With growing environmental awareness and increasing energy demands, sustainable manufacturing has become a focal point in the industry. Meanwhile, globalization has propelled distributed manufacturing systems as a dominant trend. This paper tackles the energy-efficient distributed heterogeneous hybrid flow-shop scheduling problem (EDHHFSP), aiming to minimize both makespan and total energy consumption. We first formulate a mixed-integer linear programming (MILP) model to provide a benchmark for small instances. More importantly, we propose a novel end-to-end deep reinforcement learning framework based on a heterogeneous graph neural network, which models the scheduling problem as a distributed decision-making process. A key innovation lies in the design of an action space composed of "job–factory" and "operation–machine" pairs, enabling fine-grained, decentralized scheduling decisions. Our approach starts with a novel heterogeneous graph representation of scheduling states, capturing complex interactions among jobs, factories, and machines. A three-stage embedding mechanism is developed to encode real-time scheduling environments. The agent then learns a parameterized policy using the proximal policy optimization (PPO) algorithm, guided by a reward function that balances makespan and energy efficiency. Experimental results demonstrate that our method generalizes well across different problem scales and significantly outperforms traditional heuristics and learning-based baselines in terms of both scheduling quality and energy savings.

This paper investigates the discrete-time sliding mode (DTSM) trajectory tracking control problem for fully actuated autonomous surface vehicles with stochastic network communication delays, based on a self-triggered mechanism. By integrating the Poisson distribution, Thiran approximation, and DTSM control methods, the adverse impact of stochastic network delays on trajectory tracking control is mitigated. To reduce data transmission load and the wear and energy consumption associated with frequent sensor sampling, this study explores enhancing the adaptability of the controller over a larger range of sampling periods. A novel adaptive DTSM power reaching law is proposed, facilitating the development of a DTSM controller that eliminates the need for repeated parameter adjustments across different sampling periods. This innovation enables effective trajectory tracking control over a broader range of sampling periods. Based on this, an uncommon non-predictive DTSM-based self-triggered control strategy is designed within the discrete-time domain. Unlike conventional prediction-based and non-predictive linear state feedback-based discrete-time self-triggered strategies, this method effectively balances computational complexity with the demands for robustness and rapid response. It eliminates the reliance on real-time system state monitoring required by event-triggered mechanisms. This is the first self-triggered strategy proposed to accommodate large sampling periods, thereby further reducing data transmission frequency while ensuring satisfactory trajectory tracking performance. Stability analysis demonstrates that all tracking errors converge to a small region near zero. Simulation results validate the efficacy of the proposed control strategy.

Due to the complexity of modern production processes and environments, most products must pass through multiple workshops from raw materials to finished goods. This article investigates a collaborative scheduling problem in a cascaded dual-shop production setting. Unlike single-shop scheduling or distributed multiworkshop scheduling, this problem emphasizes collaborative optimization between two interdependent workshops. In addition, real-world production often involves a mode where main and suborders must be integrated through mating operations. This study formulates an energy-efficient cascaded dual-shop collaborative scheduling problem with the mating operation (ECDCSP-M). The focus is on developing a mixed-integer linear programming (MILP) model for the ECDCSP-M and designing an end-to-end graph-based deep reinforcement learning (GDRL) approach. A dual-shop heterogeneous graph is constructed to capture the real-time state of the entire system, in which "job-factory" and "operation-machine" pairs are defined as agent actions. A heterogeneous graph neural network (HGNN) is then proposed, employing a three-stage embedding mechanism to model complex relationships, including mating operations. Experimental results show that the proposed method achieves strong generalization across varying problem complexities and provides robust solutions to challenging scheduling scenarios.

In this study, coastal acoustic tomography (CAT) technology was utilized to perform an initial investigation into the observation of underwater small-scale dynamic processes. An underwater monitoring experiment using a CAT network was conducted with four stations at Huangcai Reservoir in Hunan, China. Ray acoustic simulations were employed to match the simulated ray paths of the vertical profile of each pair of trans-ducers to the two identified times of flight (TOFs). To visualize flow field fluctuations caused by the underwater small-scale dynamic processes, an autonomous underwater vehicle (AUV) was deployed to navigate within the observation area. Three-dimensional (3D) inversion techniques were used for multi-layer analyses of the underwater horizontal flow field in the region. The AUV cruising layer’s flow field was mapped and showed consistency with acoustic Doppler current profiler (ADCP) data. The velocity data recorded by the ADCP and CAT were 0.87 m/s and 0.82 m/s, respectively, as the AUV passed by. Additionally, the results were validated through comparison of range-average current measurements and the net inflow error. This study illustrates that the 3D CAT mapping method can effectively reconstruct the 3D flow field, facilitating the observation of underwater small-scale dynamic processes.

