mlsanityData to 7 Oct 2026

End-to-End Pixel-Based Deep Active Inference for Body Perception and Action

arXiv 2001.05847 ↗First posted 28 Dec 2019cs.CV cs.AI cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

We present a pixel-based deep active inference algorithm (PixelAI) inspired by human body perception and action. Our algorithm combines the free-energy principle from neuroscience, rooted in variational inference, with deep convolutional decoders to scale the algorithm to directly deal with raw visual input and provide online adaptive inference. Our approach is validated by studying body perception and action in a simulated and a real Nao robot. Results show that our approach allows the robot to perform 1) dynamical body estimation of its arm using only monocular camera images and 2) autonomous reaching to "imagined" arm poses in the visual space. This suggests that robot and human body perception and action can be efficiently solved by viewing both as an active inference problem guided by ongoing sensory input.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 5; 2023: 3; 2024: 4; 2025: 1; 2026: 1.

24 papers.

Sort:

By area:

  1. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  2. 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
  3. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  4. 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
  5. 2021Multimodal VAE Active Inference Controllercited by 21
  6. 2021Branching Time Active Inference: the theory and its generalitycited by 15
  7. 2021Branching Time Active Inference: empirical study and complexity class analysiscited by 9
  8. 2021Adaptation through prediction: multisensory active inference torque controlcited by 6
  9. 2022Disentangling Shape and Pose for Object-Centric Deep Active Inference Modelscited by 6
  10. 2021Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perceptioncited by 5
  11. 2023Deconstructing deep active inferencecited by 5
  12. 2022Learning Policies for Continuous Control via Transition Modelscited by 3
12 more
  1. 2021Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problemcited by 2
  2. 2021Branching Time Active Inference with Bayesian Filteringcited by 2
  3. 2022Multi-Modal and Multi-Factor Branching Time Active Inferencecited by 2
  4. 2021Robot Localization and Navigation through Predictive Processing using LiDARcited by 1
  5. 2024Free Energy Projective Simulation (FEPS): Active inference with interpretabilitycited by 1
  6. 2025Emergence of Goal-Directed Behaviors via Active Inference with Self-Priorcited by 1
  7. 2021Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospectscited by 0
  8. 2023Integrating large language models and active inference to understand eye movements in reading and dyslexiacited by 0
  9. 2024Deep hybrid models: infer and plan in a dynamic worldcited by 0
  10. 2024Dynamic planning in hierarchical active inferencecited by 0
  11. 2024Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RLcited by 0
  12. 2026A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deploymentcited by 0