Robust Real-Time Musculoskeletal Modeling Driven by Electromyograms

Robust Opponent Modeling in Real-Time Strategy Games using Bayesian Networks

Opponent modeling is a key challenge in Real-Time Strategy (RTS) games as the environment is adversarial in these games, and the player cannot predict the future actions of her opponent. Additionally, the environment is partially observable due to the fog of war. In this paper, we propose an opponent model which is robust to the observation noise existing due to the fog of war. In order to cope...

A real-time EMG-driven musculoskeletal model of the ankle

The real-time estimation of muscle forces could be a very valuable tool for rehabilitation. By seeing how much muscle force is being produced during rehabilitation, therapists know whether they are working within safe limits in their therapies and patients know if they are producing enough force to expect improvement. This is especially true for rehabilitation of Achilles tendon ruptures where,...

Real-Time Data Driven Wildland Fire Modeling

We are developing a wildland fire model based on semiempirical relations that estimate the rate of spread of a surface fire and post-frontal heat release, coupled with WRF, the Weather Research and Forecasting atmospheric model. A level set method identifies the fire front. Data are assimilated using both amplitude and position corrections using a morphing ensemble Kalman filter. We will use th...

Sensor-Driven Musculoskeletal Dynamic Modeling*

The creation of a human dynamical model useful in upper-limb exoskeleton control remains an open problem. We present a framework that approaches model generation from a “sensor-driven” design perspective that explicitly avoids overfitting parameters and minimally relies on literature values and biological assumptions. Initial results on synthetic data for a simplified model of the elbow indicat...

Modeling event - driven real - time appli ations using DAGs