Online decoding of rat self-paced locomotion speed from EEG using recurrent neural networks

Alejandro de Miguel; Nelson Totah; Uri Maoz

cs.LGFeb 20, 2026

Online decoding of rat self-paced locomotion speed from EEG using recurrent neural networks

Authors: Alejandro de Miguel, Nelson Totah, Uri Maoz

Organizations: Schmid College of Science and Technology, Chapman University, Orange, California, USA · LUCID-AI, Chapman University, Orange, California, USA · Helsinki Institute of Life Science, University of Helsinki, Finland · Neuroscience Center, University of Helsinki, Finland ·

Abstract

$\textit{Objective.}$ Accurate neural decoding of locomotion holds promise for advancing rehabilitation, prosthetic control, and understanding neural correlates of action. Recent studies have demonstrated decoding of locomotion kinematics across species on motorized treadmills. However, efforts to decode locomotion speed in more natural contexts $-$ where pace is self-selected rather than externally imposed $-$ are scarce, generally achieve only modest accuracy, and require intracranial implants. Here, we aim to decode self-paced locomotion speed non-invasively and continuously using cortex-wide EEG recordings from rats. $\textit{Approach.}$ We introduce an asynchronous brain $-$ computer interface (BCI) that processes a stream of 32-electrode skull-surface EEG (0.01 $-$ 45 Hz) to decode instantaneous speed from a non-motorized treadmill during self-paced locomotion in head-fixed rats. Using recurrent neural networks and a dataset of over 133 h of recordings, we trained decoders to map ongoing EEG activity to treadmill speed. $\textit{Main results.}$ Our decoding achieves a correlation of 0.88 ( $R^2$ = 0.78) for speed, primarily driven by visual cortex electrodes and low-frequency ( $< 8$ Hz) oscillations. Moreover, pre-training on a single session permitted decoding on other sessions from the same rat, suggesting uniform neural signatures that generalize across sessions but fail to transfer across animals. Finally, we found that cortical states not only carry information about current speed, but also about future and past dynamics, extending up to 1000 ms. $\textit{Significance.}$ These findings demonstrate that self-paced locomotion speed can be decoded accurately and continuously from non-invasive, cortex-wide EEG. Our approach provides a framework for developing high-performing, non-invasive BCI systems and contributes to understanding distributed neural representations of action dynamics.

Figures & tables

Study	Model	Neural Recordings	Locomotion Control	Target	Decoding Method
Rigosa et al. [ 29 ]	Rodent (rat)	Invasive, M1 (single- and multi-unit)	Enforced and self-paced	Gait phase, discrete locomotion tasks	Classification
Mirfathollahi et al. [ 21 ]	Rodent (rat)	Invasive, M1 (LFP)	Enforced	Speed and slope	Classification
Muzzu et al. [ 22 ]	Rodent (mouse)	Invasive, cerebellum (single-unit)	Self-paced	Speed	Regression
Li et al. [ 16 ]	Rodent (rat)	Invasive, cortex-wide (implanted EEG/epidural)	Self-paced	Slope	Classification
Benisty et al. [ 4 ]	Rodent (mouse)	Invasive (cranial window), dorsal cortex (widefield calcium imaging)	Self-paced	Speed	Regression
Fitzsimmons et al. [ 11 ]	Non-human primate (rhesus macaque)	Invasive, M1 and S1 (single- and multi-unit)	Enforced	Speed	Regression

Table 1: Summary of relevant literature directly addressing decoding of locomotion speed or related locomotor variables from neural signals, across species. Each study listed includes speed decoding as a primary or secondary objective.

Figure 1: Conceptual diagram of the decoding strategy. This schematic is provided for visualization purposes only.

Figure 2: Schematic of training strategies and data splits for assessing generalization of locomotion-related neural signatures across sessions and animals. Models were evaluated under three strategies: single-session training, where decoders were trained from scratch on either 80% or 10% of the target session; zero-shot generalization, where a model trained on a different session with the same animal (cross-session) or a different subject (cross-subject) was directly applied to the target session without further training; and transfer learning, where pre-trained cross-session or cross-subject models were fine-tuned using only 10% of the target session. Each bar represents a data partition: training (TR), validation (V), and test (TS), with numbers indicating the proportion of session data used.

Figure 3: Recurrent neural networks with LSTM units achieve high-precision decoding of treadmill speed on a sample-by-sample basis. A) Decoding performance distribution across sessions for different machine- and deep-learning models. Each histogram represents the performance of individual sessions, measured by correlation (r, left) and coefficient of determination (R², right). The red horizontal lines indicate the median performance across sessions. B) Scatter plot of actual vs. decoded treadmill speeds (at 10ms intervals) on test data for one of the top 5% best-performing sessions. Speeds are decoded using the RNN, which achieved the highest overall performance across sessions. C) Example speed trace from a 20-second segment of the session shown in panel B, comparing actual (in black) and decoded (in red) treadmill speeds over time.

Figure 4: Neural signatures of locomotion are conserved across sessions on multiple days within a single subject. Decoding performance distribution for different RNN models across three training strategies: single-session from scratch (80% training in dark green, 10% training in pink); zero-shot—i.e., using a model trained on another session of the same animal (cross session, in light green) or from another animal (cross animal, in yellow) and fine-tuning (i.e., transfer learning) a pre-trained model (cross-session in orange, cross-subject in blue). Performance is shown for correlation (r, left) and coefficient of determination (R², right). The numbers inside the boxes show the median value of that metric. The top section displays boxplots without outliers, while the bottom section shows violin plots of the outliers separately to improve the visualization of the overall data distribution. (The cross-subject zero-shot strategy, in yellow, did not exhibit outliers in the correlation measurements.)

