To solve the complexity of the traditional motion intention recognition method using a multi-mode sensor signal and the lag of the recognition process, in this paper, an inertial sensor-based motion intention recognition method for a soft exoskeleton is proposed. Compared with traditional motion recognition, in addition to the classic five kinds of terrain, the recognition of transformed terrain is also added. In the mode acquisition, the sensors’ data in the thigh and calf in different motion modes are collected. After a series of data preprocessing, such as data filtering and normalization, the sliding window is used to enhance the data, so that each frame of inertial measurement unit (IMU) data keeps the last half of the previous frame’s historical information. Finally, we designed a deep convolution neural network which can learn to extract discriminant features from temporal gait period to classify different terrain. The experimental results show that the proposed method can recognize the pose of the soft exoskeleton in different terrain, including walking on flat ground, going up and downstairs, and up and down slopes. The recognition accuracy rate can reach 97.64%. In addition, the recognition delay of the conversion pattern, which is converted between the five modes, only accounts for 23.97% of a gait cycle. Finally, the oxygen consumption was measured by the wearable metabolic system (COSMED K5, The Metabolic Company, Rome, Italy), and compared with that without an identification method; the net metabolism was reduced by 5.79%. The method in this paper can greatly improve the control performance of the flexible lower extremity exoskeleton system and realize the natural and seamless state switching of the exoskeleton between multiple motion modes according to the human motion intention.

With the rapid development of microelectronic technology, increasing wearable devices are available for us in daily lives. These wearable devices are usually powered by batteries, so the endurance of wearable devices is limited by battery capacity. Biomechanical energy harvesting (EH) is a promising approach to extend the endurance or replace batteries to power microelectronic devices. In this paper, we would first review the different types of EH devices and analyze the key technologies. Secondly, to compare the advantages and disadvantages of different EH devices, the design guidelines of the EH device is proposed. According to the design guidelines, an EH device with a weight of only 110 g is designed, which is lighter than the suspended-load backpack (38 kg) and the knee harvester (1.6 kg). Our EH device is able to convert the vibrations energy generated by the motion of lower limbs into electrical energy. Finally, to verify whether our EH device meets the design guidelines, three sets of experiment are conducted to evaluate the performance of the EH device. Experiment A is used to monitor the metabolic energy and electricity energy. According to experiment data, we calculate the COH and TCOH of EH device. The lowest COH and TCOH are 58 and 59, respectively. The TCOH of our EH device is higher than suspended-load backpack (30.7) and the knee harvester (13.6). Experiment B is used to test the adaptability of the EH device under the different conditions of terrains and walking speeds. The EH device is able to harvest energy in different terrains (up and down stair, at the treadmill with a slope of 0${}^{°}$, 5${}^{°}$ and 10${}^{°}$) and at different speeds(4 km/h~8 km/h). The converted electrical power is up to 7.71 mW during walking at the speed of 8 km/h and is up to 5.28 mW when going up stairs. Experiment C is conducted to investigate the influence of the EH device on human motion by measuring the torque of the ankle, knee, and hip joints. When comparing the curves of torque, the EH device does not influence the biological moment of joints, indicating the EH device does not interfere with the movement. At the same time, another method to calculate the TCOH by calculating the net work done by the muscle in a gait cycle is proposed. When comparing the TCOH calculated by the metabolic energy with the TCOH calculated by the additional work done by the muscle, the results are basically the same. Meanwhile, the variation of the latter calculation result is smaller, indicating the method proposed by us is more precise.