Control Interfaces & Assistive Layer for a Powered Back Exoskeleton
Multi-Modal Sensor Fusion (Xsens IMUs + Cometa sEMG), automated headless OpenSim biomechanical ground-truth generation ($L5/S1$ lumbar moments), causal signal conditioning, and a full-stack deep learning neural training studio.
Work-Related Musculoskeletal Disorders (WRMSDs) represent over 60% of occupational ailments, primarily caused by excessive lumbar spinal compression at the $L5/S1$ joint during repetitive material lifting.
Active exoskeletons can relieve spinal loads, but predicting human joint torque in real time requires navigating a fragmented bottleneck: manual coordinate alignment, complex OpenSim Inverse Dynamics solvers, and non-standardized multi-channel sensor files.
Architected an automated, full-stack biomechanical engineering workbench in Python and C++ that ingests multi-trial workbooks, applies strictly causal second-order section filters, and executes headless OpenSim Inverse Kinematics and Inverse Dynamics without GUI intervention.
Built an interactive browser studio to visually design neural architectures (CNN, LSTM, GRU), stream live GPU training loss over WebSockets, and benchmark continuous lumbar torque predictions against biomechanical ground truth.
Full-Stack Biomechanics & Neural Studio
Automated simulation pipeline and modular neural network training platform
Automated Headless OpenSim Pipeline
IK & Inverse DynamicsAutomates subject model scaling from static upright posture, auto-detects heading yaw ($\theta_{\text{yaw}}$) by maximizing sagittal lumbar variance, and solves Inverse Dynamics to generate 3D continuous lumbar torques ($\tau_{\text{ext}}$, $\tau_{\text{bend}}$, $\tau_{\text{rot}}$).
Causal Signal Conditioning & FFT
Zero-Lookahead4th-order Butterworth SOS bandpass [20–450 Hz] eliminating DC baseline drift, rolling Median Absolute Deviation (MAD) spike rejection, RMS envelope downsampling to 60 Hz kinematics, and live FFT spectrum comparison.
Neural Network Builder & GPU Telemetry
CNN-LSTM • WebSocketsVisual architecture synthesizer for 1D CNNs, Stacked LSTMs, and GRUs with sliding time-window controls. WebSocket streams live loss curves directly from NVIDIA GPU instances with early stopping and automatic checkpoint packaging.
Torque Prediction & Generalization
Quantitative BenchmarksRigorous evaluation across 7 participants: robust continuous torque tracking on seen subject trials ($R^2 \approx 0.85\text{--}0.92$) and comprehensive analysis of the zero-shot cross-subject generalization gap on unseen participants.
Technical Specifications & Subsystems
Detailed breakdown of acquisition, physics pipelines, and software infrastructure
Multi-Modal Acquisition & 19-Sheet Datasheet Architecture
Sensor IngestionSynchronized electrophysiology and 3D full-body motion capture
Recorded an experimental cohort of 7 participants across symmetrical box lifts (8–22 kg), asymmetrical diagonal lifts, and sustained static flexion until physical fatigue. Integrated 17 wireless Xsens IMUs (60 Hz) streaming 23 anatomical segment coordinates alongside 8–10 Cometa wireless sEMG electrodes (1980 Hz) positioned on bilateral lumbar stabilizers (Longissimus, Iliocostalis, Multifidus, and Rectus Abdominis).
Headless OpenSim C++/Python Physics Solver
Ground Truth KineticsAutomated musculoskeletal model scaling and inverse dynamics
Programmatic OpenSim pipeline executing in the background without manual GUI interaction. Scales generic 37-DOF musculoskeletal models based on static subject segment lengths, evaluates candidate global heading orientations ($0^\circ, \pm 90^\circ, 180^\circ$) to maximize sagittal variance, and computes ground-truth 3D joint torques ($\tau_{\text{extension}}$, $\tau_{\text{bending}}$, $\tau_{\text{rotation}}$).
Strictly Causal DSP & Artifact Rejection
Real-Time ReadinessZero-lookahead filtering preserving causal timeline for physical exoskeletons
Standard non-causal two-pass filtering (`filtfilt`) causes temporal data leakage and cannot run on real-time wearable hardware. Our platform enforces strictly single-pass causal Second-Order Sections (SOS) bandpass filtering, rolling MAD outlier rejection with causal forward-fill, and RMS envelope downsampling to 60 Hz kinematics.
Full-Stack Neural Studio & WebSocket Telemetry
Web InterfaceFastAPI async backend streaming live GPU metrics to React 18 frontend
Provides an intuitive multi-step wizard: multi-file dataset stacking, interactive channel selection across 100+ telemetry variables, visual DSP graph ordering, dynamic Keras model compilation, and live per-epoch loss telemetry streaming over WebSockets.
Data Pipeline Optimizations & Docker Orchestration
DevOps & PerformanceSub-millisecond columnar caching and reproducible containerization
Converts heavy multi-sheet Excel files to compressed Apache Parquet for sub-millisecond column slicing, implements NumPy zero-copy sliding window views to prevent RAM exhaustion during window extraction, and packages the entire platform in Docker with NVIDIA Container Toolkit GPU passthrough.
Interested in my machine learning & robotics thesis?
I would be glad to discuss biomechanical modeling, neural network architectures, and full-stack software design.