mlsanityData to 7 Oct 2026

Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments

arXiv 2202.09976 ↗First posted 21 Feb 2022cs.RO cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

We show that goal-directed action planning and generation in a teleological framework can be formulated using the free energy principle. The proposed model, which is built on a variational recurrent neural network model, is characterized by three essential features. These are that (1) goals can be specified for both static sensory states, e.g., for goal images to be reached and dynamic processes, e.g., for moving around an object, (2) the model can not only generate goal-directed action plans, but can also understand goals by sensory observation, and (3) the model generates future action plans for given goals based on the best estimate of the current state, inferred using past sensory observations. The proposed model is evaluated by conducting experiments on a simulated mobile agent as well as on a real humanoid robot performing object manipulation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 38 references that are in the map. First posted on arXiv 21 Feb 2022.

Builds on

12 of 38 references.

References · 12

  1. 2018YOLOv3: An Incremental Improvementcited by 2,652
  2. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  3. 2017Hindsight Experience Replaycited by 1,096
  4. 2019Planning with Goal-Conditioned Policiescited by 144
  5. 2021Discovering and Achieving Goals via World Modelscited by 131
  6. 2018Unsupervised Control Through Non-Parametric Discriminative Rewardscited by 102
  7. 2020Deep active inference agents using Monte-Carlo methodscited by 72
  8. 2021Exploration and preference satisfaction trade-off in reward-free learningcited by 12
  9. 2018Learning, Planning, and Control in a Monolithic Neural Event Inference Architecturecited by 8
  10. 2017An active inference implementation of phototaxiscited by 6
  11. 2021Adaptation through prediction: multisensory active inference torque controlcited by 6
  12. 2020Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Networkcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2023On efficient computation in active inferencecited by 15
  2. 2023Habits and goals in synergy: a variational Bayesian framework for behaviorcited by 3
  3. 2025Emergence of Goal-Directed Behaviors via Active Inference with Self-Priorcited by 1
  4. 2024CogNarr Ecosystem: Facilitating Group Cognition at Scalecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
  2. 2025Act2Goal: From World Model To General Goal-conditioned Policy
  3. 2023Toward Open-ended Embodied Tasks Solving
  4. 2025GoalLadder: Incremental Goal Discovery with Vision-Language Models
  5. 2026Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning
  6. 2025Real-World Robot Control by Deep Active Inference With a Temporally Hierarchical World Model
  7. 2026Probabilistic Recurrent Intention Switching Model
  8. 2022Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space