![[2510.00167] Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2510.00167] Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI
Summary
The paper discusses how embodied AI enables drones to make adaptive landing decisions in real-time, enhancing their resilience and safety in unpredictable environments.
Why It Matters
As autonomous drones become increasingly prevalent, their ability to respond to sudden changes in their environment is critical for safety and reliability. This research highlights the potential of embodied AI to improve decision-making processes, moving beyond traditional rule-based systems that may fail in complex scenarios.
Key Takeaways
- Embodied AI allows drones to interpret their surroundings dynamically.
- Traditional safety protocols are insufficient for real-world contingencies.
- The study demonstrates improved adaptive recovery strategies for drones.
- Real-time decision-making enhances the safety of autonomous aerial systems.
- Simulation results indicate significant advancements in drone resilience.
Computer Science > Artificial Intelligence arXiv:2510.00167 (cs) [Submitted on 30 Sep 2025 (v1), last revised 19 Feb 2026 (this version, v2)] Title:Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI Authors:Diego Ortiz Barbosa, Mohit Agrawal, Yash Malegaonkar, Luis Burbano, Axel Andersson, György Dán, Henrik Sandberg, Alvaro A. Cardenas View a PDF of the paper titled Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI, by Diego Ortiz Barbosa and 7 other authors View PDF HTML (experimental) Abstract:Autonomous drones must often respond to sudden events, such as alarms, faults, or unexpected changes in their environment, that require immediate and adaptive decision-making. Traditional approaches rely on safety engineers hand-coding large sets of recovery rules, but this strategy cannot anticipate the vast range of real-world contingencies and quickly becomes incomplete. Recent advances in embodied AI, powered by large visual language models, provide commonsense reasoning to assess context and generate appropriate actions in real time. We demonstrate this capability in a simulated urban benchmark in the Unreal Engine, where drones dynamically interpret their surroundings and decide on sudden maneuvers for safe landings. Our results show that embodied AI makes possible a new class of adaptive recovery and decision-making pipelines that were previously infeasible to design by hand, advancing resilience and safety in autonomous aeri...