A Comparison of Intention Estimation Methods for Decoder Calibration in Intracortical Brain-Computer Interfaces

Objective : Recent reports indicate that making better assumptions about the user's intended movement can improve decoder calibration for intracortical brain–computer interfaces. Several methods now exist for estimating user intent, including an optimal feedback control model, a piecewise-linear feedback control model, ReFIT, and other heuristics. Which of these methods yields the best decoding performance? Methods : Using data from the BrainGate2 pilot clinical trial, we measured how a steady-state velocity Kalman filter decoder was affected by the choice of intention estimation method. We examined three separate components of the Kalman filter: dimensionality reduction, temporal smoothing, and output gain (speed scaling). Results : The decoder's dimensionality reduction properties were largely unaffected by the intention estimation method (the unsmoothed velocity vectors differed by $ in terms of how accurately they pointed at the target and how their speeds decreased near the target). In contrast, the smoothing and gain properties of the decoder were greatly affected ( $> \text{50}\% $ difference in average values). Surprisingly, simulation results show that these differences in gain and smoothing values were largely arbitrary, as all methods failed to optimize the gain and smoothing values to match the task parameters. Conclusion : Our results show that, gain and smoothing differences aside, current intention estimation methods yield nearly equivalent decoders and that simple models of user intent, such as a position error vector (target position minus cursor position), perform comparably to more elaborate models. Our results also highlight that current calibration methods yield arbitrary differences in gain and smoothing properties that can confound decoder comparisons.