The focus of this research is to develop a learning-based method that computes self-motion manifolds (SMMs) efficiently and accurately to enable real-time global fault-tolerant motion planning. The proposed method first develops a learnable, closed-form representation of SMMs based on Fourier series. A cellular automaton is then applied to cluster workspace locations having the same number of SMMs and group SMMs with similar shape by homotopy classes, such that the SMMs of each homotopy class can be accurately learned by a neural network. To approximate the SMMs of an arbitrary workspace location, a neural network is first trained to predict the set of homotopy classes belonging to this workspace location. For each set of homotopy classes, another neural network is trained to approximate the Fourier series coefficients of the SMMs, and the joint configurations along the SMMs can be retrieved using the inverse Fourier transform. The proposed method is validated on planar 3R positioning, spatial 4R positioning, and spatial 7R positioning and orienting robots, using 10,000 randomly sampled workspace locations each. The results show that the proposed method can approximate SMMs with high accuracy redand is much faster than the traditionally used nullspace projection method, a sampling-based method, and a grid-based method. The performance of the proposed method in real-time fault-tolerant motion planning applications is also demonstrated using the simulation of the spatial 7R robot and physical experiments on a planar 3R robot. Due to the computational efficiency of the proposed method, both robots are able to quickly plan trajectories which maximize the likelihood of task completion after the failure of one arbitrary joint.

Hand gesture recognition has been playing an important role in robotic applications, which allows robots to communicate with humans in an effective way. However, it typically desires to process high-dimensional data, such as images or sensor measurements. To address the computational challenges due to the data growth, it is desirable to select most relevant features during recognition by reducing the redundancy of the data. In this paper, we propose a novel feature selection approach based on the separable nonnegative matrix factorization (NMF) framework for hand gesture recognition. In particular, we adopt a nonconvex regularization term, i.e., the ratio of matrix nuclear norm and Frobenius norm. The proposed method reduces the data dimension by utilizing the data low-rankness in an adaptive way. To address the nonconvexity of the proposed model, we reformulate it by introducing an auxiliary variable and then apply the alternating direction method of multipliers (ADMM). Furthermore, a variety of numerical experiments on binary and grayscale hand gesture images demonstrate the efficiency of the proposed feature selection approach in improving the quality of factorization and its potential impact on robotic applications.

There are currently two existing methods to compute the fault-tolerant workspace of a redundant robot arm for a given set of artificial joint limits. However, both of these methods are very computationally expensive. This article proposes using a mixture density network to learn the probability that a rotation angle belongs to the fault-tolerant rotation ranges. A difference filter is used to remove outlying rotation angles predicted by the network, and the remaining rotation angles are grouped together to generate the fault-tolerant workspace. Because this method is highly computationally efficient, it can be used alongside a genetic algorithm to compute the optimal artificial joint limits to maximize the area of the fault-tolerant workspace for a given robot arm. The predicted fault-tolerant workspace is compared to the actual fault-tolerant workspace, which proves the effectiveness of this algorithm. The computational speed of this proposed algorithm is roughly 390 times faster than the traditional method. Finally, a trajectory is placed within the fault-tolerant workspace predicted by the proposed method, and the experimental results show that this trajectory is tolerant to arbitrary joint failures.

This article considers the problem of planning a trajectory that maximizes the probability that a robot will be able to complete a set of point-to-point tasks, after experiencing locked joint failures. The proposed approach first develops a method to calculate the probability of task failure for an arbitrary trajectory based on its failure scenarios, which are efficiently computed by identifying the ranges of task point self-motion manifolds. Then, a novel trajectory planning algorithm is proposed to find the optimal trajectory with maximum probability of task completion. The planning algorithm exploits the overlap of self-motion manifold bounding boxes, as opposed to always using the shortest distance, to determine an optimal trajectory. The proposed trajectory planning algorithm is demonstrated on planar positioning 3R, spatial positioning 4R, and spatial positioning/orienting 7R redundant robots, resulting in average improvement of 17%, 22%, and 30%, respectively, compared to the best shortest distance trajectory.

A novel motion planning method is proposed to generate human-like motion for anthropomorphic robot arms. Its highlight is to consider the robot arm to be human-like not only in its configuration but also in its motion patterns. To achieve this, the intrinsic mechanisms of human arm motion generation are transferred to robot motion planning. First, human arm motion is modeled using human arm motion primitives. The mechanisms of human arm motion generation are dissected from a large number of motion samples, reflected in the types, sequencing and quantification rules/laws of the primitives. Next, the human arm motion patterns are studied based on primitive chains. Finally, a new motion planning method is built that autonomously performs motion pattern decisions, motion time allocation, and joint trajectory generation. The proposed method is validated by a motion planning app and a robot simulation.

There is an increasing interest in accurately predicting natural human arm motions for areas like human-robot interaction, wearable robots, and ergonomic simulations. This paper studies the problem of predicting natural fingertip and joint trajectories in human arm reaching movements. Compared to the widely-used minimum jerk model, the 5-parameter logistic model can represent natural fingertip trajectories more accurately. Based on 3520 human arm motions recorded by a motion capture system, regression learning is used to predict the five parameters representing the fingertip trajectory for a given target point. Then, the elbow swivel angle is predicted using regression learning to resolve the kinematic redundancy of the human arm at discrete fingertip positions. Finally, discrete joint angles are solved based on the predicted elbow swivel angles and then fitted to a continuous 5-parameter logistic function to obtain the joint trajectory. This method is verified using 48 test motions, and the results show that this method can generate accurate human arm motions.