Optimal Energy Shaping via Neural Approximators

TL;DR

This paper presents a systematic approach to optimize energy shaping in passivity-based control using neural networks and gradient optimization, enabling performance tuning within a passive control framework.

Contribution

It introduces an optimal control formulation for energy shaping, leveraging neural approximators to systematically improve performance in passive control tasks.

Findings

Successfully applied to state-regulation tasks

Demonstrates systematic performance tuning

Uses neural networks for iterative optimization

Abstract

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