To overcome the difficulty of collecting the working resistance and working trajectory of a wheel loader, this paper constructs a statics model of the bucket working resistance and a kinematics model of the working trajectory in the shoveling process and analyzes the key parameters of measuring the working resistance and working trajectory. Based on this, a working resistance and working trajectory acquisition strategy is proposed. To verify the effectiveness of the acquisition strategy, the in-service operation data of fine sand and loose soil shoveled by the wheel loader are collected and analyzed. Then, the test-fitted working resistance and working trajectory are obtained, and the working trajectory is input into the RecurDyn–EDEM co-simulation model to obtain the simulation-fitted working resistance. Considering the complex working conditions of the wheel loader, it is difficult to obtain accurate working resistance, and the actual working resistance is also a relative value. Therefore, a strong correlation between the two curves indicates that the acquisition strategy of the wheel loader’s working trajectory and working resistance proposed in this paper is feasible.

To handle the problem of low detection accuracy and missed detection caused by dense detection objects, overlapping, and occlusions in the scenario of complex construction machinery swarm operations, this paper proposes a multi-object detection method based on the improved YOLOv4 model. Firstly, the K-means algorithm is used to initialize the anchor boxes to improve the learning efficiency of the depth features of construction machinery objects. Then, the pooling operation is replaced with dilated convolution to solve the problem that the pooling layer reduces the resolution of feature maps and causes a high missed detection rate. Finally, focus loss is introduced to optimize the loss function of YOLOv4 to improve the imbalance of positive and negative samples during the model training process. To verify the effectiveness of the above optimizations, the proposed method is verified on the Pytorch platform with a self-build dataset. The experimental results show that the mean average precision(mAP) of the improved YOLOv4 model for multi-object detection of construction machinery can reach 97.03%, which is 2.16% higher than that of the original YOLOv4 detection network. Meanwhile, the detection speed is 31.11 fps, and it is reduced by only 0.59 fps, still meeting the real-time requirements. The research lays a foundation for environment perception of construction machinery swarm operations and promotes the unmanned and intelligent development of construction machinery swarm operations.