This work presents that, only using non-invasively captured brain signals, a person can navigate an electric wheelchair with no serious training for a long term. Only two electrodes are set on the scalp non-invasively to detect a P300 EEG signal and a reference signal. A simple signal processing interprets the measured signals to decide a movement direction of the wheelchair. The whole devices are loaded on the wheelchair. No external system is required. The experimental results demonstrate the feasibility of the simple BCI processing to achieve reasonable performance.