Reproduce “BoundPlanner: A convex-set-based approach to bounded manipulator trajectory planning” 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
Thies Oelerich, Christian Hartl-Nesic, Florian Beck, Andreas Kugi
A 7-DoF arm must reach into a box beneath an overhead obstacle, making a direct approach difficult. BoundPlanner plans through overlapping collision-free regions, allowing its joint-space controller to deviate from a reference path within each region. It reaches the goal in this scenario, while tested RRT+MPC gets stuck before the box; this is a result in one setup, not a general guarantee.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.