ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
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_ | 1866910882947137536 |
|---|---|
| author | Zhang, Qiang Cao, Jiahang Sun, Jingkai Shao, Yecheng Han, Gang Zhao, Wen Guo, Yijie Xu, Renjing |
| author_facet | Zhang, Qiang Cao, Jiahang Sun, Jingkai Shao, Yecheng Han, Gang Zhao, Wen Guo, Yijie Xu, Renjing |
| contents | In recent years, quadruped robotics has advanced significantly, particularly in perception and motion control via reinforcement learning, enabling complex motions in challenging environments. Visual sensors like depth cameras enhance stability and robustness but face limitations, such as low operating frequencies relative to joint control and sensitivity to lighting, which hinder outdoor deployment. Additionally, deep neural networks in sensor and control systems increase computational demands. To address these issues, we introduce spiking neural networks (SNNs) and event cameras to perform a challenging quadruped parkour task. Event cameras capture dynamic visual data, while SNNs efficiently process spike sequences, mimicking biological perception. Experimental results demonstrate that this approach significantly outperforms traditional models, achieving excellent parkour performance with just 11.7% of the energy consumption of an artificial neural network (ANN)-based model, yielding an 88.3% energy reduction. By integrating event cameras with SNNs, our work advances robotic reinforcement learning and opens new possibilities for applications in demanding environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09985 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network Zhang, Qiang Cao, Jiahang Sun, Jingkai Shao, Yecheng Han, Gang Zhao, Wen Guo, Yijie Xu, Renjing Robotics Computer Vision and Pattern Recognition Machine Learning In recent years, quadruped robotics has advanced significantly, particularly in perception and motion control via reinforcement learning, enabling complex motions in challenging environments. Visual sensors like depth cameras enhance stability and robustness but face limitations, such as low operating frequencies relative to joint control and sensitivity to lighting, which hinder outdoor deployment. Additionally, deep neural networks in sensor and control systems increase computational demands. To address these issues, we introduce spiking neural networks (SNNs) and event cameras to perform a challenging quadruped parkour task. Event cameras capture dynamic visual data, while SNNs efficiently process spike sequences, mimicking biological perception. Experimental results demonstrate that this approach significantly outperforms traditional models, achieving excellent parkour performance with just 11.7% of the energy consumption of an artificial neural network (ANN)-based model, yielding an 88.3% energy reduction. By integrating event cameras with SNNs, our work advances robotic reinforcement learning and opens new possibilities for applications in demanding environments. |
| title | ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network |
| topic | Robotics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.09985 |