Learning Varying Physical Therapist-Patient Interactions for Robot-mediated Upper Limb Task-Specific Training

Jia Quan Loh; Vincent Crocher; Marlena Klaic; Denny Oetomo; Ying Tan

cs.ROAug 17, 2026

Learning Varying Physical Therapist-Patient Interactions for Robot-mediated Upper Limb Task-Specific Training

Authors: Jia Quan Loh, Vincent Crocher, Marlena Klaic, Denny Oetomo, Ying Tan

Organizations: Human Robotics Laboratory, Department of Mechanical Engineering, The University of Melbourne · Melbourne School of Health Sciences, The University of Melbourne

Abstract

Upper extremity motor function recovery is positively linked to Task-Specific Training (TST) and sufficient therapy dosage. Rehabilitation robots can increase TST dosage via controlled, repetitive treatment and free therapists to simultaneously manage other patients, but it has yet to demonstrate significant benefits over conventional treatment. This is potentially linked to inaccurate robotic representation of personalised physical therapist-patient interaction and lack of practice variability during TST. Hence, we advocate for robotic interventions that preserve the personalised physical therapist-patient interactions when delivering TST for patients across varying practise conditions. We propose a Learning-from-Demonstration framework using Task-Parameterised Gaussian Mixture Models (TPGMM) to learn personalised physical therapist-patient interaction in Task-Specific exercises, mapping patient joint kinematics to therapist-applied torques using few demonstrations. The model is generalised to reconstruct therapist torques in new task variations. The framework was evaluated on physical interactions from 14 mock "therapist-patient" pairs over three tasks of increasing complexity, each with six variations. A benchmark comparison against a Look-Up Table was conducted. The results show both methods reproducing interactions in unseen task variations that deviate slightly from the actual interaction, with TPGMM slightly outperforming LUT. Both methods reproduced interactions that gets increasingly closer to the actual interaction as task complexity increases.

Figures & tables

Ref.	RHHI Configuration	Input	Learning Method	Desired Output	Variation
[ 14 ]	T-R-P	Measured end-effector position	GMM	End-effector force	✗
[ 17 ]	T-R-R-P	Measured end-effector force	GMM-based non-linear system	End-effector force derivative	✗
[ 18 ]	T-R-P	Measured end-effector position	GMM-based Impedance model	End-effector force	✗
[ 19 ]	T-R-R-P	Measured patient end-effector kinematics	GMM	Patient end-effector position	✗
[ 20 ]	T-R-P	Measured end-effector kinematics	Potential Field Function	End-effector force	✗
[ 13 ]	T-R-P	Measured joint positions	Look-Up Table	Joint torques	✗

TABLE I: Learning Therapist Interaction Profiles from Demonstration— Summary of literature.

Fig. 1: Task-specific exercises performed in the study. TP refers to task points where the joint kinematics are extracted from for the task frames. 1. , 2. and 3. refers to each patient persona.

	Patient History		Task Description			Sub-tasks
P1	FMA-UE	8/66	Task	Reaching towards a cup and return		1-1	Move wrist from home (TP0) to cup (TP1)
	MMSE	28/30	Variations	Cup Distance	Close	1-2	Move wrist from cup (TP1) to home (TP2)
	Diagnosis	Dense right hemiparesis			Far
		Left middle cerebral artery stroke (6 weeks)		Shoulder Rotation	External rotation
	Presentation	Severe weakness in right upper extremity			No rotation
		Cannot initiate active grasp and voluntary movement against gravity			Internal rotation

TABLE II: Patient personas (P

\#

) with associated task descriptions.

Fig. 2: 1. Construction of TPU braces - PETG cuffs sensorised to measure force-torque interactions and placement of sensors on the wearer’s body. Sensors holders house the IMU trackers on the right upper and forearm, with the force-torque sensors fixed on top. 2. Tight attachments on the wearer’s body using buckle-velcro straps and kinesiology tapes. Foam padding is layered underneath the brace to increase surface contact with the skin. 3. Common interactions “therapist” apply on the “patient” when constrained to only interact with the sensorised cuffs (highlighted in red), identified during the experiment.

