Robot-assisted therapy can deliver high-dose, task-specific training after neurologic injury, but most systems act primarily at the limb level-engaging the impaired neural circuits only indirectly-which remains a key barrier to truly contingent, neuroplasticity-targeted rehabilitation. We address this gap by implementing online, dual-state motor imagery control of an upper-limb exoskeleton, enabling goal-directed reaches to be both initiated and terminated directly from non-invasive EEG. Eight participants used EEG to initiate assistance and then volitionally halt the robot mid-trajectory. Across two online sessions, group-mean hit rates were 61.5% for onset and 64.5% for offset, demonstrating reliable start-stop command delivery despite instrumental noise and passive arm motion. Methodologically, we reveal a systematic, class-driven bias induced by common task-based recentering using an asymmetric margin diagnostic, and we introduce a class-agnostic fixation-based recentering method that tracks drift without sampling command classes while preserving class geometry. This substantially improves threshold-free separability (AUC gains: onset +56%, p = 0.0117; offset +34%, p = 0.0251) and reduces bias within and across days. Together, these results help bridge offline decoding and practical, intention-driven start-stop control of a rehabilitation exoskeleton, enabling precisely timed, contingent assistance aligned with neuroplasticity goals while supporting future clinical translation.

翻译：机器人辅助疗法可在神经损伤后提供高强度、任务特异性训练，但多数系统主要作用于肢体层面——仅间接激活受损神经回路——这仍是实现真正偶联性、靶向神经可塑性康复的关键障碍。为解决这一不足，我们实现了上肢外骨骼的在线双态运动想象控制，使目标导向的伸展运动既能通过非侵入性脑电图直接启动，也能直接终止。八名参与者使用脑电图启动辅助，并在轨迹中途自主停止机器人运动。在两次在线实验中，组平均命中率在起始阶段为61.5%，终止阶段为64.5%，证明在仪器噪声和被动手臂运动干扰下仍能实现可靠的启停指令传递。在方法论层面，我们通过非对称边界诊断揭示了常见基于任务的重心校正方法所引发的系统性、类别驱动偏差，并提出了一种类别无关的注视点重心校正方法。该方法能在不采样指令类别的情况下追踪漂移，同时保持类别几何结构。这显著提升了无阈值分离性能（AUC增益：起始阶段+56%，p = 0.0117；终止阶段+34%，p = 0.0251），并减少了日内与跨日偏差。综合而言，这些成果有助于弥合离线解码与康复外骨骼实用化、意图驱动的启停控制之间的鸿沟，为实现精准定时、符合神经可塑性目标的偶联性辅助提供了支持，并为未来临床转化奠定了基础。