Abstract:This paper considers the problem of data driven iterative learning control (DDILC) for a class of nonaffine nonlinear systems with random iterative lengths, data quantization and random packet dropouts. Resorting to pseudopartial derivative dynamic technique, such systems fall into time varying linear form. The adaptive learning gain is updated only using the information of former iteration input and incomplete information of system output caused by random iterative lengths, data quantization and random packet dropouts. The prior information of randomly varying iteration lengths and the dynamic information of ILC systems is not required. This design guarantee the the mathematical expectation of tracking errors converge to zero as iteration increases. An illustrative example verifies the effectiveness of the proposed design.