Various stair-climbing or cleaning mechanisms have been proposed or developed in the past decades. Most of them are big-sized, complex, and/or expensive, which hinder their practical application. In this study, a new stair-cleaning robot is proposed and developed. In the new robot, a pair of legs is used for stair climbing. Rotating around the main body, the legs of the robot drive the feet to execute revolving but translational motions, thereby allowing the robot to climb. The new robot is highly compact compared with most traditional stair-cleaning or climbing robots, because only one motor is utilized to drive the climbing mechanism and the legs can be retracted at both sides of the robot when it is not climbing. Its compact structure enables the new robot to move along the riser to do cleaning on the stairs, which is a prominent advantage over most similar robots. The cleaning device is designed similar to that of current ground cleaning robots. The sensing and control system is designed for successful stair climbing and avoidance of falls and collisions. Experiments show that the new robot has high success rates in climbing up or down common types of stairs, and thus can do cleaning on the related stairs.

This paper aims to investigate the strengthening mechanism of laser shock peening on the interfacial bonding properties between TiN coatings and TC4 titanium alloy substrates. The different surface textures were induced by LSP on a TC4 titanium alloy substrate. Subsequently, titanium nitride (TiN) coatings were deposited on the surface texture. A scratch test and reciprocating sliding wear assessment were conducted to evaluate the impact of LSP on the interfacial bonding properties and wear performance of the coatings. The experimental results demonstrated that the adhesion of TiN coatings deposited on the surface texture formed by laser shock peening was significantly enhanced. The efficacy of laser shock treatment in reducing wear rates was found to be significantly enhanced in cases of both increased spot overlapping rate and increased laser power density. The surface texture created using laser parameters of 6.43 GW/cm² and a 50% overlapping rate was found to have the most significant effect on improving the adhesion and anti-wear properties of the coating. The laser shock texture was identified as the main contributor to this improvement, providing a large interfacial contact area and a mechanical bond between the coating and the substrate. This bond inhibited the initiation and propagation of micro-cracks caused by the concentration of internal stress and interfacial stress of the coating.

Annular laser metal deposition (ALMD) is a rising technology that fabricates near-net-shaped components. In this research, a single factor experiment with 18 groups was designed to study the influence of process parameters on the geometric characteristics (bead width, bead height, fusion depth, and fusion line) and thermal history of Ti6Al4V tracks. The results show that discontinuous and uneven tracks with pores or large-sized incomplete fusion defects were observed when the laser power was less than 800 W or the defocus distance was −5 mm. The laser power had a positive effect on the bead width and height, while the scanning speed had the opposite effect. The shape of the fusion line varied at different defocus distances, and the straight fusion line could be obtained with the appropriate process parameters. The scanning speed was the parameter that had the greatest effect on the molten pool lifetime and solidification time as well as the cooling rate. In addition, the microstructure and microhardness of the thin wall sample were also studied. Many clusters with various sizes in different zones were distributed within the crystal. The microhardness ranged from 330 HV to 370 HV.

Gesture recognition techniques based on surface electromyography (sEMG) signals face instability problems caused by electrode displacement and the time-varying characteristics of the signals in cross-time applications. This study proposes an incremental learning framework based on densely connected convolutional networks (DenseNet) to capture non-synchronous data features and overcome catastrophic forgetting by constructing replay datasets that store data with different time spans and jointly participate in model training. The results show that, after multiple increments, the framework achieves an average recognition rate of 96.5% from eight subjects, which is significantly better than that of cross-day analysis. The density-based spatial clustering of applications with noise (DBSCAN) algorithm is utilized to select representative samples to update the replayed dataset, achieving a 93.7% recognition rate with fewer samples, which is better than the other three conventional sample selection methods. In addition, a comparison of full dataset training with incremental learning training demonstrates that the framework improves the recognition rate by nearly 1%, exhibits better recognition performance, significantly shortens the training time, reduces the cost of model updating and iteration, and is more suitable for practical applications. This study also investigates the use of the incremental learning of action classes, achieving an average recognition rate of 88.6%, which facilitates the supplementation of action types according to the demand, and further improves the application value of the action pattern recognition technology based on sEMG signals.