Reproduce “VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behavior” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Julius Jankowski, Lara Brudermüller, Nick Hawes, Sylvain Calinon
VP-STO plans smooth joint-space routes with durations and updates them from feedback. It represents routes with via-points, optimizes their timing and path, repeatedly replans the full route, and executes a short segment. In five trials in a point-mass obstacle simulation, VP-STO reached the goal while STORM stopped before the obstacle; this comparison does not isolate horizon length or involve a real robot.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.