An Empirical Study of Active Inference on a Humanoid Robot
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
One of the biggest challenges in robotics is interacting under uncertainty. Unlike robots, humans learn, adapt, and perceive their body as a unity when interacting with the world. Here, we investigate the suitability ofactive inference, a computational model proposed for the brain and governed by the free-energy principle, for robotic body perception and action in a nonsimulated environment. We designed and deployed the algorithm on the humanoid iCub showing how our proposed model enabled the robot to have adaptive body perception and to perform robust upper body reaching and head object tracking behaviors even under high levels of sensor noise and discrepancies between the model and the real robot. Estimation and control are formalized as an inference problem where the body posterior state distribution is approximated by means of the variational free-energy bound, yielding to a minimization of the prediction error. Besides, our study forecasts reactive actions in the presence of sensorimotor conflicts, a mechanism that may be relevant in human body adaptation to uncertain situations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The free-energy principle: a unified brain theory?
Friston, K. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2787 · Cited by 8,120 · cited 3×
“The free-energy principle [5] exploits a tractable solution widely used in machine learning, where, instead of calculating the marginal likelihood, the idea is to minimize the Kullback–Leibler divergence [23] between a reference distribution q(x) and the real p(x|s), in order for the first to be a good approximation o…”
BackgroundMethodThe Bayesian brain: The role of uncertainty in neural coding and computation
Knill, D. C., & Pouget, A. (2004) · Trends in Neurosciences · doi:10.1016/j.tins.2004.10.007 · Cited by 2,588 · cited 1×
“Nowadays, there is a scientific mainstream that describes the inner workings of the brain as those of a Bayesian inference machine [2], [3].”
BackgroundVariational free energy and the Laplace approximation
Friston, K., Mattout, J., Trujillo-Barreto, N., Ashburner, J., & Penny, W. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2006.08.035 · Cited by 880 · cited 1×
“Under the Laplace approximation 3 [26], variational density q ( x ) is assumed to have Gaussian form N ( x | μ, (cid:2)) , simplifying the calculus of F .”
BackgroundAction and behavior: a free-energy formulation
Friston, K. J., Daunizeau, J., Kilner, J., & Kiebel, S. J. (2010) · Biological Cybernetics · doi:10.1007/s00422-010-0364-z · Cited by 866 · cited 5×
“According to this approach, the free-energy bound quan-tifies surprise and it can be optimized by changing current beliefs (perception) or by acting on the environment (action) to adjust the difference between reality and prediction [6].”
BackgroundMethodInfluentialThe Markov blankets of life: autonomy, active inference and the free energy principle
Kirchhoff, M., Parr, T., Palacios, E., Friston, K., & Kiverstein, J. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0792 · Cited by 473 · cited 1×
“Active inference would allow inferring and simultaneously adapting the body to uncertain situations [8], something just partially solved in robotics.”
BackgroundBeal, M. J., & Ghahramani, Z. (2003) · Bayesian Statistics 7 · doi:10.1093/oso/9780198526155.003.0025 · Cited by 458
Uncertainty, epistemics and active inference
Parr, T., & Friston, K. J. (2017) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0376 · Cited by 252 · cited 1×
“Under this approach, sensorimotor integration (visual, tactile, proprioceptive, etc.) occurs in a Bayesian optimal taking into account sensors and motor uncertainties [4].”
BackgroundGeneral duality between optimal control and estimation
Todorov, E. (2008) · 2008 47th IEEE Conference on Decision and Control · doi:10.1109/cdc.2008.4739438 · Cited by 248 · cited 1×
“Active inference [5], [6], an alternative theory to perception and action duality of optimal feedback control [7], proposes Fig.”
BackgroundA Novel Adaptive Controller for Robot Manipulators Based on Active Inference
Pezzato, C., Ferrari, R., & Corbato, C. H. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2974451 · Cited by 104 · cited 3×
“Recently, an active inference controller, working in the joint space for an industrial 7-DOF robot arm, was tested and compared to an adaptive controller, obtaining compelling results [20].”
