Sim-to-Real Reinforcement Learning for Autonomous Driving Using Pseudosegmentation Labeling and Dynamic Calibration

<div>(a) Camera input image. (b) Inferenced segmentation results from the model trained with the ground-truth labels. (c) Segmentation results from the model trained with pseudolabels.</div>

Journal of Robotics

fig9

Figure 9

Figure 9: Sim-to-Real Reinforcement Learning for Autonomous Driving Using Pseudosegmentation Labeling and Dynamic Calibration 