This paper addresses the morphology transformation problem of an underwater self-reconfigurable modular robotic system. Morphology decomposition and reconnections are reduced to mitigate transformation failures and the overhead of underwater wireless communication, giving rise to subgraph matching problems. We propose an efficient probabilistic decomposition method by constraining the search depth of maximal common subgraphs of the initial and goal morphologies. The computational complexity reduces from$O(n^{2})$to$O(n)$. The decomposition yields a swarm of heterogeneous clusters, which are interconnected modular robots of varying quantities. The heterogeneity makes the exchange of clusters’ designated positions in the goal morphology not immediately feasible. Subsequently, we present Distributed Control with minimal In-situ task Refinement (DCIR). DCIR is proven to ensure collision-free and deadlock-free morphology transformation. The numerical simulations involving up to 641 modular robots and experiments on 6 robots have shown that DCIR scales well with the number of modular robots, runs in real time, and reduces traveling distances by at least 14% and communication costs by about half, compared to the distributed control with homogeneous task exchange and the modified surface sliding method. Note to Practitioners—This paper presents a distributed control approach to transform the morphologies. Considering the limited communication bandwidth, the disconnections between modular robots are minimized. The proposed distributed control approach refines tasks locally to transform the morphologies, and it scales well to the number of modular robots. This effort is orthogonal to the existing studies on the structures of the modular system. However, the positioning of the underwater robots in this study was assumed known or given by an underwater motion capture system, and it should be further investigated.

Quadrotors have been applied to a wide range of industrial applications in recent years. It is vital to ensure the safety of a quadrotor operated by a human pilot in a practical environment that usually involves dynamic obstacles. This article develops an onboard Operational Safety Filter (OSF) for a quadrotor in an environment with dynamic obstacles. The developed OSF integrates motion prediction of dynamic obstacles and an improved backup controller into the existing backup controller-based OSF framework. The motion prediction of dynamic obstacles aims to address the dynamic obstacles. The improved backup controller can provide enhanced operational freedom for a quadrotor with respect to the existing backup controllers. The developed onboard OSF is applied to quadrotors in simulation and in the real world to evaluate its effectiveness in addressing dynamic obstacles, improving operational freedom, and running on a real quadrotor.

Although the fast tool servo (FTS) exhibits unique advantages for surface texturing, its intrinsic form accuracy is capped by the position and motion accuracy of the manufacturing system. In this article, a novel FTS combining the sensing and control capability of 2-DOF tool position and cutting force is developed to enable the high-performance adaptive surface texturing. The proposed design of FTS features a motion-decoupled symmetric configuration and functions via leveraging the system dynamics and online position monitoring of two pairs of actuation-force sensing observers. Analytical models and the differential evolution algorithm are established to describe the essential working performances and guide the optimal structural parameter design, which are validated using finite element simulation. The performance assessments suggest positioning resolution around 20 nm and force-sensing resolution at the millinewton level for both cutting and thrust directions, along with motion strokes of tens of micrometers and resonant frequency of up to 4172 Hz. Moreover, the adaptive texturing of microgrooved surfaces with consistent geometry is demonstrated without prior knowledge of workpiece shapes. The outcomes of this article contribute to developing the next-generation of intelligent FTS for flexible and intelligent manufacturing.

An increasing number of Autonomous Mobile Robots (AMRs) are used in warehouses and factories in recent years. The risk of some of the AMRs being out of control is surging. Although Reinforcement Learning (RL)-based approaches have achieved dramatic success in the motion planning of a large number of AMRs, the available RL-based motion planning approaches cannot provide a safety guarantee for the remaining functional AMRs if some of the AMRs are out of control. To this end, this paper develops a scalable Multi-agent RL (MARL) with Control Barrier Function (CBF)-based shields algorithm. The MARL with CBF-based shields algorithm can address complex high-level tasks by MARL and deal with the safety issue of every single functional AMR by a low-level CBF-based shield. A CBF-based shield is designed for every single functional AMR to ensure that the action of the functional AMR is safe, even if an uncontrollable AMR is pursuing the functional AMR. Experiments are conducted based on simulated warehouse environments to evaluate the effectiveness and scalability of a safe RL-based motion planning approach (The safe RL-based motion planning approach developed in this study is demonstrated in a video: https://youtu.be/I7ja5nFVpY4). developed according to the MARL with CBF-based shields algorithm.

