The automatic completion of multiple peg-in-hole assembly tasks by robots remains a formidable challenge because the traditional control strategies require a complex analysis of the contact model. In this paper, the assembly task is formulated as a Markov decision process (MDP), and a model-driven deep deterministic policy gradient (MDDPG) algorithm is proposed to accomplish the assembly task through the learned policy without analyzing the contact states. In our algorithm, the learning process is driven by a simple traditional force controller. In addition, a feedback exploration strategy is proposed to ensure that our algorithm can eciently explore the optimal assembly policy and avoid risky actions, which can address the data eciency and guarantee stability in real assembly scenarios. To improve the learning eciency, we utilize a fuzzy reward system for the complex assembly process. Then, simulations and real experiments of a dual peg-in-hole assembly demonstrate the eectiveness of the proposed algorithm. The advantages of the fuzzy reward system and feedback exploration strategy are validated by comparing the performances of dierent cases in simulations and experiments.

This study aims to present a robust environmental features recognition system (EFRS) for lower limb prosthesis, which can assist the control of prosthesis by predicting locomotion modes of amputees and estimating environmental features in the following steps. A depth sensor and an inertial measurement unit (IMU) are combined to stabilize the point cloud of environments. Subsequently, the 2D point cloud is extracted from origin 3D point cloud and is classified through a neural network. Environmental features, including slope of road, width, and height of stair, were also estimated via the 2D point cloud. Finally, EFRS is evaluated through classifying and recognizing five kinds of common environments in simulation, indoor experiments and outdoor experiments by six healthy subjects and three transfemoral amputees, and databases of five healthy subjects and three amputees are used to validate without training. The classification accuracy of five kinds of common environments reach up to 99.3% and 98.5% for the amputees in the indoor and outdoor experiments, respectively. The locomotion modes are predicted at least 0.6 s before the switch of actual locomotion modes. Most estimation errors of indoor and outdoor environments features are lower than 5% and 10%, respectively. The overall process of EFRS takes less than 0.023 s. The promising results demonstrate the robustness and the potential application of the presented EFRS to help control of lower limb prostheses.

In order to deal with automatic assembly problems for flexible components, we develop contact states analysis, jamming analysis and force control strategies for flexible dual peg-in-hole assembly. Firstly, the contact states in large and small deformation stages are enumerated respectively. Secondly, the relationship between forces and moments is derived, and the jamming states for different stages are analyzed. Thirdly, the control strategies are also presented. Finally, the results of experiments verified the effectiveness of the contact state analysis, jamming analysis and force control strategies.

Visual information is indispensable to human locomotion in complex environments. Although amputees can perceive the environmental information by eyes, they cannot transmit the neural signals to prostheses directly. To augment human-prosthesis interaction, this article introduces a subvision system that can perceive environments actively, assist to control the powered prosthesis predictively, and accordingly reconstruct a complete vision-locomotion loop for transfemoral amputees. By using deep learning, the subvision system can classify common static terrains (e.g., level ground, stairs, and ramps) and estimate corresponding motion intents of amputees with high accuracy (98%). After applying the subvision system to the locomotion control system, the powered prosthesis can help amputees to achieve nonrhythmic locomotion naturally, including switching between different locomotion modes and crossing the obstacle. The subvision system can also recognize dynamic objects, such as an unexpected obstacle approaching the amputee, and assist in generating an agile obstacle-avoidance reflex movement. The experimental results demonstrate that the subvision system can cooperate with the powered prosthesis to reconstruct a complete vision-locomotion loop, which enhances the environmental adaptability of the amputees.

Purpose: This paper aims to realize the automatic assembly process for multiple rigid peg-in-hole components. Design/methodology/approach: This paper develops fuzzy force control strategies for the rigid dual peg-in-hole assembly. Firstly the fuzzy force control strategies are presented. Secondly the contact states and contact forces are analyzed to prove the availability of the force control strategies. Findings: The rigid dual peg-in-hole assembly experimental results show the effectiveness of the control strategies. Originality/value: This paper proposes fuzzy force control strategies for a rigid dual peg-in-hole assembly task.

Accurately predicting human locomotion intent is beneficial in controlling wearable robots and in assisting humans to walk smoothly on different terrains. Traditional methods for predicting human locomotion intent require collecting and labeling the human signals, and training specific classifiers for each new subject, which introduce a heavy burden on both the subject and the researcher. In addressing this issue, the present study liberates the subject and the researcher from labeling a large amount of data, by incorporating an unsupervised cross-subject adaptation method to predict the locomotion intent of a target subject whose signals are not labeled. The adaptation is realized by designing two classifiers to maximize the classification discrepancy and a feature generator to align the hidden features of the source and the target subjects to minimize the classification discrepancy. A neural network is trained by the labeled training set of source subjects and the unlabeled training set of target subjects. Then it is validated and tested on the validation set and the test set of target subjects. Experimental results in the leave-one-subject-out test indicate that the present method can classify the locomotion intent and activities of target subjects at the averaged accuracy of 93.60% and 94.59% on two public datasets. The present method increases the user-independence of the classifiers, but it has been evaluated only on the data of subjects without disabilities. The potential of the present method to predict the locomotion intent of subjects with disabilities and control the wearable robots will be evaluated in future work.