Characterizing the onset and offset of motor imagery during passive arm movements induced by an upper-body exoskeleton

Kanishka Mitra; Frigyes Samuel Racz; Satyam Kumar; Ashish D. Deshpande; José del R. Millán

cs.ROMar 21, 2026

Characterizing the onset and offset of motor imagery during passive arm movements induced by an upper-body exoskeleton

Authors: Kanishka Mitra, Frigyes Samuel Racz, Satyam Kumar, Ashish D. Deshpande, José del R. Millán

Organizations: Chandra Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA. · Department of Neurology, The University of Texas at Austin, Austin, TX, USA. · Walker Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX, USA.

Abstract

Two distinct technologies have gained attention lately due to their prospects for motor rehabilitation: robotics and brain-machine interfaces (BMIs). Harnessing their combined efforts is a largely uncharted and promising direction that has immense clinical potential. However, a significant challenge is whether motor intentions from the user can be accurately detected using non-invasive BMIs in the presence of instrumental noise and passive movements induced by the rehabilitation exoskeleton. As an alternative to the straightforward continuous control approach, this study instead aims to characterize the onset and offset of motor imagery during passive arm movements induced by an upper-body exoskeleton to allow for the natural control (initiation and termination) of functional movements. Ten participants were recruited to perform kinesthetic motor imagery (MI) of the right arm while attached to the robot, simultaneously cued with LEDs indicating the initiation and termination of a goal-oriented reaching task. Using electroencephalogram signals, we built a decoder to detect the transition between i) rest and beginning MI and ii) maintaining and ending MI. Offline decoder evaluation achieved group average onset accuracy of 60.7% and 66.6% for offset accuracy, revealing that the start and stop of MI could be identified while attached to the robot. Furthermore, pseudo-online evaluation could replicate this performance, forecasting reliable online exoskeleton control in the future. Our approach showed that participants could produce quality and reliable sensorimotor rhythms regardless of noise or passive arm movements induced by wearing the exoskeleton, which opens new possibilities for BMI control of assistive devices.

Figures & tables

Fig. 1 : Experimental setup and task paradigm pipeline. Panel A shows a representative subject and the Harmony robotic exoskeleton (a. LED indicating trial phases, b. Harmony exoskeleton, c. EEG cap), while panel B shows the timeline of a task trial (see text for details).

Fig. 2 : Grand average spectrogram from C3 region showing changes in spectral power over the course of task trials. Data was obtained by averaging over all trials and all subjects.


	MI-onset		MI-offset
ID	train	test	train	test

1	$61.7\%$	$57.0\%$	$70.4\%$	$64.7\%$
2	$71.1\%$	$69.3\%$	$71.2\%$	$68.1\%$
3	$67.3\%$	$65.9\%$	$67.5\%$	$63.7\%$

TABLE I : Classification accuracies

Fig. 3 : Grand average classification accuracies over time during the 1-second epochs. Shaded areas indicate standard deviation, and the dashed black line denotes the chance level ( $54.4\%$ ).

Fig. 4 : Top 10 most discriminative feature frequencies. The color indicates how frequently a given feature was selected as one of the top 10 for the MI-onset (left) and MI-offset (right) distinctions.

Fig. 5 : Average spectrograms of the two subjects (Left: subject 2; Right: subject 8) re-recorded with the task protocol that includes control trials. The top and bottom rows correspond to the test and control trials, respectively.

Fig. 6 : Time-resolved performance of Riemannian classifier. The charts show the grand average of predicted labels over time in the relevant segments of task trials. Top: RS (class 0) vs. bMI (class 1). Bottom: dMI (class 0) vs. eMI (class 1). As a reference, the horizontal dashed lines indicate chance level ( $54.4\%$ ).

