In regenerative medicine, manual cell processing is labor-intensive and costly and needs to become more efficient. Recently, automatic cell culture systems equipped with vertically articulated robots have been developed. However, automating all cell processing tasks complicates these systems. This study aims to develop a simple and rational cell processing system by combining robot and human tasks. In a previous study, we improved the efficiency of discarding and injecting tasks using a robot in a media changing process. In this study, we further investigated the injection method and developed and evaluated two types of algorithms that are both accurate and can handle variable target volumes. One algorithm predicts the time to stop injecting based on the flow rate and corrects the stop timing based on the y-intercept of the injection volume and the target volume. The other algorithm uses machine learning to predict the time to stop injecting based on the flow rate, y-intercept, and target volume. Our experimental results revealed the feasibility of both algorithms. With these algorithms, a robot can perform the injecting task more efficiently than a human.