The Capsule Shape All-Terrain Robot (CS-ATR) is designed to address the challenges of navigating rough and unpredictable environments, such as disaster zones, where stability, maneuverability, and adaptability are critical. This study presents the design and development of the CS-ATR, focusing on its perpendicular dual-track system, real-time PID-controlled tilt correction mechanism specifically for capsule-shaped robots, and autoencoder-based anomaly detection system. The perpendicular dual-track system enables the robot to perform precise lateral movements, allowing navigation through confined spaces, while the PID controller ensures continuous real-time adjustments to maintain balance across uneven terrains. The variational autoencoder enhances the robot’s ability to detect and correct abnormal movements, improving overall system reliability. Extensive simulation experiments using Simscape™ were conducted to evaluate the robot’s ability to maintain balance and adapt to disturbances, such as rocks and pits. Additionally, the performance of the physical prototype was tested on various terrains, including river sand, rocky paths, and simulated pits, to validate its operational effectiveness in real-world conditions. The results demonstrate that CS-ATR effectively overcomes obstacles, maintains stability, adapts to changes in traction, and corrects anomalies, making it a promising solution for applications such as search and rescue missions.