<p>This paper presents a novel guidance, navigation, and control architecture for planetary landing based on a stabilized seeker guidance algorithm and an autonomous safe landing site selection system. The seeker tracks the designated landing site by adjusting seeker elevation and azimuth angles to center the designated landing site in the sensor field of view. The seeker angles, closing speed, and range to the designated landing site are used to formulate a velocity field, which is mapped, together with attitude, and rotational velocity directly to the commanded thrust for the four thrusters by the guidance and control system to achieve a safe landing at the designated landing site. The guidance and control system is implemented as a policy optimized using meta-reinforcement learning. The designated landing site is selected via semantic segmentation using a convolutional neural network, trained on a hazard map based on the digital elevation model of the landing area and simulated images produced by the onboard camera. We demonstrate that the system is compatible with multiple divert maneuvers during the powered descent phase and is robust to seeker lag, actuator lag and degradation, and that the landing site selection system consistently avoids potential hazard.</p>