Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities
This addresses the challenge of capturing multiple valid actions in autonomous driving scenarios, though it appears incremental as it builds on existing IBC methods.
The paper tackled the problem of standard Behavior Cloning failing to learn multimodal driving decisions in vehicle navigation by exploring Implicit Behavioral Cloning with Energy-Based Models, proposing Data-Augmented IBC which outperforms standard IBC in simulated urban driving tasks.
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.