One of the key challenges for autonomous vehicles is the ability to accurately predict the motion of other objects in the surrounding environment, such as pedestrians or other vehicles. In this thesis, a motion forecasting approach for autonomous vehicles is developed, inspired by Heatmap Output for Motion Estimation (HOME)[1]. We predict multiple heatmaps with a neural-network-based model for every traffic participant in the vicinity of the autonomous vehicle; with one heatmap per timestep. The heatmaps are used as input to a novel sampling algorithm that extracts a restricted number of six coordinates corresponding to the most likely future positions. Furthermore, we experiment with different encoders and decoders, as well as a comparison of two loss functions. Additionally, a new grid-scaling technique is introduced, showing further improved performance. Overall, our approach achieves state-of-the-art miss rate performance in short-term prediction (up to three seconds) while being competitive in longterm prediction (up to eight seconds) in the public 2022Waymo motion challenge. Furthermore, we show that the performance is even higher when the output representation is not restricted to six coordinates.