Reproduce “EAAE: Energy-Aware Autonomous Exploration for UAVs in Unknown 3D Environments” 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
Jacob Elskamp, Moji Shi, Leonard Bauersfeld, Davide Scaramuzza, Marija Popović
A framework named Energy-Aware Autonomous Exploration (EAAE) integrates trajectory-level energy prediction into the frontier selection process for multirotor UAVs exploring unknown 3D environments. The approach yields a 12.5% to 21.1% reduction in total energy consumption in cluttered environments compared to baseline methods, while maintaining competitive exploration speed and map quality.
Key insights
- Explicitly incorporating trajectory-level energy prediction during frontier selection significantly reduces total energy consumption for multirotor UAVs in complex 3D exploration tasks.
- This energy-aware planning approach can achieve substantial energy savings without compromising exploration speed or the quality of the generated map.
- The computational cost introduced by the detailed energy estimation module is modest compared to other necessary planning components, making it practical for real-time integration.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.