This article addresses the crucial aspect of safety in collaborative robotics by introducing a new continuous wavelet transform-convolutional neural network (CWT-CNN) for efficient robot collision detection. Unlike conventional methods, CWT-CNN exhibits superior data efficiency, requiring minimal collision data for robust training without relying on a dynamic model. The network’s adaptability extends to varying internal stiffness levels, offering robustness to changes in robotic system characteristics. Through comprehensive experimental studies, we investigate the impact of input signal types, wavelet types, wavelet scale ranges, and time-moving window sizes on collision detection performance, offering critical insights for optimal CWT parameter selection. Additionally, our transferability analysis demonstrates that the CWT-CNN can seamlessly adapt from one joint to another, requiring only minimal free-motion data from the new joint. This adaptability is validated through extensive experiments on an industrial robot and the robot equipped with variable stiffness actuators. In conclusion, the CWT-CNN is highly generalizable and data-efficient, making it a reliable solution for real-time collision detection in human-robot interactions, addressing a key aspect of safety in collaborative environments.

Loss of upper extremity motor control and function is an unremitting symptom in post-stroke patients. This would impose hardships on accomplishing their daily life activities. Supernumerary robotic limbs (SRLs) were introduced as a solution to regain the lost Degrees of Freedom (DoFs) by introducing an independent new limb. The actuation systems in SRL can be categorized into rigid and soft actuators. Soft actuators have proven advantageous over their rigid counterparts through intrinsic safety, cost, and energy efficiency. However, they suffer from low stiffness, which jeopardizes their accuracy. Variable Stiffness Actuators (VSAs) are newly developed technologies that have been proven to ensure accuracy and safety. In this paper, we introduce the novel Supernumerary Robotic Limb based on Variable Stiffness Actuators. Based on our knowledge, the proposed proof-of-concept SRL is the first that utilizes Variable Stiffness Actuators. The developed SRL would assist post-stroke patients in bi-manual tasks, e.g., eating with a fork and knife. The modeling, design, and realization of the system are illustrated. The proposed SRL was evaluated and verified for its accuracy via predefined trajectories. The safety was verified by utilizing the momentum observer for collision detection, and several post-collision reaction strategies were evaluated through the Soft Tissue Injury Test. The assistance process is qualitatively verified through standard user-satisfaction questionnaire.

Most of existing works on the tubes design optimization of concentric-tube robot (CTR) do not include the elastic stability in the optimization criteria. The only work which formulates the elastic stability in the objective function is based on scalarization method which is used in existing multi-objective design optimization. The objective function is formed by a set of weighted objective functions. The selection of the weights is crucial as the optimization results are greatly affected by them and could be misleading if these weights are improperly chosen. As an alternative optimization technique, we use Pareto grid-searching method to avoid this problem and allow a straightforward interpretation of the results following the selection criteria for the parameters to be optimized. This paper shows a three-tube CTR design based on Pareto grid-searching method in order to optimize the reachability and elastic stability of the CTR within a specific curvature range dedicated to the deep anterior brain tumor removal surgery.

Many medical applications can benefit from the new technology of concentric-tube robot (CTR) due to its miniature size, superior steerability, and controllability of the end tool. However, the kinematic modeling of CTR is challenging because of complicated physical phenomena caused by the elasticity interaction between tubes. Existing control methods of CTR are based on inverse kinematics calculation and hence the control performance largely relies on the accuracy of kinematics model used. In this work, we propose a new control method from the actuator level and show that the control design of actuator input in task-space with approximate Jacobian matrix provides more flexibility and robustness in handling inaccuracy in kinematics model. It is shown through simulation study that the proposed control method presents better performance compared with traditional inverse kinematics based control method in face of kinematics inaccuracy.