JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908764564619264 |
|---|---|
| author | Ji, Shilong Chen, Yinuo Wang, Chuqi Chen, Jiayu Zhang, Ruize Gao, Feng Tang, Wenhao Yu, Shu'ang Xiang, Sirui Chen, Xinlei Yu, Chao Wang, Yu |
| author_facet | Ji, Shilong Chen, Yinuo Wang, Chuqi Chen, Jiayu Zhang, Ruize Gao, Feng Tang, Wenhao Yu, Shu'ang Xiang, Sirui Chen, Xinlei Yu, Chao Wang, Yu |
| contents | Aerial robots interacting with objects must perform precise, contact-rich maneuvers under uncertainty. In this paper, we study the problem of aerial ball juggling using a quadrotor equipped with a racket, a task that demands accurate timing, stable control, and continuous adaptation. We propose JuggleRL, the first reinforcement learning-based system for aerial juggling. It learns closed-loop policies in large-scale simulation using systematic calibration of quadrotor and ball dynamics to reduce the sim-to-real gap. The training incorporates reward shaping to encourage racket-centered hits and sustained juggling, as well as domain randomization over ball position and coefficient of restitution to enhance robustness and transferability. The learned policy outputs mid-level commands executed by a low-level controller and is deployed zero-shot on real hardware, where an enhanced perception module with a lightweight communication protocol reduces delays in high-frequency state estimation and ensures real-time control. Experiments show that JuggleRL achieves an average of $311$ hits over $10$ consecutive trials in the real world, with a maximum of $462$ hits observed, far exceeding a model-based baseline that reaches at most $14$ hits with an average of $3.1$. Moreover, the policy generalizes to unseen conditions, successfully juggling a lighter $5$ g ball with an average of $145.9$ hits. This work demonstrates that reinforcement learning can empower aerial robots with robust and stable control in dynamic interaction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning Ji, Shilong Chen, Yinuo Wang, Chuqi Chen, Jiayu Zhang, Ruize Gao, Feng Tang, Wenhao Yu, Shu'ang Xiang, Sirui Chen, Xinlei Yu, Chao Wang, Yu Robotics Aerial robots interacting with objects must perform precise, contact-rich maneuvers under uncertainty. In this paper, we study the problem of aerial ball juggling using a quadrotor equipped with a racket, a task that demands accurate timing, stable control, and continuous adaptation. We propose JuggleRL, the first reinforcement learning-based system for aerial juggling. It learns closed-loop policies in large-scale simulation using systematic calibration of quadrotor and ball dynamics to reduce the sim-to-real gap. The training incorporates reward shaping to encourage racket-centered hits and sustained juggling, as well as domain randomization over ball position and coefficient of restitution to enhance robustness and transferability. The learned policy outputs mid-level commands executed by a low-level controller and is deployed zero-shot on real hardware, where an enhanced perception module with a lightweight communication protocol reduces delays in high-frequency state estimation and ensures real-time control. Experiments show that JuggleRL achieves an average of $311$ hits over $10$ consecutive trials in the real world, with a maximum of $462$ hits observed, far exceeding a model-based baseline that reaches at most $14$ hits with an average of $3.1$. Moreover, the policy generalizes to unseen conditions, successfully juggling a lighter $5$ g ball with an average of $145.9$ hits. This work demonstrates that reinforcement learning can empower aerial robots with robust and stable control in dynamic interaction tasks. |
| title | JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.24892 |