Shape memory alloy (SMA) is a kind of active deformation material with a self-sensing and driving ability. It is very similar to the performance of human muscles, and through temperature changes to produce phase changes to output force and displacement, it has the ability to restore the initial shape and size. The combination of SMA and wearable robotic technology has the advantages of being light weight, energy-saving, and having great human–exoskeleton interaction. However, the existing flexible exoskeletons driven by SMA are only designed with bionic primary muscles, ignoring the role of antagonistic muscles. This study presents a novel soft bionic elbow exoskeleton based on SMA spring actuators (Sobee-SMA). The exoskeleton adopts a bionic design, combining active deformation material SMA and a high-elastic-material rubber band to simulate the contraction and relaxation of elbow skeletal muscles. Through a pulse width modulation (PWM) experiment, the driving voltage is selected as 12 V, the PWM duty cycle is 90 % during heating, and the PWM duty cycle is 18 % during heat preservation. In a relaxed state of healthy subjects, the range of motion of the elbow is about 0–80^∘, and the maximum temperature is about 60–70 ^∘C. During the circular movement of the elbow, the maximum temperature can be maintained within the SMA operating temperature without a high temperature. In conclusion, the exoskeleton provides elbow-assisted motion and ensures the safety of the heating process.

Computer vision can provide upcoming walking environment information for lower limb-assisted robots, thus enabling more accurate and robust decisions for highlevel control. However, existing computer vision systems in lower extremity devices are still limited by the disturbances present in the human-machine-environment interaction that prevent optimal performance. In this paper, we propose a gimbal-based terrain classification system that can be adapted to different lower limb movements, different walking speeds and gait phases. We use linear active disturbance rejection controller to realize fast response and antidisturbance control of the gimbal, which allows computer vision to continuously and stably focus on the desired field of view angle during lower limb motion interaction. In terms of classification algorithm, we deployed a lightweight MobileNetV2 model in an embedded vision module for real-time and highly accurate inference performance. By using the proposed terrain classification system, it can provide the ability to classify and predict terrain independent of mounting position (thighs and shanks), gait phase and walking speed. This also makes our system applicable to subjects with different physical conditions (e.g., able-bodied subjects and individuals with transfemoral amputation) without tuning the parameters, which will contribute to the plug-and-play functionality of terrain classification. Finally, our approach is promising to improve the adaptability of lower limb assisted robots in complex terrain, allowing the wearer to walk more safely.

The existing lower limb prostheses with passive knees have disadvantages, causing an asymmetric gait and higher metabolic cost during level walking which is in contrast with a normal gait. However, most existing active knee prostheses need a significant amount of energy. In this paper, a novel hybrid passive–active knee prosthesis (HPAK) that allows passive and active operating modes is proposed, which contains an active motor unit and a novel hydraulic damper with an electrically controlled valve that adjusts the damping torque dynamically during each gait cycle. An energy consumption model was built to evaluate the energy consumption when walking on level ground in three different simulation conditions to, respectively, simulate the complete HPAK, an ordinary active prosthesis (AKP) and an ordinary passive prosthesis (PKP). The results show that, in a cycle, the HPAK consumes only 16.19 J, which is 3.6 times lower than the AKP (58.95 J), and the PKP consumes only 1.24 J due to the novel spring–hydraulic damper structure designed and presented in this paper. These results indicate that the proposed novel hybrid passive–active knee prosthesis can have a positive effect on reducing energy consumption and improving the approximation of healthy gait characteristics when walking on level ground, contrasting with active or passive knee prostheses.

The ability to continuously recognize locomotion modes and accurately predict transition intentions is essential for intelligent prosthetic knees. In this study, an innovative framework for locomotion recognition and transition prediction was introduced based on fusing mechanical (inertial measurement unit (IMU)) and biomechanical (force myography (FMG)) signals. This framework integrated an FMG-IMU dual-modal sensing system implemented on a prosthetic knee, enabling simultaneous acquisition of FMG-IMU fusion signals from transfemoral amputees during dynamic walking. A novel feature-driven CNN-BiLSTM model was developed and trained as the classifier, enhancing the accuracy and efficiency of locomotion mode prediction. The RelifF-MI algorithm was employed to optimize FMG-IMU features, ensuring efficient data processing by effectively eliminating feature redundancy. The framework was evaluated using data collected from eight transfemoral amputees. The results demonstrated that the fusion of FMG-IMU dual-modal gait data with the feature-driven classifier significantly improved classification performance, achieving an overall average recognition accuracy of 98.51% and an average prediction time of 274 ms (21.82% of the gait cycle) across five locomotion modes—level walking (LW), stair ascent/descent (SA/SD), and ramp ascent/descent (RA/RD)—and eight transitions between these modes. These promising results highlighted the considerable potential of the proposed method for application in prosthetic knee control.

It is necessary to develop an effective knee prosthesis to recover the lost mobility of amputees. Variable-damping knee prostheses utilizing hydraulic dampers offer several advantages, but current researches are limited in approaching healthy knee behavior. To improve the gait symmetry, this study proposed a variable-damping knee prosthesis with a novel hydraulic damper using neural network predictive control (NNPC) scheme during swing phase. The external fan valve structure of the hydraulic damper can not only realize independent and continuous adjustment of flexion and extension damping by a single motor, but also can effectively avoid the damping adjustment failure caused by excessive load. NNPC was proposed as a controller to control the novel hydraulic damper during swing phase. The online simulation is carried out based on MATLAB utilizing the workbench composed of knee prosthesis prototype and self-built gait simulation and evaluation platform, so as to preliminarily verify the online feasibility and effectiveness of the algorithm at different speeds. The offline gait symmetry experiments are designed to more intuitively and effectively compare the performance of NNPC with the fuzzy logical control proposed in previous work. The results show that NNPC improves the gait symmetry from the fuzzy logical control at different walking speeds as the values of symmetry indices are significantly decrease in the range of 5.13% to 33.96%. These results indicate that the proposed variable-damping knee prosthesis can make a good performance on improving the approximation of healthy gait characteristics and meet the fundamental requirements of walking at various walking speeds.