Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911324740517888 |
|---|---|
| author | Tayar, Marco S. de Oliveira, Lucas K. Tommaselli, Felipe Andrade G. Negri, Juliano D. Segreto, Thiago H. Godoy, Ricardo V. Becker, Marcelo |
| author_facet | Tayar, Marco S. de Oliveira, Lucas K. Tommaselli, Felipe Andrade G. Negri, Juliano D. Segreto, Thiago H. Godoy, Ricardo V. Becker, Marcelo |
| contents | Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for developing such policies, it presents a critical trade-off between on-policy and off-policy algorithms. Off-policy methods promise high sample efficiency, a vital trait for minimizing costly and unsafe real-world fine-tuning. In contrast, on-policy methods often exhibit greater training stability, which is essential for reliable convergence in hazard-dense environments. This paper directly investigates this trade-off by comparing a leading on-policy algorithm, Proximal Policy Optimization (PPO), against an off-policy counterpart, Soft Actor-Critic (SAC), for precision flight in procedurally generated ducts within a high-fidelity simulator. Our results show that PPO consistently learned a stable, collision-free policy that completed the entire course. In contrast, SAC failed to find a complete solution, converging to a suboptimal policy that navigated only the initial segments before failure. This work provides evidence that for high-precision, safety-critical navigation tasks, the reliable convergence of a well-established on-policy method can be more decisive than the nominal sample efficiency of an off-policy algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16807 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach Tayar, Marco S. de Oliveira, Lucas K. Tommaselli, Felipe Andrade G. Negri, Juliano D. Segreto, Thiago H. Godoy, Ricardo V. Becker, Marcelo Robotics Artificial Intelligence Machine Learning Systems and Control Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for developing such policies, it presents a critical trade-off between on-policy and off-policy algorithms. Off-policy methods promise high sample efficiency, a vital trait for minimizing costly and unsafe real-world fine-tuning. In contrast, on-policy methods often exhibit greater training stability, which is essential for reliable convergence in hazard-dense environments. This paper directly investigates this trade-off by comparing a leading on-policy algorithm, Proximal Policy Optimization (PPO), against an off-policy counterpart, Soft Actor-Critic (SAC), for precision flight in procedurally generated ducts within a high-fidelity simulator. Our results show that PPO consistently learned a stable, collision-free policy that completed the entire course. In contrast, SAC failed to find a complete solution, converging to a suboptimal policy that navigated only the initial segments before failure. This work provides evidence that for high-precision, safety-critical navigation tasks, the reliable convergence of a well-established on-policy method can be more decisive than the nominal sample efficiency of an off-policy algorithm. |
| title | Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach |
| topic | Robotics Artificial Intelligence Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2508.16807 |