HERB: Human-augmented Efficient Reinforcement learning for Bin-packing
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_ | 1866916703627116544 |
|---|---|
| author | Perovic, Gojko Duarte, Nuno Ferreira Dehban, Atabak Teixeira, Gonçalo Falotico, Egidio Santos-Victor, José |
| author_facet | Perovic, Gojko Duarte, Nuno Ferreira Dehban, Atabak Teixeira, Gonçalo Falotico, Egidio Santos-Victor, José |
| contents | Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. While traditional packing solutions focus on geometric optimization, packing irregular, 3D objects presents significant challenges due to variations in shape and stability. Reinforcement Learning~(RL) has gained popularity in robotic packing tasks, but training purely from simulation can be inefficient and computationally expensive. In this work, we propose HERB, a human-augmented RL framework for packing irregular objects. We first leverage human demonstrations to learn the best sequence of objects to pack, incorporating latent factors such as space optimization, stability, and object relationships that are difficult to model explicitly. Next, we train a placement algorithm that uses visual information to determine the optimal object positioning inside a packing container. Our approach is validated through extensive performance evaluations, analyzing both packing efficiency and latency. Finally, we demonstrate the real-world feasibility of our method on a robotic system. Experimental results show that our method outperforms geometric and purely RL-based approaches by leveraging human intuition, improving both packing robustness and adaptability. This work highlights the potential of combining human expertise-driven RL to tackle complex real-world packing challenges in robotic systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16595 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HERB: Human-augmented Efficient Reinforcement learning for Bin-packing Perovic, Gojko Duarte, Nuno Ferreira Dehban, Atabak Teixeira, Gonçalo Falotico, Egidio Santos-Victor, José Robotics Machine Learning Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. While traditional packing solutions focus on geometric optimization, packing irregular, 3D objects presents significant challenges due to variations in shape and stability. Reinforcement Learning~(RL) has gained popularity in robotic packing tasks, but training purely from simulation can be inefficient and computationally expensive. In this work, we propose HERB, a human-augmented RL framework for packing irregular objects. We first leverage human demonstrations to learn the best sequence of objects to pack, incorporating latent factors such as space optimization, stability, and object relationships that are difficult to model explicitly. Next, we train a placement algorithm that uses visual information to determine the optimal object positioning inside a packing container. Our approach is validated through extensive performance evaluations, analyzing both packing efficiency and latency. Finally, we demonstrate the real-world feasibility of our method on a robotic system. Experimental results show that our method outperforms geometric and purely RL-based approaches by leveraging human intuition, improving both packing robustness and adaptability. This work highlights the potential of combining human expertise-driven RL to tackle complex real-world packing challenges in robotic systems. |
| title | HERB: Human-augmented Efficient Reinforcement learning for Bin-packing |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2504.16595 |