Learning Therapist Policy from Therapist-Exoskeleton-Patient Interaction
Authors: Grayson Snyder, Lorenzo Vianello, Levi Hargrove, Matthew L. Elwin, Jose Pons
Organizations: Center for Robotics and Biosystems, Northwestern University, Evanston, IL, USA. · Legs and Walking Lab, Shirley Ryan AbilityLab, Chicago, IL, USA.
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.
Figures & tables
Fig. 1: Learning Therapist Policy from Therapist–Exoskeleton–Patient Interaction. (A) Previously collected dataset of therapist–exoskeleton–patient physical interaction through two lower-limb exoskeletons. The exoskeletons render virtual springs connecting the joint configurations of the patient and therapist. (B) Patient–Therapist Force Field, which takes as input the patient’s and therapist’s strides, extracts latent representations, and learns a force field connecting them in a lower-dimensional space. The model uses an encoder–decoder architecture (both displayed) to reduce dimensionality. (C) Synthetic Therapist, which takes as input the patient’s joint kinematics and predicts the corresponding therapist kinematics. The model uses a Long Short-Term Memory (LSTM) network (displayed) to infer the therapist’s trajectory.
Fig. 2: Top: Latent space representation of each individual dyad. Each dot corresponds to a stride, while the ellipsoids display their distribution. Blue: patient left stride; green: therapist right stride; light blue: patient right stride; light green: therapist left stride. The connection is mirrored (patient left, therapist right). In the middle the resulting force field computed by fitting all the dyads using the GMM. Bottom: Force fields (from left to right): patient hip, therapist hip, patient knee, therapist knee.
rMSE (deg, deg/s)
Train/Validation-Set
Test-Set
Position Avg.
Velocity Avg.
PT 1-8
PT 1-8
4.30±0.41
20.67±1.47
PT 2-8
PT 1
5.93±1.20
25.13±4.54
PT 1,3-8
PT 2
5.77±1.12
25.47±5.03
PT 1,2,4-8
PT 3
6.48±0.67
33.62±3.87
PT 1-3,5-8
PT 4
4.95±1.00
20.66±1.70
TABLE I: Prediction accuracy expressed as mean root Mean-Squared-Error (rMSE) for the LSTM model joint position and joint velocity prediction. We performed a cross-user generalization evaluation by iteratively training on all users (PT i ) except one and testing on the excluded user.
Fig. 3: Example of Synthetic Therapist predictions (predicting 75ms into the future) overlayed with corresponding true therapist data and patient data. On top is presented the Hip Joint, while on the bottom the Knee joint.
Human Robotics Laboratory, Department of Mechanical Engineering, The University of Melbourne · Melbourne School of Health Sciences, The University of Melbourne
Department of Cognitive Robotics, Delft University of Technology, Delft, The Netherlands · Department of Rehabilitation Medicine, Erasmus Medical Center, Rotterdam, The Netherlands.
The authors are with the Departments of Mechanical Engineering, Physical Medicine & Rehabilitation, and Mathematics, the Kahlert School of Computing, and the Robotics Center at the University of Utah, Salt Lake City, UT 84112, USA.