The tractor is the primary power device of the agricultural production process. For the problem that the traditional electro-hydraulic hitch control method for tractors cannot simultaneously meet the requirements of maintaining a constant ploughing depth and improving traction performance and electric tractor overall efficiency, this paper proposes a hydraulic cylinder pressure control method of the electro-hydraulic hitch system for electric tractors. We establish a tractor-implement system dynamic model, calculate the rear axle load of the tractor in real-time according to the actual working parameters under the premise of ensuring the constant ploughing depth, construct a traction performance objective optimization function, and use the genetic algorithm to solve the optimal hydraulic cylinder pressure value of the electro-hydraulic hitch system. Hardware-in-the-loop (HIL) simulation results show that the electric tractor under the traditional position control method and the hydraulic cylinder pressure control method has an average wheel slip of 18.50% and 16.93%, an average traction efficiency of 71.35% and 73.08%, and an average overall efficiency of 50.81% and 52.40%. The hydraulic cylinder pressure control method proposed in this paper reduces the wheel slip by 9.27%, increases the traction efficiency by 2.42%, improves the electric tractor overall efficiency by 3.13%, and reduces the electric tractor overall energy loss by 7.67% compared with the traditional position-control method. Therefore, the hydraulic cylinder pressure control method of the electro-hydraulic hitch system proposed in this paper can achieve the purpose of effectively improving tractor traction performance and reducing tractor energy loss while maintaining a constant ploughing depth. This study offers technological references for electric tractors to improve traction performance and reduce the overall energy loss of electric tractors.

Robotic meat cutting is increasingly in demand in meat industries due to safety issues, labor shortages, and inefficiencies. This paper proposes a multi-demonstration human–robot skill transfer framework to address the flexible and generalized cutting of sheep hindquarters with complex 3D anatomy structures by imitating humans. To improve the generalization with meat sizes and demonstrations and extract target cutting behaviors, multi-demonstrations of cutting are encoded into low-dimension latent space through principal components analysis (PCA), Gaussian mixture model (GMM), and Gaussian mixture regression (GMR). To improve the robotic cutting flexibility and the cutting behavior reproducing accuracy, this study combines a modified dynamic movement primitive (DMP) high-level behavior generator with the low-level joints admittance control (AC) through real-time inverse velocity (IV) kinematics solving and constructs the IVAC-DMP control module. The experimental results show that the maximum residual meat thickness in the sheep hindquarter cutting of sample 1 is 3.1 mm, and sample 2 is 3.8 mm. The residual rates of samples 1 and 2 are 5.6% and 4.8%. Both meet the requirements for sheep hindquarter separation. The proposed framework is advantageous for harvesting high-value meat products and providing a reference technique for robot skill learning in interaction tasks.