The field of autonomous navigation and perception is rapidly advancing, with a focus on developing innovative solutions for obstacle avoidance, path planning, and state estimation. Recent research has explored the use of deep learning techniques, such as convolutional neural networks (CNNs) and sensor fusion, to improve the accuracy and efficiency of navigation systems. Additionally, there has been a shift towards leveraging multiple sources of information, including visual, inertial, and proprioceptive data, to enhance the robustness and reliability of autonomous systems. Notably, learning-based approaches have shown promise in predicting mobile robot stability in off-road environments and improving path smoothness in image-based path planning. Overall, the field is moving towards more integrated and adaptive solutions that can effectively navigate complex and dynamic environments. Noteworthy papers include: DAA* has introduced a novel learning method that improves path similarity through adaptive path smoothness, demonstrating remarkable improvements over existing methods. C-ZUPT has proposed a controlled ZUPT approach for aerial navigation and control, enabling more energy-efficient hovering and substantially extending sustained flight.