Seam tracking with structured light vision has been widely applied into the robot welding. And the precise laser stripe extraction is the premise of automatic laser vision seam tracking. However, conventional laser stripe extraction methods based on image processing have the shortcomings of poor flexibility and robustness, which are easily affected by considerable image noises in the welding processing, such as arc light, smoke, and splash. To address this issue, inspired by image segmentation, with the strong contextual feature expression ability of deep convolutional neural network (DCNN), a novel image denoising method of seam images is proposed in this paper for automatic laser stripe extraction to serve intelligent robot welding applications, such as seam tracking, seam type detection, weld bead detection, etc. With the deep encoder-decoder network framework, aimed at the information loss issue by multiple convolutional and pooling operations in DCNNs, an attention dense convolutional block is proposed to extract and accumulate multi-scale feature maps. Meanwhile, a residual bi-directional ConvLSTM block (BiConvLSTM) is proposed to effectively learn multi-scale and long-range spatial contexts from local feature maps. Finally, a weighted loss function is proposed for model training to address the class unbalanced issue. Combined with the seam image set, the experimental results show that the proposed image denoising network could correctly extract the laser stripes from seam images which could demonstrate that the proposed method shows a high detection precision and good robustness against the strong image noise interference from welding process.

Accurate welding defect location is of great significance to modern manufacturing, which could be used for accurate quality evaluation and precise repairing decision-making basis of different products. Nevertheless, accurate welding defect location is still a challenging task due to some complex factors, such as complex backgrounds, low contrast, weak texture, and class imbalance issue. Recently, deep learning has got great development due to its strong feature expression ability, which has been widely applied into defect detection, but it still exists certain shortcomings on segmentation tasks with the class unbalanced issue or microdefects. To address these issues, with the encoder–decoder network architecture, a novel welding defect location method is proposed with an attention-guided segmentation network. To reduce the contextual information loss of the deep encoder module after multiple convolution and pooling operations, a multiscale feature fusion block is proposed to embed into a U-shaped network (U-Net) to acquire more information. On the basis, combined with a bidirectional convolutional long short-term memory (BiConvLSTM) block, an improved attention block is integrated into the skip connections between the encoder path and the decoder path to capture the global, long-range contexts and emphasize target regions, contributing to locate welding defect areas and enhance the segmentation ability on microdefects. Meanwhile, to address the foreground–background class imbalance issue, a hybrid loss function combined with binary cross-entropy (BCE) and $D_{\text {ice}}$ loss functions is proposed to effectively utilize their unique excellent characteristics for accurate defect segmentation. Experiment results on the public GDXray dataset show that the proposed segmentation method could obtain a competitive segmentation performance compared with other advanced segmentation models.

It is of great importance to improve the performance of soft bending actuators with simpler control laws. Considering that the velocity information of soft actuators cannot be measured by conventional sensors due to a contradiction between the soft body and the rigid state, this letter addresses a robust tracking controller without velocity observers to improve the tracking accuracy and simplify the control laws. First, a generalized dynamic model and related system properties are developed for the construction of controllers. Second, a novel robust tracking controller combined with an auxiliary state is utilized for soft bending actuators in the presence of system uncertainties. A key feature of the proposed controller is that it does not incorporate any information about velocities and observers. Finally, corresponding comparative simulations and experiments are performed to verify the effectiveness of the proposed controller.

High precision motion control is the key to complete the refined operation tasks for cable-driven continuum robots. However, the existence of model inaccuracy and actuator saturation pose great challenges to the high precision motion control of cable-driven continuum robots. This article proposes an extended state observer (ESO)-based antisaturation control scheme for cable-driven continuum robots with consideration of unmodeled dynamics and actuator saturation. First, the dynamic model of the cable-driven continuum robot is derived. To facilitate the design of the overall control scheme, the driving input dimension of the dynamic model is reduced from three to two based on the principle of space rotational symmetry. Taking the actuator saturation into consideration, the saturated dynamic model of the cable-driven continuum robot is further developed. Then, an ESO is designed for the saturated cable-driven continuum robots to estimate the unmodeled dynamics, and an auxiliary system is proposed to handle the actuator saturation. Hereby, a novel control law based on the ESO and auxiliary system is put forward to compensate for estimated unmodeled dynamics and actuator saturation. Moreover, the stability of the closed loop system is analyzed by Lyapunov method, and a practical and effective tuning method is provided to optimize the parameters of the proposed control scheme. Finally, comparative simulations and experiments are conducted to verify the effectiveness of the proposed control scheme.

SUMMARY: Bevel-tip needles have the potential to improve paracentetic precision and decrease paracentetic traumas. In order to drive bevel-tip needles precisely with the constrains of path length and path dangerousness, we propose a closed-loop control method that only requires the position of the needle tip and can be easily applied in a clinical setting. The control method is based on the path planning method proposed in this paper. To establish the closed-loop control method, a kinematic model of bevel-tip needles is first presented, and the relationship between the puncture path and controlled variables is established. Second, we transform the path planning method into a multi-objective optimization problem, which takes the path error, path length and path dangerousness into account. Multi-objective particle swarm optimization is employed to solve the optimization problem. Then, a control method based on path planning is presented. The current needle tip attitude is essential to plan an insertion path. We analyze two methods to obtain the tip attitude and compare their effects using both simulations and experiments. In the end, simulations and experiments in phantom tissue are executed and analyzed, the results show that our methods have high accuracy and have the ability to deal with the model parameter uncertainty.