Grand Challenge on Closed-loop Neural Decoding for Motor Control of non-Human Primates

Abstract

Brain Machine Interfaces (BMI) that record signals from the motor cortex and translates these “thoughts” to action provides hope to paralyzed people. A high-accuracy decoder is needed for a seamless user experience. At the same time, it needs to be compact and low-power to support its integration in an implant to enable the compression required in wireless implantable BMIs. Hence, a model with a good trade-off between accuracy and resource requirement is desirable and was the subject of the 2024 Grand Challenge at BioCAS based on prerecorded datasets. However, in real-life, the usage of braincontrolled prosthetics, the result of decoding is presented to the user through visual feedback resulting in a closed-loop system. Hence, in the IEEE BioCAS 2025 conference, we organized the first grand challenge on Closed-Loop Neural Decoding (http://1.117.17.41/neural-decoding-grand-challenge/). The challenge requires users to move a cursor from a given start position to a target position based on spikes generated from a brain simulator. The evaluations were performed using the recently developed Neurobench software suite for benchmarking neuromorphic systems and the top 3 teams are invited to present their works in the IEEE BioCAS 2025.