Cable-Driven Parallel Robots (CDPRs) have been proposed for a variety of applications such as material handling, rehabilitation, and instrumentation. However, the collision-free constraint of CDPRs limits the workspace of CDPRs and the feasible position of anchor points. To address the collision-free constraint of CDPRs, a data-driven kinematic control scheme is developed for CDPRs, enabling a CDPR to control its pose even if suffering collisions between a cable and the base or the end-effector. To deal with the collisions, the data-driven kinematic control scheme utilizes a motion model obtained based on data samples of the motion of the CDPR, rather than the Jacobian matrix of the CDPR, to map a control law in the task space to the time derivative of the length of cables in the joint space. To evaluate the effectiveness of the developed data-driven kinematic control scheme, experiments of controlling a suspended CDPR with two cables allowing collisions are conducted.

This article proposes a predictive end-effector control method for manipulators operating on mobile platforms subjected to unwanted base motion. Time series is used to forecast the base motion using historical state information. Then, a trajectory specified in the inertial frame is transformed to a predicted trajectory with respect to the manipulator. By tracking this transformed trajectory, the manipulator negates the base motion. A model-predictive control problem is formulated via quadratic programming (QP) to track said trajectory over the prediction horizon. Only the first control action in the control sequence is constrained by kinematic feasibility. In this manner, QP can be swiftly solved with linear inequality constraints. It is shown that the actual joint trajectory executed by the manipulator is always kinematically feasible. Moreover, tracking error can still be reduced despite future predicted control actions being infeasible. The method is validated through both simulation and experiment. The proposed method can reduce pose error by over 60% compared to a proportional–integral feedback controller.

This paper presents an observer-integrated Reinforcement Learning (RL) approach, called Disturbance OB-server Network (DOB-Net), for robots operating in environments where disturbances are unknown and time-varying, and may frequently exceed robot control capabilities. The DOB-Net integrates a disturbance dynamics observer network and a controller network. Originated from conventional DOB mechanisms, the observer is built and enhanced via Recurrent Neural Networks (RNNs), encoding estimation of past values and prediction of future values of unknown disturbances in RNN hidden state. Such encoding allows the controller generate optimal control signals to actively reject disturbances, under the constraints of robot control capabilities. The observer and the controller are jointly learned within policy optimization by advantage actor critic. Numerical simulations on position regulation tasks have demonstrated that the proposed DOB-Net significantly outperforms conventional feedback controllers and classical RL policy.

Many sampling strategies often consider the goal and obstacle population to bias/restrict the search area, and they however become less effective when the robot has many degrees of freedom. This paper explores the nonhomogeneous restriction imposed by the obstacles and presents an improved SBP approach enhanced by heterogeneous dimensionality reduction of the full configuration space. Based on the projection residual, a new Dirichlet process (DP) mixture model is proposed to capture a number of Dimensionality-Reduced Spaces (DRSs), which offer the planning spaces with fewer dimensions than its single-DRS counterpart. Then, the sampling and planning procedures are unified with a proposed transversality condition, connecting sampled nodes across DRSs. At last, a quadratic programming is formulated and quickly solved to map the found path in DRSs to an output path in the full configuration space. Numerical simulations on path planning problems of a high-dimensional Intervention Autonomous Underwater Vehicle (I-AUV) have been conducted, showing the feasibility and efficiency of the proposed method.

It is evident that corticomuscular coherence (CMC), representing the functional coupling between motor cortex and muscle tissues, plays a crucial role in neurophysiologic studies and applications. It is hypothesized that there is an unknown time delay comprising at least neural conduction time in the process of corticomuscular interaction. In this study, we developed a novel delay estimation method, defined as the rate of voxels change (RVC) for the estimation of time delay in two coupled physiological signals. The RVC is the dynamic variation of the local CMCs observed in different time offsets. Both simulation and physiological data confirm the capability of RVC in estimating cortical-muscular delay. The underlying mechanisms of individual discrepancy of the latency is also investigated via exploring the correlation between delays, brain activity and motor performance. Correlation analyses indicate an intrinsic link between the connectivity strength of the brain network and the length of time delay in cortical-muscular interactions.

This paper presents a unified motion planning approach for an Intervention Autonomous Underwater Vehicle (I-AUV) in a cluttered environment with localization uncertainty. With the uncertainty being propagated by an information filter, a trajectory optimization problem closed by a Linear-Quadratic-Gaussian controller is formulated for a coupled design of optimal trajectory, localization, and control. Due to the presence of obstacles or complexity of the cluttered environment, a set of feasible initial I-AUV trajectories covering multiple homotopy classes are required by optimization solvers. Parameterized through polynomials, the initial base trajectories are from solving quasi-quadratic optimization problems that are linearly constrained by waypoints from RRTconnect, while the initial trajectories of the manipulator are generated by a null space saturation controller. Simulations on an I-AUV with a 3 DOF manipulator in cluttered underwater environments demonstrated that initial trajectories are generated efficiently and that optimal and collision-free I-AUV trajectories with low state uncertainty are obtained.