Learning High-Level Decision Making with an Interaction-Aware Attention-Based Network in Autonomous Driving

arXiv:2607.09725v1 Announce Type: new Abstract: Reliable learning-based high-level decision making for lane changes and speed control in automated driving must accommodate dynamically sized inputs due to varying scene traffic flow. DeepSet and its variants represent the state of the art among shared-encoder approaches; however, they neglect explicit traffic interaction modeling, limiting performance in negotiation-intensive scenarios such as intersections. Attention-based methods capture interac...