Autonomous vehicles are well-known for automated tasks that are difficult or dangerous to be performed by human. However, the environment in which those Autonomous Vehicle (AV) are evolving is generally hard to predict. Thus, the challenge is to achieve a predefined mission while adapting AVs to their shifting environment in real time as efficiently as possible. The mission often includes path planning problems, where self-adaptation to terrain modifications is required while maintaining contradictory objectives, such as safety, risk assessment, travelling time or distance or consumed energy. We choose to focus on supervision missions (covering area with a lidar, with pictures, searching, etc) with two objectives: travelled distance (that could later be modeled into time or energy consumption) and covered area. We propose a multiobjective optimization (MOO) framework for a self adaptation of autonomous vehicles, with an offline/online approach, in order to solve covering/monitoring missions. The offline process will predict a initial path for the AV and the online process will be useful for the dynamic path re-planning when obstacles are detected. Our results demonstrate the benefits of reusing the offline pre-computed solutions for the online phase and for dynamic path re-planning.