zhen, Haoyu, et al.
Published: (2025)

Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception
by: Yang, Jiashu, et al.
Published: (2025)

EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks
by: Li, Yihang, et al.
Published: (2026)

FlowAct: A Proactive Multimodal Human-robot Interaction System with Continuous Flow of Perception and Modular Action Sub-systems
by: Dhaussy, Timothée, et al.
Published: (2024)

Retrieval-Augmented Robots via Retrieve-Reason-Act
by: Temiraliev, Izat, et al.
Published: (2026)

ThermoAct:Thermal-Aware Vision-Language-Action Models for Robotic Perception and Decision-Making
by: Son, Young-Chae, et al.
Published: (2026)

Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Driving
by: Li, Guanzhou, et al.
Published: (2024)

CLASH: Collision Learning via Augmented Sim-to-real Hybridization to Bridge the Reality Gap
by: He, Haotian, et al.
Published: (2026)

EgoMI: Learning Active Vision and Whole-Body Manipulation from Egocentric Human Demonstrations
by: Yu, Justin, et al.
Published: (2025)

Prepare Before You Act: Learning From Humans to Rearrange Initial States
by: Dai, Yinlong, et al.
Published: (2025)

Plan-and-Act using Large Language Models for Interactive Agreement
by: Sasabuchi, Kazuhiro, et al.
Published: (2025)

COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy
by: Li, Qixuan, et al.
Published: (2025)

Non-Overlap-Aware Egocentric Pose Estimation for Collaborative Perception in Connected Autonomy
by: Huang, Hong, et al.
Published: (2025)

Instruct Large Language Models to Drive like Humans
by: Zhang, Ruijun, et al.
Published: (2024)

MolmoAct: Action Reasoning Models that can Reason in Space
by: Lee, Jason, et al.
Published: (2025)

Viewpoint Matters: Dynamically Optimizing Viewpoints with Masked Autoencoder for Visual Manipulation
by: Yi, Pengfei, et al.
Published: (2026)

StreamVLA: Breaking the Reason-Act Cycle via Completion-State Gating
by: Chen, Tongqing, et al.
Published: (2026)

See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations
by: Chen, Guangyan, et al.
Published: (2025)

PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence
by: Lin, Xiaopeng, et al.
Published: (2025)

Teaching Robots Where To Go And How To Act With Human Sketches via Spatial Diagrammatic Instructions
by: Sun, Qilin, et al.
Published: (2024)

When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics
by: Gaus, Johannes A., et al.
Published: (2026)

Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning
by: Omar, Shafeef, et al.
Published: (2025)

When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering
by: Yuan, Jessie, et al.
Published: (2026)

Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?
by: Zhang, Zhongru, et al.
Published: (2026)

Vision in Action: Learning Active Perception from Human Demonstrations
by: Xiong, Haoyu, et al.
Published: (2025)

Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models
by: Ling, Yiran, et al.
Published: (2026)

Learning to Act Robustly with View-Invariant Latent Actions
by: Jeong, Youngjoon, et al.
Published: (2026)

MolmoAct2: Action Reasoning Models for Real-world Deployment
by: Fang, Haoquan, et al.
Published: (2026)