Explore similar work

Mar 17, 2026

Real-Time Decoding of Movement Onset and Offset for Brain-Controlled Rehabilitation Exoskeleton

Robot-assisted therapy can deliver high-dose, task-specific training after neurologic injury, but most systems act primarily at the limb level-engaging the impaired neural circuits only indirectly-which remains a key barrier to truly contingent, neuroplasticity-targeted rehabilitation. We address this gap by implementing online, dual-state motor imagery control of an upper-limb exoskeleton, enabling goal-directed reaches to be both initiated and terminated directly from non-invasive EEG. Eight participants used EEG to initiate assistance and then volitionally halt the robot mid-trajectory. Across two online sessions, group-mean hit rates were 61.5% for onset and 64.5% for offset, demonstrating reliable start-stop command delivery despite instrumental noise and passive arm motion. Methodologically, we reveal a systematic, class-driven bias induced by common task-based recentering using an asymmetric margin diagnostic, and we introduce a class-agnostic fixation-based recentering method that tracks drift without sampling command classes while preserving class geometry. This substantially improves threshold-free separability (AUC gains: onset +56%, p = 0.0117; offset +34%, p = 0.0251) and reduces bias within and across days. Together, these results help bridge offline decoding and practical, intention-driven start-stop control of a rehabilitation exoskeleton, enabling precisely timed, contingent assistance aligned with neuroplasticity goals while supporting future clinical translation.

Kanishka Mitra, Satyam Kumar, Frigyes Samuel Racz +3

Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA. · Chandra Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA. · Department of Neurology, The University of Texas at Austin, Austin, TX, USA. +3

Brain-Computer Interfaces Assistive Robotics MI Classification Electroencephalography

Ask PDF

Jul 27, 2026

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

Brain-machine interfaces (BMIs) can assist individuals with limited mobility, such as stroke survivors or amputees. One of the key challenges in developing BMIs is expanding their usability and control, which can be achieved by accurately decoding multiple kinematic and kinetic parameters. To address this, we propose three regression models: partial least squares regressor, multilayered perceptron, and attention based regressor, to decode multiple movement parameters from EEG signals. We evaluated these models on the WAY EEG GAL dataset, focusing on their performance under subject specific and subject independent conditions with two strategies: a single model for all parameters and a baseline with separate models for each parameter. Among all regressors, the attention based regressor achieved the best performance, with an

R^2

of 0.8 and a latency of 29.2 milliseconds, demonstrating significant improvement in simultaneous multi parameter decoding. However, its performance dropped for single parameter decoding. The multi layered perceptron showed more consistent but lower accuracy across both decoding types (

R^2

= 0.49). These findings highlight the potential of attention based models for real time multi command BMI systems and contribute to the development of more intuitive control devices.

Parth G. Dangi, Yogesh Kumar Meena

Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, India

Brain-Computer Interfaces Neural Decoding EEG Decoding Multi-Task Learning

Ask PDF

Feb 24, 2026

Event-Driven On-Sensor Locomotion Mode Recognition Using a Shank-Mounted IMU with Embedded Machine Learning for Exoskeleton Control

This work presents a wearable human activity recognition (HAR) system that performs real-time inference directly inside a shank-mounted inertial measurement unit (IMU) to support low-latency control of a lower-limb exoskeleton. Unlike conventional approaches that continuously stream raw inertial data to a microcontroller for classification, the proposed system executes activity recognition at the sensor level using the embedded Machine Learning Core (MLC) of the STMicroelectronics LSM6DSV16X IMU, allowing the host microcontroller to remain in a low-power state and read only the recognized activity label from IMU registers. While the system generalizes to multiple human activities, this paper focuses on three representative locomotion modes - stance, level walking, and stair ascent - using data collected from adult participants. A lightweight decision-tree model was configured and deployed for on-sensor execution using ST MEMS Studio, enabling continuous operation without custom machine learning code on the microcontroller. During operation, the IMU asserts an interrupt when motion or a new classification is detected; the microcontroller wakes, reads the MLC output registers, and forwards the inferred mode to the exoskeleton controller. This interrupt-driven, on-sensor inference architecture reduces computation and communication overhead while preserving battery energy and improving robustness in distinguishing level walking from stair ascent for torque-assist control.

Mohammadsaleh Razmi, Iman Shojaei

Align Technology, Inc., San Jose, CA 95134, USA

Wearable Sensing Human Activity Recognition On-Device Inference

Ask PDF