Reproduce “A Genetic Approach to Gradient-Free Kinodynamic Planning in Uneven Terrains” 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
Otobong Jerome, Alexandr Klimchik, Alexander Maloletov, Geesara Kulathunga
GAKD plans motion for a car-like robot over uneven triangular-mesh terrain. It searches bounded acceleration and steering sequences with a genetic algorithm, simulates them, applies the first control, and replans from the updated state. Across five simulated scenarios, its average traversability cost is 4.6391, below log-MPPI's 5.2544 and MPPI's 5.8225, but log-MPPI has shorter average path-length excess.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.