摘要This paper presents a novel approach to modelling carangiform fish-like swimming motion for multi-joint robotic fish so that they can obtain fish-like behaviours and mimic the body motion of carangiform fish. A given body motion function of fish swimming is firstly converted to a tail motion function which describes the tail motion relative to the head. Then, the tail motion function is discretized into a series of tail postures over time. Thirdly, a digital approximation method calculates the taming angles of joints in the tail to approximate each tail posture; and finally, these angles are grouped into a look-up table, or re-gressed to a time-dependent function, for practically controlling the tail motors in a multi-joint robotic fish. The paper made three contributions: tail motion relative to the head, an error function for digital approximation and regressing a look-up table for online optimization. To prove the feasibility of the proposed methodology, two basic swimming motion patterns, cruise straight and C-shape sharp turning, are modelled and implemented in our robotic fish. The experimental results show that the relative tail motion and the approximation error function are good choices and the proposed method is feasible.