MixNet: Physics Constrained Deep Neural Motion Prediction for Autonomous Racing
Phillip Karle, Ferenc Török, Maximilian Geisslinger, Markus Lienkamp
Abstract
Reliably predicting the motion of contestant vehicles surrounding an autonomous racecar is crucial for effective and performant ego-motion planning. Although highly expressive, deep neural networks are black-box models, making their usage challenging in this safety-critical applications of autonomous racing. On the other hand, physics-based models provide high safety guarantees for the predicted trajectory but lack accuracy. The method presented in this paper targets this trade-off. We introduce a method to predict the trajectories of opposing racecars with deep neural networks considering physical constraints to restrict the output and to improve its feasibility.We report the method’s performance against an LSTM-based encoder-decoder architecture on data acquired from multi-agent racing simulations. The proposed method outperforms the baseline model in prediction accuracy and robustness. Still, it fulfills quality guarantees of smoothness and consistency of the predicted trajectory and prevents out-of-track predictions. Thus, a robust real-world application of the model with high prediction accuracy is proven. The presented model was deployed on the racecar of the Technical University of Munich for the Indy Autonomous Challenge 2021. The code used in this research is available as open-source software at www.github.com/TUMFTM/MixNet.