BackgroundMethodResult
Research works printed but not linked: 22
- Helmholtz, 1867, Handbuch Der Physiologischen Optik
- 10.1098/rstb.2005.1622 · DOI · Paper page
- 10.1109/IROS.2017.8205942 · DOI
- 10.1109/LRA.2016.2645124 · DOI · Paper page
- 10.3389/frobt.2016.00007 · DOI
- Gaskett, Online learning of a motor map for humanoid robot reaching, 1
- 10.1016/j.robot.2013.12.011 · DOI
- 10.1371/journal.pone.0163713 · DOI · Paper page
- 10.1109/TCDS.2016.2627820 · DOI
- 10.1109/IROS.2018.8593684 · DOI · Paper page
- 10.7551/ecal_a_011 · DOI
- 10.1098/rsif.2016.0616 · DOI · Paper page
- Lanillos, Active inference with function learning for robot body perception, 1
- 10.1214/aoms/1177729694 · DOI · Paper page
- 10.1016/j.jmp.2017.09.004 · DOI · Paper page
- Kingma, 2013, Auto-encoding variational bayes
- 10.1145/1774674.1774683 · DOI · Paper page
- 10.1109/DEVLRN.2017.8329790 · DOI
- 10.1093/oxfordhb/9780198735410.013.45 · DOI
- 10.1109/DEVLRN.2018.8761005 · DOI
- 10.1016/S0893-6080(02)00214-9 · DOI
- 10.1109/70.538972 · DOI · Paper page
Cited by
Bayesian mechanics for stationary processes
Da Costa, L., Friston, K., Heins, C., & Pavliotis, G. A. (2021) · Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rspa.2021.0518 · Cited by 63
Active Inference and Behavior Trees for Reactive Action Planning and Execution in Robotics
Pezzato, C., Corbato, C. H., Bonhof, S., & Wisse, M. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3226144 · Cited by 44
“Active inference is a neuroscientific theory that has recently shown its potential in control engineering and robotics [8], [9], [10], [11], particularly in real-world experiments for low-level adaptive control [12], [13].”
BackgroundReward maximization through discrete active inference
Da Costa, L., Sajid, N., Parr, T., Friston, K., & Smith, R. (2023) · Neural Computation · doi:10.1162/neco_a_01574 · Cited by 35
Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?
Millidge, B., Salvatori, T., Song, Y., Bogacz, R., & Lukasiewicz, T. (2022) · arXiv · doi:10.48550/arxiv.2202.09467 · Cited by 31
Hierarchical generative modelling for autonomous robots
Yuan, K., Sajid, N., Friston, K., & Li, Z. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00752-z · Cited by 23
“Our model is a particular instantiation of such hierarchical motor control models, as contrasted by the prior studies 30, 31, 12, 32, 33 .”
MethodResult
Metadata
- Authors
- Oliver, G., Lanillos, P., & Cheng, G.
- Venue
- IEEE Transactions on Cognitive and Developmental Systems
- Published
- 2022-06
- Volume
- 14
- Issue
- 2
- Pages
- 462-471
- ISSN
- 2379-8920 (ISSN-L)
- 2379-8939
- OpenAlex
- W3120701370
- Cited by
- 63
- References
- 12
- FWCI
- 5.25
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- SELFCEPTION Project EU Horizon 2020 Programme (741941)
- EU’s Erasmus+ Programme
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: An Empirical Study of Active Inference on a Humanoid Robot. https://app.cochat.ai/papers/10.1109/tcds.2021.3049907
- The paper
- Oliver, G., Lanillos, P., & Cheng, G. (2022). An Empirical Study of Active Inference on a Humanoid Robot. IEEE Transactions on Cognitive and Developmental Systems. https://doi.org/10.1109/tcds.2021.3049907
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.