Aiming at the problem of multimodal transport path planning under uncertain environments, this paper establishes a multi-objective fuzzy nonlinear programming model considering mixed-time window constraints by taking cost, time, and carbon emission as optimization objectives. To solve the model, the model is de-fuzzified by the fuzzy expectation value method and fuzzy chance-constrained planning method. Combining the game theory method with the weighted sum method, a cooperative game theory-based multi-objective optimization method is proposed. Finally, the effectiveness of the algorithm is verified in a real intermodal network. The experimental results show that the proposed method can effectively improve the performance of the weighted sum method and obtain the optimal multimodal transport path that satisfies the time window requirement, and the path optimization results are better than MOPSO and NSGA-II, effectively reducing transportation costs and carbon emissions. Meanwhile, the influence of uncertainty factors on the multimodal transport route planning results is analyzed. The results show that the uncertain factors will significantly increase the transportation cost and carbon emissions and affect the choice of route and transportation mode. Considering uncertainty factors can increase the reliability of route planning results and provide a more robust and effective solution for multimodal transportation.

The accuracy of hand-eye calibration significantly affects the performance of vision-guided robotic tasks. The main problems faced by hand-eye calibration are the tedious process of data collection and the low accuracy of collected data. To reduce the workload and improve accuracy, an industrial robot hand-eye calibration method combining a data augmentation strategy and an Actor-Critic network is proposed. In the proposed method, the parameters in the hand-eye transformation matrix are described by an X-Y-Z fixed angle representation. Then a parameter optimization strategy is formulated. The parameters are optimized using the Actor-Critic network. Data augmentation was performed based on ellipse features. Combined with Halcon image processing software, a bulk of unlabeled data is extracted from a single frame image of an ellipse calibration target. This method of data collection simplifies data acquisition and ensures the accuracy of data. According to the results of the accuracy analysis experiment, the proposed method significantly obtains a more accurate conversion relationship.

The difficulty of defecation seriously affects the quality of life of the bedridden elderly. To solve the problem that it is difficult to know the defecation time of the bedridden elderly, this paper proposed a human pre-defecation prediction method based on multi-domain features and improved support vector machine (SVM) using bowel sound as the original signal. The method includes three stages: multi-domain features extraction, feature optimization, and defecation prediction. In the stage of multi-domain features extraction, statistical analysis, fast Fourier transform (FFT), and wavelet packet transform are used to extract feature information in the time domain, frequency domain, and time-frequency domain. The symmetry of the bowel sound signal in the time domain, frequency domain, and time-frequency domain will change when the human has the urge to defecate. In the feature optimization stage, the Fisher Score (FS) algorithm is introduced to select meaningful and sensitive features according to the importance of each feature, aiming to remove redundant information and improve computational efficiency. In the stage of defecation prediction, SVM is optimized by the gray wolf optimization (GWO) algorithm to realize human defecation prediction. Finally, experimental analysis of the bowel sound data collected during the study is carried out. The experimental result shows that the proposed method could achieve an accuracy of 92.86% in defecation prediction, which proves the effectiveness of the proposed method.

In pursuit of the time-optimal path tracking (TOPT) trajectory of a robot manipulator along a preset path, a beforehand identified robot dynamic model is usually used to obtain the required optimal trajectory for perfect tracking. However, due to the inevitable model-plant mismatch, there may be a big error between the actually measured torques and the calculated torques by the dynamic model, which causes the obtained trajectory to be suboptimal or even be infeasible by exceeding given limits. This paper presents a TOPT-oriented SARSA algorithm (TOPTO-SARSA) and a two-step method for finding the time-optimal motion and ensuring the feasibility : Firstly, using TOPTO-SARSA to find a safe trajectory that satisfies the kinematic constraints through the interaction between reinforcement learning agent and kinematic model. Secondly, using TOPTO-SARSA to find the optimal trajectory through the interaction between the agent and the real world, and assure the actually measured torques satisfy the given limits at the last interaction. The effectiveness of the proposed algorithm has been verified through experiments on a 6-DOF robot manipulator.