AI Recommendation Systems for Lane-Changing Using Adherence-Aware Reinforcement Learning
This work addresses lane-changing efficiency for semi-autonomous vehicles, but it is incremental as it builds on existing RL methods with a focus on human adherence.
The paper tackled the problem of optimizing lane-changing recommendations in semi-autonomous driving by developing an adherence-aware reinforcement learning method that accounts for human driver compliance, resulting in improved travel efficiency for a single vehicle as evaluated in the CARLA simulation environment.
In this paper, we present an adherence-aware reinforcement learning (RL) approach aimed at seeking optimal lane-changing recommendations within a semi-autonomous driving environment to enhance a single vehicle's travel efficiency. The problem is framed within a Markov decision process setting and is addressed through an adherence-aware deep Q network, which takes into account the partial compliance of human drivers with the recommended actions. This approach is evaluated within CARLA's driving environment under realistic scenarios.