Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method
Abstract Achieving accurate and generalized autonomous navigation in unknown environments poses a significant challenge in robotics and artificial intelligence. Animals exhibits superlative navigation capabilities by combining the representation of internal neurals and sensory cues of self-motion an...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01777-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861495542317056 |
|---|---|
| author | Xiaode Liu Yufei Guo Yuanpei Chen Jie Zhou Yuhan Zhang Weihang Peng Xuhui Huang Zhe Ma |
| author_facet | Xiaode Liu Yufei Guo Yuanpei Chen Jie Zhou Yuhan Zhang Weihang Peng Xuhui Huang Zhe Ma |
| author_sort | Xiaode Liu |
| collection | DOAJ |
| description | Abstract Achieving accurate and generalized autonomous navigation in unknown environments poses a significant challenge in robotics and artificial intelligence. Animals exhibits superlative navigation capabilities by combining the representation of internal neurals and sensory cues of self-motion and external information. This paper proposes a brain-inspired navigation method based upon the spiking neural networks (SNN) and reinforcement learning, integrated with a lidar system that serves as the local environment explorer, by which realizes high performance of obstacle avoidance and target arrival in mapless circumstances. An asymptotic gradient method is introduced to optimize the backpropagation during training, which facilitates the improvement of model robustness. The results of our experiments conducted on the Gazebo platform showcase how our approach effectively improves navigation performance in various intricate environments. Our approach yielded a higher success navigation rate ranging from 2% to 5%, depending on the SNN timesteps. Considering the inherent lower computational cost of SNN, this work contributes to advancing the fusion of SNN and reinforcement learning techniques for energy-efficient autonomous navigation tasks in real-world mapless scenarios. |
| format | Article |
| id | doaj-art-b6a600ee05824209a50a1fc7b922310f |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-b6a600ee05824209a50a1fc7b922310f2025-02-09T13:01:15ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111211310.1007/s40747-024-01777-6Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient methodXiaode Liu0Yufei Guo1Yuanpei Chen2Jie Zhou3Yuhan Zhang4Weihang Peng5Xuhui Huang6Zhe Ma7Intelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICIntelligent Science & Technology Academy of CASICAbstract Achieving accurate and generalized autonomous navigation in unknown environments poses a significant challenge in robotics and artificial intelligence. Animals exhibits superlative navigation capabilities by combining the representation of internal neurals and sensory cues of self-motion and external information. This paper proposes a brain-inspired navigation method based upon the spiking neural networks (SNN) and reinforcement learning, integrated with a lidar system that serves as the local environment explorer, by which realizes high performance of obstacle avoidance and target arrival in mapless circumstances. An asymptotic gradient method is introduced to optimize the backpropagation during training, which facilitates the improvement of model robustness. The results of our experiments conducted on the Gazebo platform showcase how our approach effectively improves navigation performance in various intricate environments. Our approach yielded a higher success navigation rate ranging from 2% to 5%, depending on the SNN timesteps. Considering the inherent lower computational cost of SNN, this work contributes to advancing the fusion of SNN and reinforcement learning techniques for energy-efficient autonomous navigation tasks in real-world mapless scenarios.https://doi.org/10.1007/s40747-024-01777-6Spiking neural networks (SNN)Reinforcement learningAutonomous navigationUnmanned vehicleAsymptotic gradient method |
| spellingShingle | Xiaode Liu Yufei Guo Yuanpei Chen Jie Zhou Yuhan Zhang Weihang Peng Xuhui Huang Zhe Ma Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method Complex & Intelligent Systems Spiking neural networks (SNN) Reinforcement learning Autonomous navigation Unmanned vehicle Asymptotic gradient method |
| title | Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method |
| title_full | Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method |
| title_fullStr | Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method |
| title_full_unstemmed | Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method |
| title_short | Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method |
| title_sort | enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method |
| topic | Spiking neural networks (SNN) Reinforcement learning Autonomous navigation Unmanned vehicle Asymptotic gradient method |
| url | https://doi.org/10.1007/s40747-024-01777-6 |
| work_keys_str_mv | AT xiaodeliu enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT yufeiguo enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT yuanpeichen enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT jiezhou enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT yuhanzhang enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT weihangpeng enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT xuhuihuang enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod AT zhema enhancingnavigationperformanceinunknownenvironmentsusingspikingneuralnetworksandreinforcementlearningwithasymptoticgradientmethod |