To improve wheel trafficability in soft and muddy soils such as paddy fields, a bionic walking wheel is designed based on the structural morphology and movement mode of the feet of waders living in marshes and mudflats, similar to the muddy soil of paddy fields. The bionic walking wheel adopts the arrangement of double-row wheel legs and staggered arrays to imitate the walking posture of waders. The two legs move alternately, cooperate with each other, and improve the smoothness of movement. The cam inside the bionic walking wheel is used to control the movement mode of the feet. The flippers open before touching the ground to increase the contact area and reduce sinking, and the toes bend and grip the ground while touching the ground to increase traction. Multi-rigid-body dynamics software (Adams View 2020) is used to simulate the movement of the wheel during the wading process, and the movement coordination and interference between the wheel legs are analyzed. The simulation results show that there is no interference between the parts and that the movement smoothness is good. The interaction between the bionic walking wheel and muddy soil was analyzed via coupled EDEM–ADAMS simulation, and the simulation analysis and experiments were conducted and compared with those for a common paddy wheel. The results showed that the bionic walking wheel designed in this paper improved the drawbar pull by 113.56% compared with that of a common paddy wheel and had better anti-sinking performance. By analyzing the effect of toe grip on traction, it was found that the soil under the feet can be disturbed to provide greater traction when the toe is bent downward. This study provides a reference for improving the trafficability of walking mechanisms in soft and muddy soils, such as paddy fields.

To enable mobile robots to effectively deal with the emergency of visual contamination, contingency planning based on case-based reasoning (CBR) was performed in this paper. First, for a wheeled mobile robot (WMR) equipped with a chameleon-inspired visual system, a target search model in chameleon-inspired binocular negative correlation movement (CIBNCM) mode was established. Second, a CBR-based contingency planning model of visual contamination for WMRs was established, where the reasoning process using CBR for visual contamination was analyzed in detail. Third, through the analysis of environment perception when visual contamination occurs, a perception model in chameleon-inspired visual contamination for WMRs was built. Finally, to validate the proposed approach, a contingency planning experiment scheme for visual contamination was designed based on the robot’s general planning of target tracking, and the experimental result is discussed. The proposed CBR-based contingency planning approach for visual contamination can reason out effective solutions corresponding to the contamination situations. The rationality of the approach was verified by experiments with satisfactory results. Moreover, compared with the contingency planning method based on rule-based reasoning, the accuracy of target retracking after the robot visual system is contaminated is significantly higher for the CBR-based contingent planning method used in this paper.

To address the challenge of feature extraction methods in rolling bearing fault diagnosis relying excessively on human expertise, resulting in suboptimal diagnostic rates, this research introduces a fault detection method that integrates Convolutional Neural Network (CNN) and Support Vector Machine enhanced by the Improved Whale Optimization Algorithm (IWOA-SVM). Firstly, continuous wavelet transform (CWT) is applied to the time-domain signals to obtain time-frequency representations. These representations are then input into CNN for feature extraction. Testing the model on motor drive-end bearing data reveals that the average fault recognition rate exceeds 98.4%. This confirms the practicality and dependability of the suggested approach for diagnosing faults in rolling bearings.

When evaluating the dynamic accuracy of a six-degrees-of-freedom industrial robot using independent, asynchronous measurement systems, asynchronous startup, sampling rate differences, and relative clock scale deviations can cause time mismatches to propagate along the trajectory as position and attitude residuals. Fixed-delay correction or simple spatial compensation is insufficient to separate time and spatial errors. Therefore, this paper proposes a kinematically consistent spatiotemporal error compensation framework (ST-SAW-R2). This framework constructs a kinematic descriptor from a continuous pose trajectory, extracts clock-consistent anchor points from the matching cost surface, and then initializes and robustly refines the affine clock scale and offset. After time alignment, a pose coupling mapping and target bias model are established, and the position residual and right-multiplied rotation vector residual are learned separately. Dynamic compensation is then achieved through confidence-gated constraints. With a laser tracker as reference, two independent optical vision systems of different accuracy were verified: after static compensation, position RMSE decreased by 89.14% and 85.24% and attitude RMSE by 36.33% and 54.84%; in dynamic tests, position RMSE was 1.532–1.813 mm and 0.779–0.969 mm, attitude RMSE 0.182–0.264° and 0.106–0.146°. Explicitly restoring the relative clock scale separates dynamic temporal mismatch from static spatial error, enabling stable compensation across optical systems of different accuracy levels.

Efficient and intuitive programming strategies are essential for enabling robots to adapt to small-batch, high-mix production scenarios. Mixed reality (MR) and programming by demonstration (PbD) have shown great potential to lower the programming barrier and enhance human–robot interaction by leveraging natural human guidance. However, traditional offline programming methods, while capable of generating industrial-grade trajectories, remain time-consuming, costly to debug, and heavily dependent on expert knowledge. Conversely, existing MR-based PbD approaches primarily focus on improving intuitiveness but often suffer from low trajectory quality due to hand jitter and the lack of refinement mechanisms. To address these limitations, this paper introduces a coarse-to-fine human–robot collaborative programming paradigm. In this paradigm, the operator’s role is elevated from a low-level “trajectory drawer” to a high-level “task guider”. By leveraging sparse key points as guidance, the paradigm decouples high-level human task intent from machine-level trajectory planning, enabling their effective integration. The feasibility of the proposed system is validated through two industrial case studies and comparative quantitative experiments against conventional programming methods. The results demonstrate that the coarse-to-fine paradigm significantly improves programming efficiency and usability while reducing operator cognitive load. Crucially, it achieves this without compromising the final output, automatically generating smooth, high-fidelity trajectories from simple user inputs. This work provides an effective pathway toward reconciling programming intuitiveness with final trajectory quality.