This study demonstrates that primates can learn to control a brain-machine interface (BMI) to perform reaching and grasping movements by extracting multiple motor parameters (hand position, velocity, gripping force, and muscle electromyograms) from the electrical activity of frontoparietal neuronal ensembles. The researchers used a closed-loop BMI (BMIC) that continuously operated, leading to significant improvements in both model predictions and behavioral performance. Monkeys successfully produced robot reach-and-grasp movements even when their arms did not move, indicating that the BMIC's dynamic properties were incorporated into motor and sensory cortical representations. The study also found that large neuronal ensembles were necessary for high BMIC accuracy, and that functional reorganization occurred in multiple cortical areas during learning. These findings highlight the importance of using large neuronal samples and the potential for BMI-based rehabilitation in restoring complex motor functions in paralyzed patients.This study demonstrates that primates can learn to control a brain-machine interface (BMI) to perform reaching and grasping movements by extracting multiple motor parameters (hand position, velocity, gripping force, and muscle electromyograms) from the electrical activity of frontoparietal neuronal ensembles. The researchers used a closed-loop BMI (BMIC) that continuously operated, leading to significant improvements in both model predictions and behavioral performance. Monkeys successfully produced robot reach-and-grasp movements even when their arms did not move, indicating that the BMIC's dynamic properties were incorporated into motor and sensory cortical representations. The study also found that large neuronal ensembles were necessary for high BMIC accuracy, and that functional reorganization occurred in multiple cortical areas during learning. These findings highlight the importance of using large neuronal samples and the potential for BMI-based rehabilitation in restoring complex motor functions in paralyzed patients.