Many studies use surface electromyogram (sEMG) signals to estimate the joint angle, for control of upper-limb exoskeletons and prostheses. However, several practical factors still affect its clinical applicability. One of these factors is the load variation during daily use. This paper demonstrates that the load variation can have a substantial impact on performance of elbow angle estimation. This impact leads an increase in mean RMSE (Root-Mean-Square Error) from 7.86 ° to 20.44 ° in our experimental test. Therefore, we propose three methods to address this issue: 1) pooling the training data from all loads together to form the pooled training data for the training model; 2) adding the measured load value (force sensor) as an additional input; and 3) developing a two-step hybrid estimation approach based on load and sEMG. Experiments are conducted with five subjects to investigate the feasibility of the proposed three methods. The results show that the mean RMSE is reduced from 20.44 ° to 13.54 ° using method one, 10.47 ° using method two, and 8.48 ° using method three, respectively. Our study indicates that 1) the proposed methods can improve performance and stability on joint angle estimation and 2) sensor fusion (sEMG sensor and force sensor) is an efficient way to resolve the adverse effect of load variation.