SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streams
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910061021888512 |
|---|---|
| author | Gao, Zhuoheng Zhang, Jiyao Xie, Zhiyong Dong, Hao Yu, Zhaofei Chen, Rongmei Chen, Guozhang Huang, Tiejun |
| author_facet | Gao, Zhuoheng Zhang, Jiyao Xie, Zhiyong Dong, Hao Yu, Zhaofei Chen, Rongmei Chen, Guozhang Huang, Tiejun |
| contents | Most robotic grasping systems rely on converting sensor data into explicit 3D point clouds, which is a computational step not found in biological intelligence. This paper explores a fundamentally different, neuro-inspired paradigm for 6-DoF grasp detection. We introduce SpikeGrasp, a framework that mimics the biological visuomotor pathway, processing raw, asynchronous events from stereo spike cameras, similarly to retinas, to directly infer grasp poses. Our model fuses these stereo spike streams and uses a recurrent spiking neural network, analogous to high-level visual processing, to iteratively refine grasp hypotheses without ever reconstructing a point cloud. To validate this approach, we built a large-scale synthetic benchmark dataset. Experiments show that SpikeGrasp surpasses traditional point-cloud-based baselines, especially in cluttered and textureless scenes, and demonstrates remarkable data efficiency. By establishing the viability of this end-to-end, neuro-inspired approach, SpikeGrasp paves the way for future systems capable of the fluid and efficient manipulation seen in nature, particularly for dynamic objects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streams Gao, Zhuoheng Zhang, Jiyao Xie, Zhiyong Dong, Hao Yu, Zhaofei Chen, Rongmei Chen, Guozhang Huang, Tiejun Robotics Computer Vision and Pattern Recognition Most robotic grasping systems rely on converting sensor data into explicit 3D point clouds, which is a computational step not found in biological intelligence. This paper explores a fundamentally different, neuro-inspired paradigm for 6-DoF grasp detection. We introduce SpikeGrasp, a framework that mimics the biological visuomotor pathway, processing raw, asynchronous events from stereo spike cameras, similarly to retinas, to directly infer grasp poses. Our model fuses these stereo spike streams and uses a recurrent spiking neural network, analogous to high-level visual processing, to iteratively refine grasp hypotheses without ever reconstructing a point cloud. To validate this approach, we built a large-scale synthetic benchmark dataset. Experiments show that SpikeGrasp surpasses traditional point-cloud-based baselines, especially in cluttered and textureless scenes, and demonstrates remarkable data efficiency. By establishing the viability of this end-to-end, neuro-inspired approach, SpikeGrasp paves the way for future systems capable of the fluid and efficient manipulation seen in nature, particularly for dynamic objects. |
| title | SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streams |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.10602 |