Brain-machine interface (BMI) systems give users direct neural control of robotic, communication, or functional electrical stimulation systems. As BMI systems begin transitioning from laboratory settings into activities of daily living, an important goal is to develop neural decoding algorithms that can be calibrated with a minimal burden on the user, provide stable control for long periods of time, and can be responsive to fluctuations in the decoder’s neural input space (e.g. neurons appearing or being lost amongst electrode recordings). These are significant challenges for static neural decoding algorithms that assume stationary input/output relationships. Here we use an actor-critic reinforcement learning architecture to provide an adaptive BMI controller that can successfully adapt to dramatic neural reorganizations, can maintain its performance over long time periods, and which does not require the user to produce specific kinetic or kinematic activities to calibrate the BMI. Two marmoset monkeys used the Reinforcement Learning BMI (RLBMI) to successfully control a robotic arm during a two-target reaching task. The RLBMI was initialized using random initial conditions, and it quickly learned to control the robot from brain states using only a binary evaluative feedback regarding whether previously chosen robot actions were good or bad. The RLBMI was able to maintain control over the system throughout sessions spanning multiple weeks. Furthermore, the RLBMI was able to quickly adapt and maintain control of the robot despite dramatic perturbations to the neural inputs, including a series of tests in which the neuron input space was deliberately halved or doubled.

By estimating an evaluative feedback directly from the user, the HRL control algorithm may provide an efficient method for autonomous adaptation of neuroprosthetic systems. This method may enable the user to teach the controller the desired behavior using only a simple feedback signal.

Background The common marmoset (Callithrix jacchus) has been proposed as a suitable bridge between rodents and larger primates. They have been used in several types of research including auditory, vocal, visual, pharmacological and genetics studies. However, marmosets have not been used as much for behavioral studies. New Method Here we present data from training 12 adult marmosets for behavioral neuroscience studies. We discuss the husbandry, food preferences, handling, acclimation to laboratory environments and neurosurgical techniques. In this paper, we also present a custom built “scoop” and a monkey chair suitable for training of these animals. Results The animals were trained for three tasks: 4 target center-out reaching task, reaching tasks that involved following robot actions, and touch screen task. All animals learned the center-out reaching task within 1–2 weeks whereas learning reaching tasks following robot actions task took several months of behavioral training where the monkeys learned to associate robot actions with food rewards. Comparison to Existing Method We propose the marmoset as a novel model for behavioral neuroscience research as an alternate for larger primate models. This is due to the ease of handling, quick reproduction, available neuroanatomy, sensorimotor system similar to larger primates and humans, and a lissencephalic brain that can enable implantation of microelectrode arrays relatively easier at various cortical locations compared to larger primates. Conclusion All animals were able to learn behavioral tasks well and we present the marmosets as an alternate model for simple behavioral neuroscience tasks.

Here we demonstrate how a marmoset monkey can use a reinforcement learning (RL) Brain-Machine Interface (BMI) to effectively control the movements of a robot arm for a reaching task. In this work, an actor-critic RL algorithm used neural ensemble activity in the monkey's motor cortext to control the robot movements during a two-target decision task. This novel approach to decoding offers unique advantages for BMI control applications. Compared to supervised learning decoding methods, the actor-critic RL algorithm does not require an explicit set of training data to create a static control model, but rather it incrementally adapts the model parameters according to its current performance, in this case requiring only a very basic feedback signal. We show how this algorithm achieved high performance when mapping the monkey's neural states (94%) to robot actions, and only needed to experience a few trials before obtaining accurate real-time control of the robot arm. Since RL methods responsively adapt and adjust their parameters, they can provide a method to create BMIs that are robust against perturbations caused by changes in either the neural input space or the output actions they generate under different task requirements or goals.

Current neuroprosthetics rely on stable, high quality recordings from chronically implanted microelectrode arrays (MEAs) in neural tissue. While chronic electrophysiological recordings and electrode failure modes have been reported from rodent and larger non-human primate (NHP) models, chronic recordings from the marmoset model have not been previously described. The common marmoset is a New World primate that is easier to breed and handle compared to larger NHPs and has a similarly organized brain, making it a potentially useful smaller NHP model for neuroscience studies. This study reports recording stability and signal quality of MEAs chronically implanted in behaving marmosets. Six adult male marmosets, trained for reaching tasks, were implanted with either a 16-channel tungsten microwire array (five animals) or a Pt-Ir floating MEA (one animal) in the hand-arm region of the primary motor cortex (M1) and another MEA in the striatum targeting the nucleus accumbens (NAcc). Signal stability and quality was quantified as a function of array yield (active electrodes that recorded action potentials), neuronal yield (isolated single units during a recording session), and signal-to-noise ratio (SNR). Out of 11 implanted MEAs, nine provided functional recordings for at least three months, with two arrays functional for 10 months. In general, implants had high yield, which remained stable for up to several months. However, mechanical failure attributed to MEA connector was the most common failure mode. In the longest implants, signal degradation occurred, which was characterized by gradual decline in array yield, reduced number of isolated single units, and changes in waveform shape of action potentials. This work demonstrates the feasibility of longterm recordings from MEAs implanted in cortical and deep brain structures in the marmoset model. The ability to chronically record cortical signals for neural prosthetics applications in the common marmoset extends the potential of this model in neural interface research.