Year of Graduation
Grid-Based Path Planning as Image Generation Using Generative Adversarial Networks
Applied Mathematics and Information Science
2D path planning in static environment is a well-known problem in robotics, video games etc. One of the common ways to solve it is to represent the environment as a grid composed of blocked and traversable cells and perform a heuristic search for a path on such grid. On the other hand, 2D grid resembles much a digital image, thus an appealing idea comes to being – to treat the problem as an image generation task and to solve it utilizing the recent advances in artificial neural networks and deep learning. In this work we make an attempt to apply a generative model as a path finder. We create a context aware generative adversarial net that generates a path image in response to context input, i.e. image of the grid-map with start and goal. We demonstrate empirically that the model can successfully handle low-dimensional input and solve previously unseen instances.