30 January 2023 in IEEE Transactions on Industrial Informatics
Multirobot path planning leads multiple robots from start positions to designated goal positions by generating efficient and collision-free paths. Multirobot systems realize coordination solutions and decentralized path planning, which is essential for large-scale systems. The state-of-the-art decentralized methods utilize imitation learning and reinforcement learning methods to teach fully decentralized policies, dramatically improving their performance. However, these methods cannot enable robots to perform tasks efficiently in relatively dense environments without communication between robots. We introduce the transformer structure into policy neural networks for the first time, dramatically enhancing the ability of policy neural networks to extract features that facilitate collaboration between robots. It mainly focuses on improving the performance of policies in relatively dense multirobot environments under conditions where robots do not communicate with each other. Furthermore, a novel imitation reinforcement learning framework is proposed by combining contrastive learning and double deep Q-network to solve the problem of difficulty training policy neural networks after introducing the transformer structure. We present results in the simulation environment and compare the resulting policy against advanced multirobot path-planning methods in terms of success rate. Simulation results show that our policy achieves state-of-the-art performance when there is no communication between robots. Finally, we experimented with a real-world case using a total of three robots in our robotic laboratory.
20 September 2022 in IEEE Transactions on Industrial Electronics
Multiagent path finding (MAPF) is employed to find collision-free paths to guide agents traveling from an initial to a target position. The advanced decentralized approach utilizes communication between agents to improve their performance in environments with high-density obstacles. However, it dramatically reduces the robustness of multiagent systems. To overcome this difficulty, we propose a novel method for solving MAPF problems. In this method, expert data are transformed into supervised signals by proposing a hot supervised contrastive loss, which is combined with reinforcement learning to teach fully-decentralized policies. Agents reactively plan paths online in a partially observable world while exhibiting implicit coordination without communication with others. We introduce the self-attention mechanism in the policy network, which improves the ability of the policy network to extract collaborative information between agents from the observation data. By designing simulation experiments, we demonstrate that the learned policy achieved good performance without communication between agents. Furthermore, real-world application experiments demonstrate the effectiveness of our method in practical applications.
10 August 2022 in IEEE Transactions on Industrial Electronics
It is a challenging problem for redundant wheeled mobile manipulators to satisfy multiple physical constraints and avoid obstacles while performing certain tasks, not to mention constraining tracking performance. In this article, a control scheme based on hierarchical quadratic programming-prescribed performance control (HQP-PPC) is proposed. The first layer of HQP can achieve trajectory tracking, obstacle avoidance, and physical constraints. The second layer of HQP is used to guide the direction of obstacle avoidance and produce a smoother planned path. The prescribed performance function (PPF) can ensure tracking performance so that the physical constraints and obstacle avoidance constraints are satisfied in actual motion. Moreover, the proposed controller can guarantee the tracking performance of the end effector due to the characteristics of the PPF. Finally, the effectiveness and superiority of the proposed method are verified by simulations and experiments.
26 April 2022 in IEEE Transactions on Instrumentation and Measurement
Point cloud registration is an essential step for free-form blade reconstruction in industrial measurement. Nonetheless, measuring defects of the 3D acquisition system unavoidably result in noisy and incomplete point cloud data, which renders efficient and accurate registration challenging. In this paper, we propose a novel global registration method that is based on the minimum potential energy (MPE) method to address these problems. The basic strategy is that the objective function is defined as the minimum potential energy optimization function of the physical registration system. The function distributes more weight to the majority of inlier points and less weight to the noise and outliers, which essentially reduces the influence of perturbations in the mathematical formulation. We decompose the solution into a globally optimal approximation procedure and a fine registration process with the trimmed iterative closest point algorithm to boost convergence. The approximation procedure consists of two main steps. First, according to the construction of the force traction operator, we can simply compute the position of the potential energy minimum. Second, to find the MPE point, we propose a new theory that employs two flags to observe the status of the registration procedure. We demonstrate the performance of the proposed algorithm on four types of blades. The proposed method outperforms the other global methods in terms of both accuracy and noise resistance.
2 August 2023 in IEEE Transactions on Industrial Electronics
Human–robot interaction (HRI) systems are crucial in robotics, natural, fast-response, and multimodal are the future trends in their development. However, current interaction methods have the following flaws: 1) slow response of action recognition algorithms for generic scenes, especially at the beginning stage; 2) insufficient feature extraction and fusion capabilities for spatiotemporal graph data; and 3) no good paradigm of body–hand recognition in HRI. To overcome these bottlenecks, we propose a fast-response graph convolutional network (GCN) for body–hand gesture recognition. First, we propose a dynamic-static parallel network for dynamic body gestures that is responsive and accurate. Second, we propose a spatiotemporal graph attention module to improve the graph data fusion effect in the dynamic-static network. Third, we implement a complete command module to form complete commands with body and hand information for interactions and control of the robot. Finally, extensive experiments on four datasets and real-world experiments were conducted to demonstrate that our network is capable of fast response and accurate recognition of dynamic body gestures at the beginning stage, verifying the effectiveness of skeleton-based body-hand gesture recognition, with a clear advantage over the state-of-the-art.
10 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Fault detection for distributed parameter systems (DPSs) generally requires the complete model information to be known so far. However, for numerous industrial applications, it is common that accurate first-principles physical models are extremely difficult to obtain. Hence, the applicability of traditional model-based methods is being restricted. To pave the way, an adaptive neural network (AdNN) is constructed to simultaneously estimate the state variable and the unknown nonlinearity for a class of partially known nonlinear DPSs. Moreover, considering that full-state measurement is unrealistic in applications, the proposed adaptive neural observer is based on a reduced-order model, which also increases the computation efficiency. Then, the residual generation and evaluation are conducted using the output estimation error of the proposed adaptive neural observer. Bearing the effects of the neglected fast dynamics in mind, a data-driven threshold generation scheme is proposed. Extensive experimental results are presented and analyzed to validate the effectiveness of the proposed method.