# Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.12278 · HTML: https://mlsanity.com/paper/2505.12278/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 51 of its 71 references that are in the map.
- First posted on arXiv 18 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Object Motion Guided Human Motion Synthesis](https://mlsanity.com/paper/2309.16237/) (2023)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs](https://mlsanity.com/paper/2402.07872/) (2024)
- [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024)
- [AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System](https://mlsanity.com/paper/2307.04577/) (2023)
- [Open-TeleVision: Teleoperation with Immersive Active Visual Feedback](https://mlsanity.com/paper/2407.01512/) (2024)
- [Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning](https://mlsanity.com/paper/2304.13653/) (2023)
- [Flow as the Cross-Domain Manipulation Interface](https://mlsanity.com/paper/2407.15208/) (2024)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy](https://mlsanity.com/paper/2303.00938/) (2023)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [Efficient Learning on Point Clouds with Basis Point Sets](https://mlsanity.com/paper/1908.09186/) (2019)
- [Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation](https://mlsanity.com/paper/2106.05969/) (2021)
- [Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes](https://mlsanity.com/paper/2211.11744/) (2022)
- [General In-Hand Object Rotation with Vision and Touch](https://mlsanity.com/paper/2309.09979/) (2023)
- [CALM: Conditional Adversarial Latent Models for Directable Virtual Characters](https://mlsanity.com/paper/2305.02195/) (2023)
- [A Deep Hierarchical Approach to Lifelong Learning in Minecraft](https://mlsanity.com/paper/1604.07255/) (2016)
- [PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction](https://mlsanity.com/paper/2312.04393/) (2023)

## Built on by (most cited first, 5 of 5)

- [TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System](https://mlsanity.com/paper/2511.02832/) (2025)
- [Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations](https://mlsanity.com/paper/2602.06643/) (2026)
- [InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2602.06035/) (2026)
- [FOVI: A biologically-inspired foveated interface for deep vision models](https://mlsanity.com/paper/2602.03766/) (2026)
- [Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions](https://mlsanity.com/paper/2609.16683/) (2026)

## Abstract (arXiv)

Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements accordingly. Behaviors like searching for objects, reaching, and hand-eye coordination naturally emerge from the structure of our sensory system. Inspired by these principles, we introduce Perceptive Dexterous Control (PDC), a framework for vision-driven dexterous whole-body control with simulated humanoids. PDC operates solely on egocentric vision for task specification, enabling object search, target placement, and skill selection through visual cues, without relying on privileged state information (e.g., 3D object positions and geometries). This perception-as-interface paradigm enables learning a single policy to perform multiple household tasks, including reaching, grasping, placing, and articulated object manipulation. We also show that training from scratch with reinforcement learning can produce emergent behaviors such as active search. These results demonstrate how vision-driven control and complex tasks induce human-like behaviors and can serve as the key ingredients in closing the perception-action loop for animation, robotics, and embodied AI.