Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. We explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better capture this multimodality. We propose Data-Augmented IBC (DA-IBC), which improves learning by perturbing expert actions to form the counterexamples of IBC training and using better initialization for derivative-free inference. Experiments in the CARLA simulator with Bird's-Eye View inputs demonstrate that DA-IBC outperforms standard IBC in urban driving tasks designed to evaluate multimodal behavior learning in a test environment. The learned energy landscapes are able to represent multimodal action distributions, which BC fails to achieve.
@article{arxiv.2509.15400,
title = {Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities},
author = {Eric Aislan Antonelo and Gustavo Claudio Karl Couto and Christian Möller},
journal= {arXiv preprint arXiv:2509.15400},
year = {2025}
}