Vehicle Trajectory Prediction
Deep learning approach to predict movement of neighboring vehicles
This was my final project for CS7643 Deep Learning. My team and I implemented a state of the art approach for predicting the motion of vehicles. It taught us about multi headed attention, LSTMs, and a concept known as social tensors. Social tensors are basically a way to model interactions between agents in space, originally used to predict how people would move throughout a room, but in our case is applied to the interaction between cars. The general idea of this algorithm was to combine social tensors with a feature representation of the birds eye view to predict future movement. The picture below shows the target vehicle in green, other vehicles in blue, and the prediction for the target vehicle in purple. Ultimately, we did not achieve great accuracy, likely because we still have bugs (even after countless nights of debugging). Nonetheless, this project helped me dive into deep learning research!
