About this Research Topic
The field of Guidance, Navigation, and Control (GNC) systems for spacecraft and various vehicles, including surface, aerial, and underwater, is pivotal for extending human and robotic exploration into harsh and inaccessible environments. Current GNC systems are constrained by limited automation, onboard computational capacity, and the necessity for human intervention. Recent advancements in sensing and perception are crucial for enhancing the performance of these systems. Visual data processing methods are particularly important for robotic systems onboard spacecraft and other vehicles, as they help in determining the asset's pose and improving path planning. Conventional techniques, such as processing range finder data or stereo-images for planetary rovers and analyzing deep space radio tracking data for spacecraft, are computationally intensive and often lack the necessary autonomy due to limited onboard CPU resources. Additionally, these methods are hindered by incomplete knowledge of the physical laws governing specific tasks. The integration of AI-based algorithms is essential to overcome these limitations and develop reliable, autonomous systems for deep space and harsh environment exploration.
This Research Topic aims to explore the application of AI techniques to enhance the GNC systems of spacecraft and surface, aerial, and underwater vehicles. The primary objectives include investigating AI-based methods for autonomous navigation, path planning, and decision-making processes. Specific questions to be addressed include the effectiveness of neural networks in GNC applications, the potential of supervised and unsupervised machine learning algorithms in poorly understood dynamical models, and the role of reinforcement learning in developing control policies for robotic systems. The research will also test hypotheses related to the efficiency and accuracy of deep learning architectures, such as Convolutional Neural Networks (CNNs), in image classification and feature extraction for GNC systems.
To gather further insights into the boundaries and limitations of AI-based GNC systems, we welcome articles addressing, but not limited to, the following themes:
- Use of Computer Vision (CV) for prototypes of the navigation systems of spacecraft and surface, aerial, and underwater vehicles
- Deep learning-based algorithms for terrain classification and obstacle avoidance
- Machine Learning (ML) algorithms for feature detection in extremely harsh environments
- Visual Simultaneous Localization and Mapping (VSLAM) algorithms for path planning
- Model-Based Reinforcement Learning (MBRL) for autonomous navigation
This Research Topic aims to explore the application of AI techniques to enhance the GNC systems of spacecraft and surface, aerial, and underwater vehicles. The primary objectives include investigating AI-based methods for autonomous navigation, path planning, and decision-making processes. Specific questions to be addressed include the effectiveness of neural networks in GNC applications, the potential of supervised and unsupervised machine learning algorithms in poorly understood dynamical models, and the role of reinforcement learning in developing control policies for robotic systems. The research will also test hypotheses related to the efficiency and accuracy of deep learning architectures, such as Convolutional Neural Networks (CNNs), in image classification and feature extraction for GNC systems.
To gather further insights into the boundaries and limitations of AI-based GNC systems, we welcome articles addressing, but not limited to, the following themes:
- Use of Computer Vision (CV) for prototypes of the navigation systems of spacecraft and surface, aerial, and underwater vehicles
- Deep learning-based algorithms for terrain classification and obstacle avoidance
- Machine Learning (ML) algorithms for feature detection in extremely harsh environments
- Visual Simultaneous Localization and Mapping (VSLAM) algorithms for path planning
- Model-Based Reinforcement Learning (MBRL) for autonomous navigation
Keywords: Deep Learning, Planetary Rover, Navigation, Path planning, Computer Vision, Guidance Navigation and Control (GNC) System
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
