Prostheses are becoming more advanced and biomimetic with time, providing additional capabilities to their users. However, prosthetic sensation lags far behind its natural limb counterpart, limiting the use of sensory feedback in prosthetic motion planning and execution. Without actionable sensation, prostheses may never meet the functional requirements to match biological performance. We propose an approach for upper-limb prosthetic object slip prediction and notification, delivered to the wearer through direct nerve stimulation. The method is based on sensory synthesis, training a linear regression of the sensors embedded in a prosthetic hand to predict slip before it occurs. Four participants with transhumeral amputation performed block pulling tasks against increasing resistance, attempting to pull the block as far as possible without slip. These trials were performed with two different prediction notification paradigms. At lower grasp forces, spike notification stimulation reduced the incidence of object slip by 32%, and at higher grasp forces, the maximum achieved pull forces increased by 19% across participants when provided with stimulation proportional to the likelihood of a predicted slip. These results suggest that this approach may be effective in recreating a lost sense of grip stability in the missing limb and may reduce unanticipated slips.
