Scene understanding is one of the key components for robotic navigation and self-driving application. Semantic segmentation gives detailed information about a scene as it involves pixel-wise dense labeling. However, semantic segmentation models are challenging to deploy on resource constraint devices due to high computational costs. In this project, we address the problem of deploying and improving semantic segmentation models on resource constraint devices. Further, we aim to develop a better-generalized segmentation model that has the capabilities to better identify the unknown object and via federated learning.