A Segmented Robot Grasping Perception Neural Network for Edge AI
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_ | 1866913993058156544 |
|---|---|
| author | Bröcheler, Casper Vroom, Thomas Timmermans, Derrick Akker, Alan van den Tang, Guangzhi Kouzinopoulos, Charalampos S. Möckel, Rico |
| author_facet | Bröcheler, Casper Vroom, Thomas Timmermans, Derrick Akker, Alan van den Tang, Guangzhi Kouzinopoulos, Charalampos S. Möckel, Rico |
| contents | Robotic grasping, the ability of robots to reliably secure and manipulate objects of varying shapes, sizes and orientations, is a complex task that requires precise perception and control. Deep neural networks have shown remarkable success in grasp synthesis by learning rich and abstract representations of objects. When deployed at the edge, these models can enable low-latency, low-power inference, making real-time grasping feasible in resource-constrained environments. This work implements Heatmap-Guided Grasp Detection, an end-to-end framework for the detection of 6-Dof grasp poses, on the GAP9 RISC-V System-on-Chip. The model is optimised using hardware-aware techniques, including input dimensionality reduction, model partitioning, and quantisation. Experimental evaluation on the GraspNet-1Billion benchmark validates the feasibility of fully on-chip inference, highlighting the potential of low-power MCUs for real-time, autonomous manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13970 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Segmented Robot Grasping Perception Neural Network for Edge AI Bröcheler, Casper Vroom, Thomas Timmermans, Derrick Akker, Alan van den Tang, Guangzhi Kouzinopoulos, Charalampos S. Möckel, Rico Robotics Artificial Intelligence I.2; I.2.9; I.2.10 Robotic grasping, the ability of robots to reliably secure and manipulate objects of varying shapes, sizes and orientations, is a complex task that requires precise perception and control. Deep neural networks have shown remarkable success in grasp synthesis by learning rich and abstract representations of objects. When deployed at the edge, these models can enable low-latency, low-power inference, making real-time grasping feasible in resource-constrained environments. This work implements Heatmap-Guided Grasp Detection, an end-to-end framework for the detection of 6-Dof grasp poses, on the GAP9 RISC-V System-on-Chip. The model is optimised using hardware-aware techniques, including input dimensionality reduction, model partitioning, and quantisation. Experimental evaluation on the GraspNet-1Billion benchmark validates the feasibility of fully on-chip inference, highlighting the potential of low-power MCUs for real-time, autonomous manipulation. |
| title | A Segmented Robot Grasping Perception Neural Network for Edge AI |
| topic | Robotics Artificial Intelligence I.2; I.2.9; I.2.10 |
| url | https://arxiv.org/abs/2507.13970 |