Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.03423 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912309581971456 |
|---|---|
| author | Kumar, Sathish Damodaran, Swaroop Kuruba, Naveen Kumar Jha, Sumit Ramanathan, Arvind |
| author_facet | Kumar, Sathish Damodaran, Swaroop Kuruba, Naveen Kumar Jha, Sumit Ramanathan, Arvind |
| contents | This paper presents a novel deep learning framework for robotic arm manipulation that integrates multimodal inputs using a late-fusion strategy. Unlike traditional end-to-end or reinforcement learning approaches, our method processes image sequences with pre-trained models and robot state data with machine learning algorithms, fusing their outputs to predict continuous action values for control. Evaluated on BridgeData V2 and Kuka datasets, the best configuration (VGG16 + Random Forest) achieved MSEs of 0.0021 and 0.0028, respectively, demonstrating strong predictive performance and robustness. The framework supports modularity, interpretability, and real-time decision-making, aligning with the goals of adaptive, human-in-the-loop cyber-physical systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03423 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DML-RAM: Deep Multimodal Learning Framework for Robotic Arm Manipulation using Pre-trained Models Kumar, Sathish Damodaran, Swaroop Kuruba, Naveen Kumar Jha, Sumit Ramanathan, Arvind Machine Learning Robotics This paper presents a novel deep learning framework for robotic arm manipulation that integrates multimodal inputs using a late-fusion strategy. Unlike traditional end-to-end or reinforcement learning approaches, our method processes image sequences with pre-trained models and robot state data with machine learning algorithms, fusing their outputs to predict continuous action values for control. Evaluated on BridgeData V2 and Kuka datasets, the best configuration (VGG16 + Random Forest) achieved MSEs of 0.0021 and 0.0028, respectively, demonstrating strong predictive performance and robustness. The framework supports modularity, interpretability, and real-time decision-making, aligning with the goals of adaptive, human-in-the-loop cyber-physical systems. |
| title | DML-RAM: Deep Multimodal Learning Framework for Robotic Arm Manipulation using Pre-trained Models |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2504.03423 |