bstract One of the main challenges in the visual simultaneous localization and mapping (V-SLAM) of construction robots is robustness to overexposure conditions. The main difficulties arise from sensor exposure limitations that cause images to lose information. In addition, construction robots can hardly track enough points in overexposure conditions due to the assumption of constant brightness in SLAM. We propose a High and Low Exposure SLAM (HLE-SLAM) system to recover missing information in overexposed frames. Our method uses frame exposure fusion to generate globally wellexposed frames. It uses exposure, contrast and information entropy as indicators to select the best part of brightness and information in high and low exposed frames. We adopt the Shi-Tomasi and Kanade-Lucas-Tomasi (KLT) sparse optical flow algorithms to improve the ability to detect and track feature points in the overexposed environment. Experimental results on data sets and real environments show that HLESLAM can effectively solve the overexposure problem.