A Novel Human-Machine Dual-Task Gaming Framework for Visual-Attention Training
Fengjun Mu, Jingting Zhang, Zonghai Huang, Chen Chen, Chaobin Zou, Guangkui Song, Hong Cheng
AI summary
Problem
Current human-machine interaction systems for brain training often fail to precisely activate target neural pathways, resulting in inefficient and unstandardized rehabilitation outcomes.
Approach
The authors propose a closed-loop co-gaming framework that uses gaze-driven dual tasks to simultaneously engage active and passive attention networks, with a reinforcement learning agent dynamically adjusting task difficulty to maintain optimal neural competition.
Key results
- Gaze-driven dual-task paradigm successfully co-activates active and passive attention networks
- Reinforcement learning strategy dynamically tunes task parameters to sustain neural competition
- Joint EEG and eye-tracking analysis confirms measurable improvements in attention allocation
- Achieves a 15.6% average increase in brain engagement compared to standard staircase strategies
Why it matters
Offers a scalable, neurologically grounded approach for adaptive cognitive training and neurorehabilitation, benefiting clinicians and HMI developers.
Abstract
Efficient brain functional training with rehabil- itation robots has been an important and challenging topic in the human-machine interaction (HMI) field. Adjusting the interaction and gaming behaviors between human and machine to effectively activate the brain’s functional behavior is still a substantial challenge. In this paper, we take the visual- attention training as an example, and propose a novel human- machine co-gaming interaction framework by integrating a dual-task gaming paradigm and a human–machine gaming strategy. It has a remarkable capability of effectively utilizing the gaming characteristics of HMI behaviors and tasks, to effectively and precisely activate the human’s active attention and passive attention for training. Specifically, we design a gaze- driven dual-task gaming paradigm to co-activate the active and passive attention-network competition for systematically engag- ing human visual-attention allocation and training. We fur- ther develop a reinforcement-learning-based human–machine gaming strategy to adjust the task parameters for improving the attention training efficiency. Consequently, we conduct an experiment study with 8 healthy participants, by jointly analyzing participants’ EEG and eye-tracking data through the training process. Results show that our method can achieve improvement of brain engagement by an average of 15.6% over the widely-employed staircase strategy.