The problem of inverse kinematics is fundamental in robot control. Many traditional inverse kinematics solutions, such as geometry, iteration, and algebraic methods, are inadequate in high-speed solutions and accurate positioning. In recent years, the problem of robot inverse kinematics based on neural networks has received extensive attention, but its precision control is convenient and needs to be improved. This paper studies a particle swarm optimization (PSO) back propagation (BP) neural network algorithm to solve the inverse kinematics problem of a UR3 robot based on six degrees of freedom, overcoming some disadvantages of BP neural networks. The BP neural network improves the convergence precision, convergence speed, and generalization ability. The results show that the position error is solved by the research method with respect to the UR3 robot inverse kinematics with the joint angle less than 0.1 degrees and the output end tool less than 0.1 mm, achieving the required positioning for medical puncture surgery, which demands precise positioning of the robot to less than 1 mm. Aiming at the precise application of the puncturing robot, the preliminary experiment has been conducted and the preliminary results have been obtained, which lays the foundation for the popularization of the robot in the medical field.

Flexible wearable devices have attracted wide attention in capacious fields because of their real-time and continuous monitoring of human information. The development of flexible sensors and corresponding integration with wearable devices is of great significance to build smart wearable devices. In this work, multi-walled carbon nanotube/polydimethylsiloxane-based (MWCNT/PDMS) resistive strain sensors and pressure sensors were developed to integrate a smart glove for human motion/perception detection. Firstly, MWCNT/PDMS conductive layers with excellent electrical and mechanical properties (resistivity of 2.897 KΩ · cm, elongation at break of 145%) were fabricated via a facile scraping-coating method. Then, a resistive strain sensor with a stable homogeneous structure was developed due to the similar physicochemical properties of the PDMS encapsulation layer and MWCNT/PDMS sensing layer. The resistance changes of the prepared strain sensor exhibited a great linear relationship with the strain. Moreover, it could output obvious repeatable dynamic response signals. It still had good cyclic stability and durability after 180° bending/restoring cycles and 40% stretching/releasing cycles. Secondly, MWCNT/PDMS layers with bioinspired spinous microstructures were formed by a simple sandpaper retransfer process and then assembled face-to-face into a resistive pressure sensor. The pressure sensor presented a linear relationship of relative resistance change and pressure in the range of 0–31.83 KPa with a sensitivity of 0.026 KPa⁻¹, and a sensitivity of 2.769 × 10⁻⁴ KPa⁻¹ over 32 KPa. Furthermore, it responded quickly and kept good cycle stability at 25.78 KPa dynamic loop over 2000 s. Finally, as parts of a wearable device, resistive strain sensors and a pressure sensor were then integrated into different areas of the glove. The cost-effective, multi-functional smart glove can recognize finger bending, gestures, and external mechanical stimuli, which holds great potential in the fields of medical healthcare, human-computer cooperation, and so on.

When a robot is working properly, it is possible to collide with people or objects entering its working space. This research is different than usual control algorithm. It proposes a universal algorithm for sensorless collision detection of robot actuator faults to enhance the security of the robot. On the basis of the dynamic model, a classical friction model to ensure the accuracy of the whole dynamic model is introduced. This collision detection algorithm can conduct without any external sensors or acceleration and realize the real-time detection just needs to measure the motor current and the location information from the encoder of the robot joint. The value of external torque τ_ext was used to compare with the threshold to detect the collision. After using the proposed collision detection method, the two rotational (2R) planar manipulators can detect the slight collision reliably. The experimental results and performance comparisons show that this sensorless collision detection algorithm is simple and effective. It can be promoted to any other type of robot arm with more degrees of freedom.

The focus of this study is a moment compensation control algorithm driven by a direct current servo motor. Zero moment robot teaching is achieved with a joint moment compensation algorithm. The moment equilibrium equation is derived based on moment compensation. The current signal detected by a Hall effect sensor is multiplied by a torque constant to estimate the torque value of the robot joint. The compensation current is obtained through parameter identification to overcome gravitational and friction torques. The two variables of speed and position are separately controlled, allowing the compensation current of Coulomb friction and viscous friction force to be separated from the compensation current of friction torque. This study presents the system research, design, and development of a high-precision position control theory of a robot zero moment teaching control method. A collaborative robot is used as the test and verification platform to confirm the feasibility and effectiveness of the proposed theoretical method and implementation technology.

With the advancement of technology, unmanned ground vehicles (UGVs) have shown increasing application value in various tasks, such as food delivery and cleaning. A key capability of UGVs is obstacle detection, which is essential for avoiding collisions during movement. Current mainstream methods use point cloud information from onboard sensors, such as light detection and ranging (LiDAR) and depth cameras, for obstacle perception. However, the substantial volume of point clouds generated by these sensors, coupled with the presence of noise, poses significant challenges for efficient obstacle detection. Therefore, this paper presents a fast obstacle detection algorithm designed to ensure the safe operation of UGVs. Building on multi-sensor point cloud fusion, an efficient ground segmentation algorithm based on multi-plane fitting and plane combination is proposed in order to prevent them from being considered as obstacles. Additionally, instead of point cloud clustering, a vertical projection method is used to count the distribution of the potential obstacle points through converting the point cloud to a 2D polar coordinate system. Points in the fan-shaped area with a density lower than a certain threshold will be considered as noise. To verify the effectiveness of the proposed algorithm, a cleaning UGV equipped with one LiDAR sensor and four depth cameras is used to test the performance of obstacle detection in various environments. Several experiments have demonstrated the effectiveness and real-time capability of the proposed algorithm. The experimental results show that the proposed algorithm achieves an over 90% detection rate within a 20 m sensing area and has an average processing time of just 14.1 ms per frame.