An adaptive-learning regeneration control strategy to enhance the regeneration quality for electric vehicles (EV) is proposed. In recent years, several kinds of EV are equipped with regeneration function. For example, i-MiEV, the EV of Mitsubishi motors, whose energy regeneration ratio is adjusted via the gear shift for standard using, increasing energy regeneration ratio and decreasing energy regeneration ratio. In Taiwan, the TOBE W′ car and Luxgen MPV EV, whose energy regeneration ratios are adjusted by a knob and a shaft, respectively. However, the abovementioned methods are not adaptively to be adjusted to adapt the various customs of drivers. There are some drawbacks, such as manually adjusting energy regeneration ratio and constant energy regeneration ratio, etc. Therefore, an adaptive-learning regeneration control strategy is proposed to account for the above-mentioned drawbacks. The function of the proposed strategy consists of driving mode judge unit, analyzing unit and regeneration judge unit. The driving mode judge unit determines a driving mode according to an accelerator signal, a brake signal and a speed signal from a vehicle. It outputs a coasting duration and coasting information associated with the driving mode to analyzing unit for obtaining acceleration information. The regeneration judge unit obtains target regeneration data containing target vehicle speeds that varying with time based upon the acceleration information and the regeneration reference data. Hence, the adaptive-learning regeneration control strategy can provide an adaptive energy regeneration ratio to the various customs of drivers. Finally, the simulation results show the feasibility of the proposed regeneration control strategy.