		RM-ANOVA
		Persona						Method						Persona * Method
Measure	Case	SS	df1	df2	MS	F	P-val	SS	df1	df2	MS	F	P-val	SS	df1	df2	MS	F	P-val
$\varepsilon$	Val	0.348	2	26	0.174	15.59	0.0***	0.133	1	13	0.133	7.623	0.016*	0.003	2	26	0.002	0.162	0.766
$\varepsilon$	Gen	0.612	2	26	0.306	7.965	0.002**	0.164	1	13	0.164	8.134	0.014*	0.013	2	26	0.006	0.609	0.551
$\Delta\tau_{peak}$	Val	1.032	2	26	0.516	15.069	0.000***	5.694	1	13	5.694	74.026	0.000***	0.667	2	26	0.333	11.752	0.000***
$\Delta\tau_{peak}$	Gen	0.265	2	26	0.133	1.95	0.163	2.01	1	13	2.01	24.514	0.000***	0.592	2	26	0.296	8.785	0.005**

TABLE III: Top: Repeated-measures ANOVA for Effects of Persona, Method and Interaction. Bottom: Holm-corrected pairwise comparisons between independent within-subject factor levels. (Val: Seen Variations, Gen: Unseen Variations)

Fig. 3: A: Variability of therapist behaviour,

\boldsymbol{\tau}_{\zeta=\{18,2,1\}}

in the trunk, shoulder and elbow. The dotted line represents the mid-range profile

\boldsymbol{m}_{\zeta=\{18,2,1\}}

and the shaded region represents the behaviour boundaries. B: Reconstructed torques from TPGMM (TPGMM) and vector search (LUT) for

\boldsymbol{\tau}_{n=\{18,2,1,3\}}

Fig. 4: Distribution of outcome measures for both candidate methods between the validation (white background) and generalisation (grey background) cases across patient personas. The therapist’s own variability of behaviour is shown as reference.

Explore similar work

Learning Therapist Policy from Therapist-Exoskeleton-Patient Interaction
Mar 2, 2026Grayson Snyder, Lorenzo Vianello, Levi Hargrove +2Assistive Robotics Human-Robot Interaction
Center for Robotics and Biosystems, Northwestern University, Evanston, IL, USA. · Legs and Walking Lab, Shirley Ryan AbilityLab, Chicago, IL, USA.
Therapist-Robot-Patient Physical Interaction is Worth a Thousand Words: Enabling Intuitive Therapist Guidance via Remote Haptic Control
Feb 25, 2026Beatrice Luciani, Alex van den Berg, Matti Lang +2Human-Robot Interaction Robot Teleoperation
Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands · Department of Rehabilitation Medicine, Erasmus Medical Center, Rotterdam, The Netherlands.
See, Learn, Assist: Safe and Self-Paced Robotic Rehabilitation via Video-Based Learning from Demonstration
Mar 15, 2026Ali Alabbas, Camillo Murgia, Joanne Regan +1Assistive Robotics Robotic Control
Faculty of Mechanical Engineering, Atlantic Technological University, Galway, Ireland. · Department of Health and Nutritional Science, Atlantic Technological University, Sligo, Ireland.

Mar 2, 2026J/K move · Enter open · S save

Learning Therapist Policy from Therapist-Exoskeleton-Patient Interaction

Grayson Snyder, Lorenzo Vianello, Levi Hargrove, Matthew L. Elwin+1

Center for Robotics and Biosystems, Northwestern University, Evanston, IL, USA. · Legs and Walking Lab, Shirley Ryan AbilityLab, Chicago, IL, USA.

Assistive Robotics Human-Robot Interaction Policy Learning Robot Imitation Learning Ankle Exoskeleton Control

Open paper AskPDF arXiv

Post-stroke rehabilitation is often necessary for patients to regain proper walking gait. However, the typical therapy process can be exhausting and physically demanding for therapists, potentially reducing therapy intensity, duration, and consistency over time. We propose a Patient-Therapist Force Field (PTFF) to visualize therapist responses to patient kinematics and a Synthetic Therapist (ST) machine learning model to support the therapist in dyadic robot-mediated physical interaction therapy. The first encodes patient and therapist stride kinematics into a shared low-dimensional latent manifold using a Variational Autoencoder (VAE) and models their interaction through a Gaussian Mixture Model (GMM), which learns a probabilistic vector field mapping patient latent states to therapist responses. This representation visualizes patient-therapist interaction dynamics to inform therapy strategies and robot controller design. The latter is implemented as a Long Short-Term Memory (LSTM) network trained on patient-therapist interaction data to predict therapist-applied joint torques from patient kinematics. Trained and validated using leave-one-out cross-validation across eight post-stroke patients, the model was integrated into a ROS-based exoskeleton controller to generate real-time torque assistance based on predicted therapist responses. Offline results and preliminary testing indicate the potential of their use as an alternative approach to post-stroke exoskeleton therapy. The PTFF provides understanding of the therapist's actions while the ST frees the human therapist from the exoskeleton, allowing them to continuously monitor the patient's nuanced condition.

Abstract

Explore similar work

Learning Therapist Policy from Therapist-Exoskeleton-Patient Interaction

Therapist-Robot-Patient Physical Interaction is Worth a Thousand Words: Enabling Intuitive Therapist Guidance via Remote Haptic Control

See, Learn, Assist: Safe and Self-Paced Robotic Rehabilitation via Video-Based Learning from Demonstration