RoboAgent is an innovative integrated hardware-software system designed to simulate human-like behavior in interactions with short video platforms such as Instagram, TikTok, WeiXin, XiaoHongShu, and YouTube. By combining a three-axis writing robot, computer vision capabilities, and advanced language models, RoboAgent facilitates controlled, reproducible studies of user behavior and engagement on these platforms. This paper details RoboAgent's design, including its system architecture and components, and presents results from experiments demonstrating high interaction success rates, precise icon detection, and generation of contextually relevant comments. RoboAgent represents a significant step forward in automated testing and analysis of social media interactions, offering valuable insights into user dynamics and platform engagement.

This paper proposes WaveDepth, a novel method for enabling accurate water depth estimation by combining water semantic segmentation models with depth estimation models. By masking out the water portions in images before inputting them into the depth estimation model, WaveDepth significantly improves the accuracy and detail representation of depth estimation for water targets. To overcome the lack of water depth estimation datasets, a dedicated dataset was constructed using multiple devices and WaveShot water photography drones. Multiple depth estimation models were trained and tested on this dataset to select an optimized model that can estimate depths in water scenes without additional image preprocessing. This work contributes an innovative water depth estimation method, a purpose-built water depth estimation dataset, and an optimized model for practical application.