Neuroprosthetic decoder training as imitation learning

TL;DR

This paper introduces a novel imitation learning framework for training neuroprosthetic decoders, enabling scalable and goal-oriented control of complex effectors like robotic arms using brain-computer interfaces.

Contribution

It adapts the dataset aggregation (DAgger) imitation learning algorithm to brain-computer interfaces and combines it with optimal control for scalable neuroprosthetic training.

Findings

Derived new regret bounds for BCI algorithms

Demonstrated control of a 26-DOF robotic arm in simulation

Provided a scalable framework for naturalistic neuroprosthetic control

Abstract

Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly observable, recent methods have demonstrated value in training the decoder against a surrogate for the user's intended movement. We describe how training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available. Specifically, we describe how a generic imitation learning meta-algorithm, dataset aggregation (DAgger, [1]), can be adapted to train a generic brain-computer interface. By deriving existing learning algorithms for brain-computer interfaces in this framework, we provide a novel analysis of regret (an important metric of learning efficacy) for brain-computer interfaces. This analysis allows us to characterize the space of algorithmic variants and bounds on their regret rates. Existing approaches for decoder learning have been performed in the cursor control setting, but the available design principles for these decoders are such that it has been impossible to scale them to naturalistic settings. Leveraging our findings, we then offer an algorithm that combines imitation learning with optimal control, which should allow for training of arbitrary effectors for which optimal control can generate goal-oriented control. We demonstrate this novel and general BCI algorithm with simulated neuroprosthetic control of a 26 degree-of-freedom model of an arm, a sophisticated and realistic end effector.