Figure 5: Visual cortex is the predominant contributor to locomotion decoding. Decoding performance across sessions for RNN models trained and tested on five specific brain regions (diagonal elements) and on all pairs of regions (off-diagonal elements); measured by the median correlation (r, left) and coefficient of determination (R², right).

Figure 6: Decoding performance is primarely driven by low-frequency ( $<$ 8 Hz) oscillations . A) Decoding performance distributions across sessions for RNN models trained and tested on isolated frequency bands. Each histogram represents the performance of individual sessions, measured by correlation (r, left) and coefficient of determination (R², right). The red horizontal lines indicate the median performance across sessions. B) Mean EEG spectra conditioned on speed percentile. Within each session, speed samples were binned into deciles and Welch PSDs were computed from EEG segments corresponding to each bin ( $f\in[0,45]$ Hz). PSDs were averaged across channels, transformed to a frequency-normalized representation ( $f\cdot P(f)$ ) to flatten the $1/f$ slope, and then averaged across sessions (shaded areas: SEM).

Figure 7: EEG encodes information about previous and future treadmill speeds beyond what can be estimated from treadmill readouts alone . Decoding performance across sessions for EEG-based (red), speed-based (blue) and autocorrelation (gray) models estimating previous speeds (left) and future speeds (right). Models were evaluated at discrete time horizons (0, $\pm$ 100, $\pm$ 200, $\pm$ 500, and $\pm$ 1000 ms), with 95% confidence intervals computed from bootstrapped medians across sessions. To aid visualization and analysis, a second-order polynomial was fit to these points, resulting in the smooth curves shown (see Supplementary Tables 13-14 for the actual performance on discrete time horizons). The signal autocorrelation was calculated for all lags, in 10 ms increments, up to $\pm$ 1000 ms without polynomial approximation.

EEG Decoding

Electroencephalography (EEG) decoding maps brain-signal patterns to mental states, stimuli, speech, or intended actions.

See all 208 papers

Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
Jul 13, 2026Jiamian Li, Niall McShane, Attila Korik +6Brain-Computer Interfaces Neural Decoding
Department of Computer Science, University of Bath, Bath, BA2 7AY · Intelligent Systems Research Centre, University of Ulster, BT48 7JL · Bath Institute for the Augmented Human, University of Bath, Bath, BA2 7AY +1
Towards simultaneous decoding of kinetic and kinematic movement parameters during grasp and lift task by noninvasive brain imaging
Jul 27, 2026Parth G. Dangi, Yogesh Kumar MeenaBrain-Computer Interfaces Neural Decoding
Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, India
NeuroAct: Advancing EEG Analysis and Decoding via Dual-Loop Autonomous Research
Oct 18, 2026Wei Xiong, Jiangtong Li, Han Zhao +3EEG Decoding Autonomous Research Agents
Tongji University · Ant Group · Shanghai Jiao Tong University +1

Jul 13, 2026J/K move · Enter open · S save

Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning

Jiamian Li, Niall McShane, Attila Korik, Naomi du Bois+5

Department of Computer Science, University of Bath, Bath, BA2 7AY · Intelligent Systems Research Centre, University of Ulster, BT48 7JL · Bath Institute for the Augmented Human, University of Bath, Bath, BA2 7AY+1

Brain-Computer Interfaces Neural Decoding Residual Learning EEG Decoding RL Post-Training

Open paper AskPDF arXiv

Decoding continuous three-dimensional (3D) motor imagery (MI) using non-invasive electroencephalography (EEG)-based brain--computer interfaces (BCIs) remains challenging due to signal variability and residual decoding errors. Deep learning architectures such as convolutional neural network--long short-term memory (CNN--LSTM) models can capture spatial and temporal dynamics for continuous kinematic decoding; however, systematic residual errors persist in predicted trajectories. We propose a two-stage decoding framework that applies reinforcement learning (RL) to perform residual kinematic correction on the outputs of a CNN--LSTM decoder (CNN--LSTM--RL). The RL agent is trained offline without direct EEG input and instead operates on predicted kinematic trajectories to optimize movement accuracy relative to target trajectories. Decoding performance was quantified using Pearson correlation coefficients (

r

) and Root Mean Square Errors (RMSE) along the

x, y

, and

z

axes. Compared to CNN--LSTM applied alone, CNN--LSTM--RL improved the mean correlation from

0.5076

0.7181

(

p = 0.0005

) in 2D and from

0.6420

0.7780

(

p = 0.0059

) in VR, with relative gains of

41.5\%

and

21.2\%

, respectively. Correspondingly, RMSE was reduced from

0.0890

0.0532

(2D,

p < 0.0001

) and from

0.0714

0.0441

(VR,

p < 0.0001

), representing relative reductions of

40.2\%

and

38.2\%

. These findings demonstrate that this scalable framework enhances 3D BCI MI decoding by correcting kinematic errors via offline residual RL without extra neural data, advancing neurorehabilitation, prosthetics, and virtual interaction.

Abstract

EEG Decoding

Explore similar work

Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning

Towards simultaneous decoding of kinetic and kinematic movement parameters during grasp and lift task by noninvasive brain imaging

NeuroAct: Advancing EEG Analysis and Decoding via Dual-Loop Autonomous Research