mlsanityData to 14 Oct 2026

Vision in Action: Learning Active Perception from Human Demonstrations

arXiv 2506.15666 ↗First posted 18 Jun 2025cs.ROcited by 37

Not on the map. Why?

Abstract (arXiv)

We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, and focusing) directly from human demonstrations. On the hardware side, ViA employs a simple yet effective 6-DoF robotic neck to enable flexible, human-like head movements. To capture human active perception strategies, we design a VR-based teleoperation interface that creates a shared observation space between the robot and the human operator. To mitigate VR motion sickness caused by latency in the robot's physical movements, the interface uses an intermediate 3D scene representation, enabling real-time view rendering on the operator side while asynchronously updating the scene with the robot's latest observations. Together, these design elements enable the learning of robust visuomotor policies for three complex, multi-stage bimanual manipulation tasks involving visual occlusions, significantly outperforming baseline systems.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Jun 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 28.

37 papers.

Sort:

By area:

  1. 2026EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the Worldcited by 57
  2. 2025TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection Systemcited by 44
  3. 2025Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Correctionscited by 29
  4. 2025Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understandingcited by 29
  5. 2025ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrationscited by 19
  6. 2025OPENTOUCH: Bringing Full-Hand Touch to Real-World Interactioncited by 15
  7. 2026OAT: Ordered Action Tokenizationcited by 15
  8. 2026SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Roboticscited by 8
  9. 2026ActiveMimic: Egocentric Video Pretraining with Active Perceptioncited by 6
  10. 2026Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategycited by 4
  11. 2026SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Modelscited by 4
  12. 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Actioncited by 4
25 more
  1. 2026E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenescited by 3
  2. 2026TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learningcited by 3
  3. 2025Observer-Actor: Active Vision Imitation Learning with Sparse-View Gaussian Splattingcited by 2
  4. 2026Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulationcited by 2
  5. 2026LIME: Learning Intent-aware Camera Motion from Egocentric Videocited by 2
  6. 2025Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learningcited by 1
  7. 2025Look, Zoom, Understand: The Robotic Eyeball for Embodied Perceptioncited by 1
  8. 2025Real-World Reinforcement Learning of Active Perception Behaviorscited by 1
  9. 2026Tac-DINO: Learning Vision-Tactile Features with Patch Alignmentcited by 1
  10. 2026See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulationcited by 1
  11. 2026Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitationcited by 1
  12. 2026VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Controlcited by 1
  13. 2026Active Stereo-Camera Outperforms Multi-Sensor Setup in ACT Imitation Learning for Humanoid Manipulationcited by 0
  14. 2026The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collectioncited by 0
  15. 2026ModPack: Extensible Teleoperation Interface for Bimanual Mobile Manipulationcited by 0
  16. 2026ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardwarecited by 0
  17. 2026HAP: A Hand-Driven Active Perception Framework for Egocentric Head Motion Predictioncited by 0
  18. 2026INSPECT: Learning Robot View Selection from Assistant Usecited by 0
  19. 2026ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulationcited by 0
  20. 2026Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learningcited by 0
  21. 2026EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Camerascited by 0
  22. 2026ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perceptioncited by 0
  23. 2026TKCAM: Text and Keyframe to Camera Trajectory Generationcited by 0
  24. 2026Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedbackcited by 0
  25. 2026FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAscited by 0