Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910319697199104 |
|---|---|
| author | Kulkarni, Mihir Alexis, Kostas |
| author_facet | Kulkarni, Mihir Alexis, Kostas |
| contents | This work contributes a novel deep navigation policy that enables collision-free flight of aerial robots based on a modular approach exploiting deep collision encoding and reinforcement learning. The proposed solution builds upon a deep collision encoder that is trained on both simulated and real depth images using supervised learning such that it compresses the high-dimensional depth data to a low-dimensional latent space encoding collision information while accounting for the robot size. This compressed encoding is combined with an estimate of the robot's odometry and the desired target location to train a deep reinforcement learning navigation policy that offers low-latency computation and robust sim2real performance. A set of simulation and experimental studies in diverse environments are conducted and demonstrate the efficiency of the emerged behavior and its resilience in real-life deployments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03947 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding Kulkarni, Mihir Alexis, Kostas Robotics This work contributes a novel deep navigation policy that enables collision-free flight of aerial robots based on a modular approach exploiting deep collision encoding and reinforcement learning. The proposed solution builds upon a deep collision encoder that is trained on both simulated and real depth images using supervised learning such that it compresses the high-dimensional depth data to a low-dimensional latent space encoding collision information while accounting for the robot size. This compressed encoding is combined with an estimate of the robot's odometry and the desired target location to train a deep reinforcement learning navigation policy that offers low-latency computation and robust sim2real performance. A set of simulation and experimental studies in diverse environments are conducted and demonstrate the efficiency of the emerged behavior and its resilience in real-life deployments. |
| title | Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding |
| topic | Robotics |
| url | https://arxiv.org/abs/2402.03947 |