High rehydration quality is essential for infant formula (IF) powder. Existing rehydration tests lack objectivity and reproducibility. Furthermore, current studies into improving the objectivity of rehydration tests lack both integrated platforms and systematic analysis of end-user rehydration behaviour. This thesis evaluated an automated approach to measuring the IF Powders rehydration quality. It was hypothesised that the approach would provide a better understanding of how human-like bottle agitation and powder physicochemical properties impact rehydration quality. First, a previously-developed robotic sample preparation prototype was integrated with a computer vision system to estimate sediment height, foam height, and number of white particles in rehydrated IF powders. Secondly, these estimates were compared to ratings from eight participants and modified laboratory reference tests. Finally, bottle agitations from ten participants were characterised using computer vision, and human-like robotic agitations were statistically learned. The platform exhibited significant correlations with participants’ ratings (> 0.68), modified reference tests (0.79 and 0.55 for sediment height and white particles, respectively), and platform duplicate measurements (> 0.87). While white particle correlation may necessitate further research, the results suggest the potential to provide automated objective results across laboratories. The platform’s novel ability to monitor sediment height over time was used to develop a predictive model for rapid screening of dispersibility. The learned swirl agitation resulted in a lower foam height and higher sediment height than shake agitation suggesting that different end-users’ rehydration styles may yield different rehydration qualities. Results also showed that participants applied less energy and lower amplitude to agitation in the swirl style than shake style. Taken together, these findings could inform future updates to international guidelines on powder rehydration (e.g., WHO). The thesis contributions include: (i) the development of an objective automated platform, (ii) the improvement/development of reference/benchmarking tests, (iii) providing insights into rehydration, and (iv) characterising/learning human bottle agitations.