Visualizing Movement Control Optimization Landscapes

Perttu Hämäläinen, Juuso Toikka, Amin Babadi, C Karen Liu

Research output: Contribution to journalArticleScientificpeer-review

26 Downloads (Pure)

Abstract

A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters. However, as closed-form expressions of the objective functions are often not available, our understanding of the optimization problems is limited. Building on recent work on analyzing neural network training, we contribute novel visualizations of high-dimensional control optimization landscapes; this yields insights into why control optimization is hard and why common practices like early termination and spline-based action parameterizations make optimization easier. For example, our experiments show how trajectory optimization can become increasingly ill-conditioned with longer trajectories, but parameterizing control as partial target states-e.g., target angles converted to torques using a PD-controller-can act as an efficient preconditioner. Both our visualizations and quantitative empirical data also indicate that neural network policy optimization scales better than trajectory optimization for long planning horizons. Our work advances the understanding of movement optimization and our visualizations should also provide value in educational use.
Original languageEnglish
JournalIEEE Transactions on Visualization and Computer Graphics
DOIs
Publication statusE-pub ahead of print - 2020
MoE publication typeA1 Journal article-refereed

Fingerprint Dive into the research topics of 'Visualizing Movement Control Optimization Landscapes'. Together they form a unique fingerprint.

Cite this