Max Robotics — Global Service Robot Directory + US Certification

About

Junhua Li is a leading researcher at the intersection of brain–computer interfaces (BCIs), assistive robotics, and neural signal processing. Their work focuses on enhancing the performance of BCI systems—particularly P300 and asymmetric visual evoked potential (aVEP) spellers—by developing advanced deep learning architectures. Li’s most cited paper (2021, 32 citations) introduced a multiscale convolutional neural network (CNN) that significantly improved P300 detection accuracy and information transmission rate, a critical step toward practical BCI communication tools. In 2022, they extended this multi-scale learning approach to classify gait patterns from multimodal neurophysiological signals, bridging neural decoding with motor rehabilitation. Li has also explored the integration of BCIs with robotic exoskeletons and functional electrical stimulation (FES) for post-stroke rehabilitation, as seen in their 2013 work on causal neurofeedback. Their systematic review on seniors’ adoption of assistive robots (2016) highlights a human-centered perspective, identifying key barriers to technology acceptance. With recent work incorporating attention mechanisms (CBAM-DeepConvNet, 2025) for improved aVEP recognition, Li continues to push the boundaries of real-world BCI applications, aiming to restore mobility and communication for individuals with severe motor disabilities.