Addressing key challenges in unstructured environments, including local optimum traps, limited real-time interaction, and convergence difficulties, this research pioneers a hybrid reinforcement learning approach that combines simulated annealing (SA) with proximal policy optimization (PPO) for robotic arm trajectory planning. The framework enables the accurate, collision-free grasping of randomly appearing objects in dynamic obstacles through three key innovations: a probabilistically enhanced simulation environment with a 20% obstacle generation rate; an optimized state-action space featuring 12-dimensional environment coding and 6-DoF joint control; and an SA-PPO algorithm that dynamically adjusts the learning rate to balance exploration and convergence. Experimental results show a 6.52% increase in success rate (98% vs. 92%) and a 7.14% reduction in steps per set compared to the baseline PPO. A real deployment on the AUBO-i5 robotic arm enables real machine grasping, validating a robust transfer from simulation to reality. This work establishes a new paradigm for adaptive robot manipulation in industrial scenarios requiring a real-time response to environmental uncertainty.

Manufacturing enterprises accumulate numerous manufacturing instances as they run and develop. Being able to excavate and apply the instance resources reasonably is one of the most effective approaches to improve manufacturing and support innovation. A novel framework for the discovery and reuse of typical process routes driven by symbolic entropy and intelligent optimisation algorithm so as to scientifically determine reuse objects and raise the reuse flexibility is proposed in this paper. A similarity measurement method of machining process routes based on symbolic entropy is developed in this framework. Subsequently, a typical process route discovery method based on the ant colony clustering model and similarity measurement is devised, and two reuse approaches based on the typical process route are analysed. Finally, three case studies are rendered. These case studies cover the aspects of similarity analysis, mining, and reuse of manufacturing instances, which systematically explains the whole procedure of discovery and reuse based on typical process route. The case studies show that (i) the similarity measurement method based on symbolic entropy can accurately evaluate the similarity among ten machining process routes, (ii) ant colony clustering model can realize adaptive clustering for these ten process routes, and (iii) indirect reuse approach for the typical process route can support the generation of new machining plan effectively. This reveal that the proposed framework comprehensively considers various aspects of retrieval and reuse of manufacturing instances, which can effectively support process instance reuse. Can better support process instance reuse.

Vibration characteristics are important reference indicators for reflecting the overall performance of RV reducers. At present, there is no factory testing standard for vibration characteristics applicable to production enterprises in the industry. This study conducted vibration characteristic tests on RV40E reducers at different speed ratios. Through a large number of sample comparisons, suitable vibration characteristic factory testing standards for production enterprises were provided. Detailed on-site inspection standards have been developed based on research and analysis results for defective products such as eccentricity, gear defects, and detection errors. This standard can cover 90% of defect types within the factory. The samples are specific and executable. This study solves the problem of the lack of clear vibration detection standards in the industry. For the first time, such a detailed sample set of internal data within a company has been provided. It has extremely practical engineering application value and provides data reference for the development of RV reducer industry.

The combination of vision and robotic grinding technology provides robots with “visual perception” capabilities that enable them to accurately locate the area to be ground and perform the grinding tasks efficiently. Based on the rough grinding requirements for wheel hub burrs proposed by a casting company, this paper investigates the application of a vision-guided grinding robot in treating burrs on wheel hub castings. First, through vision system calibration, the conversion from pixel coordinate system to robot base coordinate system is implemented, thus ensuring that the subsequently extracted burr point coordinates can be correctly mapped to the robot’s operational coordinate system. Next, the images of the burrs on wheel hub castings are collected and processed. All the burr points are extracted by applying image algorithms. In order to improve grinding accuracy, a height error compensation model is established to adjust the coordinates of the 2D-pixel points; the coordinate error after compensation was reduced by 58.33%. Subsequently, the compensated burr point trajectories are optimized by utilizing an intelligent optimization algorithm to generate the shortest grinding path. Through experimental analysis of the relationship between spindle speed and surface roughness, a grinding trajectory simulation model is constructed, and the simulation results are integrated into the robot system. Finally, actual wheel hub burr grinding experiments are performed to validate the effectiveness and practicality of the proposed solution.