Memory Clustering Using Persistent Homology for Multimodality- and Discontinuity-Sensitive Learning of Optimal Control Warm-Starts

Wolfgang Xaver Merkt, Vladimir Ivan, Traiko Dinev, Ioannis Havoutis, Sethu Vijayakumar

Research output: Contribution to journalArticlepeer-review

Abstract

Shooting methods are an efficient approach to solving nonlinear optimal control problems. As they use local optimization, they exhibit favorable convergence when initialized with a good warm-start but may not converge at all if provided with a poor initial guess. Recent work has focused on providing an initial guess from a learned model trained on samples generated during an offline exploration of the problem space. However, in practice, the solutions contain discontinuities introduced by system dynamics or the environment. Additionally, in many cases, multiple equally suitable, i.e., multimodal, solutions exist to solve a problem. Classic learning approaches smooth across the boundary of these discontinuities and thus generalize poorly. In this work, we apply tools from algebraic topology to extract information on the underlying structure of the solution space. In particular, we introduce a method based on persistent homology to automatically cluster the dataset of precomputed solutions to obtain different candidate initial guesses. We then train a mixture-of-experts within each cluster to predict state and control trajectories to warm-start the optimal control solver and provide a comparison with modality-agnostic learning. We demonstrate our method on a cartpole toy problem and a quadrotor avoiding obstacles, and show that clustering samples based on inherent structure improves the warm-start quality.
Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIEEE Transactions on Robotics
Early online date30 Apr 2021
DOIs
Publication statusE-pub ahead of print - 30 Apr 2021

Keywords

  • Optimal control
  • topology
  • robot learning
  • motion planning

Fingerprint

Dive into the research topics of 'Memory Clustering Using Persistent Homology for Multimodality- and Discontinuity-Sensitive Learning of Optimal Control Warm-Starts'. Together they form a unique fingerprint.

Cite this