Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Multimodal spiking neural network for space robotic manipulation. |
| Συγγραφείς: |
Zhang, Liwen1 (AUTHOR), Sun, Guanghui1 (AUTHOR) guanghuisun@hit.edu.cn, Deng, Heng1 (AUTHOR) |
| Πηγή: |
Acta Astronautica. Oct2026, Vol. 247, p92-103. 12p. |
| Θεματικοί όροι: |
*Space robotics, *Multisensor data fusion, *Reinforcement learning, *Energy conservation, *Artificial neural networks, *Machine learning, *Reduced gravity environments, *Tactile sensors |
| Περίληψη: |
The microgravity environment places stringent demands on autonomous manipulators for on-orbit assembly. While model-free reinforcement learning (RL) improves adaptability, its high computational cost hampers deployment on resource-limited platforms. We propose a multimodal control framework based on a spiking neural network (SNN) that enhances perception by integrating geometric states, tactile forces, and semantic cues. The system features a dual-channel, three-stage curriculum reinforcement learning (CRL) mechanism. Specifically, the dual-channel design shifts grasping reliance from spatial data to tactile feedback to ensure accuracy. Furthermore, the three-stage approach decomposes the challenge by gradually increasing complexity, which fosters robust control strategies. Compared with conventional artificial neural network (ANN) controllers, our method achieves significantly higher success rates and energy efficiency in robotic manipulation tasks, validating its suitability for resource-constrained space applications. • Unified architecture controls space robots across diverse mounting setups. • Multimodal framework fuses geometric and tactile data for robust grasping. • Curriculum learning achieves high manipulation success in microgravity. • Spiking neural networks use far less energy than artificial neural networks. [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: |
Academic Search Index |