Backend
Drone Navigation for Fast, Safe Emergency Response
arXiv cs.RO0 views
arXiv:2611.19818v1 Announce Type: new Abstract: In 2025, there was a total of 358 weather-related disasters worldwide affecting millions of people. For unmanned aerial vehicles (UAVs) to autonomously aid these people, they need to be able to navigate around complex obstacles and reach their destinations to deliver supplies or quickly locate survivors in disaster-stricken areas. Our research addresses this need by providing a method to compute minimum-time trajectories in real time while providing guarantees of obstacle avoidance along the trajectory. Previous approaches treat the problem of computing time-optimal trajectories without considering obstacle avoidance. Our work not only includes obstacle avoidance constraints, but also improves overall mission time for navigation. We define mission time as the sum of planning time and traversal time. In time-sensitive emergencies, rapid trajectory planning is essential to ensure the prompt delivery of critical medical aid. As such, we consider the combined planning and traversal time as the key metric for how quickly the vehicle can reach a survivor. We show a sample mission in Fig. 1 where the quadrotor navigates through multiple canyon-like obstacles to deliver aid; during most of this trajectory, it is applying the near-maximum thrust.
Source:https://arxiv.org/abs/2611.19818PreviousDynLimit: A Simulation Benchmark for Dynamics-Critical Planning and ControlNextEasyNav: A Modular Architecture for Real-Time Navigation Across Heterogeneous Robot Environments
Related posts
Direct Numerical Simulation of Thermoacoustically Unstable Flames Via Non-Drifting Acoustic Delay Characteristic Boundary Conditions
0arXiv cs.NA
On the sharp linear convergence rate of the circumcentered--reflection method on subspaces
0arXiv cs.NA
Quantum Gibbs sampling through the detectability lemma
0arXiv cs.NA
RustMC: Automated Verification of Real-World Concurrent Rust
0arXiv cs.CR
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
0arXiv cs.CR
HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption
0arXiv cs.CR