Optimal Energy Shaping via Neural Approximators

We introduce optimal energy shaping as an enhancement of classical passivity-based control methods. A promising feature passivity theory, alongside stability, has traditionally claimed to be intuitive performance tuning along the execution a given task. However, systematic approach for adjusting within passive framework yet developed, each method relies on few and problem-specific practical insights. Here, we cast classic energy-shaping design process in framework; once task-dependent metric is defined, solution systematically obtained through iterative procedure relying neural networks gradient-based optimization. The proposed validated state-regulation tasks.