Please see the first post of Please read: make it easier to help you - #8. In particular, provide a minimal working example and use the tools to format your code.
You should also read the docs on NLP: Nonlinear Modeling · JuMP
For your specific question, there is a chain of issues: i) don’t use nonlinear functions in @constraint and ii) no, you can’t use round. You will need to think of a way to reformulate your problem to make it amenable to solvers.
You may be interested in GitHub - RoboticExplorationLab/TrajectoryOptimization.jl: A fast trajectory optimization library written in Julia