This paper investigates discrete-time sliding mode trajectory tracking control for fully actuated autonomous surface vessels (ASVs) with unknown nonlinear dead-zone and saturation inputs, utilizing a switching dynamic event-triggered mechanism (DETM). Through model integration, a direct relationship between ASV position and control inputs is established, simplifying trajectory tracking strategy design. ASVs face dead-zone and saturation constraints in control inputs, where low input signals may not overcome static friction, hindering maneuverability, and further increases are ineffective once actuators reach maximum thrust. Unlike linear dead-zone and saturation input constraints with known parameters, this paper considers a more realistic scenario of unknown nonlinearity, employing adaptive neural networks to approximate and compensate for the resulting unknown dynamics. Moreover, limited internal communication resources constrain real-time inter-subsystem communication in ASVs, while frequent short-period sampling in stable conditions results in unnecessary energy and computational consumption, collectively degrading trajectory tracking performance. A novel switching DETM is proposed to reduce unnecessary data transmission, which switches triggering conditions based on variations in auxiliary dynamic variables. Meanwhile, the controller output variation is integrated into the event-triggered conditions to enhance tracking control performance. Based on this, a discrete-time sliding mode trajectory tracking controller suitable for large sampling periods is designed. This ensures satisfactory tracking control effectiveness while further reducing unnecessary data transmission frequency and conserving limited communication resources within a larger range of sampling periods. All tracking errors are proven to be controlled within a small vicinity near zero. The numerical simulation results validate the efficacy of the proposed control strategy.

This paper investigates theresilientmulti-robot efficient search problem (R-MuRES), which aims at coordinating multiple robots to detect a ‘non-adversarial’ moving target with the minimal expected time. One unique characteristic of R-MuRES among others is the possibility of individual robot's malfunction and withdrawal from the team during task execution, which results in avariablenumber of searchers in the deployment phase and entails that the possibility of team member failures must be considered during the planning stage, particularly in the training phase. We propose a resilient value function factorization (R-FAC) paradigm, which constructs the central value function from individual ones in a resilient manner, taking into account individual robots' failures, and ensures that the constructed central value function has the minimal mean squared temporal difference error across various team compositions. R-FAC stipulates that the individual global maximum (IGM) principle is satisfied for whichever team configuration and thus any functioning robot contributes positively to the remaining team, as long as it executes the greedy policy with respect to the factorized individual value function. Subsequently, we introduce thevariationalvalue decomposition network (V2DN) as one of the instantiated R-FAC algorithms. V2DN employs the$\log$-sum-$\exp$mechanism to construct the central value function from individual ones, enabling it to take a varying number of robots' individual value functions as inputs. Then, we explain why, specifically for the multi-robot search task, the$\log$-sum-$\exp$mechanism is superior to the brute-force summation operation used in the canonical value decomposition network (VDN), and compare V2DN with state-of-the-art MuRES solutions as well as the vanilla VDN algorithm in two canonical MuRES testing environments and show that it achieves the best resiliency score when one or several individual robots quit the team during task execution. Furthermore, we validate V2DN with a real multi-robot system in a self-constructed indoor environment as the proof of concept.

The potential of tactile sensing for dexterous robotic manipulation has been demonstrated by its ability to enable nuanced real-world interactions. In this study, the retrieval of unknown objects from confined spaces, which is unsuitable for conventional visual perception and gripper-based manipulation, is identified and addressed. Specifically, a tactile-sensorized tool stick that well fits in the narrow space is utilized to provide multi-point contact sensing for object manipulation. A reinforcement learning (RL) agent with a hybrid action space is then proposed to acquire the optimal policy for manipulating the objects without prior knowledge of their physical properties. To accelerate on-hardware training, a focused training strategy is adopted with the hypothesis that an agent trained on a small set of representative shapes can be generalized to a wide range of everyday objects. Additionally, a curriculum on terminal goals is designed to further accelerate the hardware-based training process. Comparative experiments and ablation studies have been conducted to evaluate the effectiveness and robustness of the proposed approach, which highlights the high success rate of our solution for retrieving everyday objects.

This paper investigates finite-time trajectory tracking control based on discrete-time sliding mode of underactuated surface vessels with compound disturbances comprising model parameter uncertainties and environmental disturbances under large sampling periods. By introducing the second-order Runge-Kutta method without complex operation to discretize the continuous-time vessel model, a high-precision discrete-time model is first obtained to ensure the controller design accuracy in discrete-time systems. Then, a novel finite-time discrete position tracking controller is developed by constructing a coordinate transformation to address the underactuating problem of surface vessels and convert position tracking error into expected velocity command. The compound disturbance is estimated and compensated by a high-order finite-time discrete disturbance observer. The current research on large sampling period control faces the shortcoming of adjusting parameters repeatedly to accommodate varying sampling periods while balancing convergence speed. To address it and enhance control system adaptability to large sampling periods while reducing operating losses and communication burdens on the sensing system, a novel adaptive reaching law is proposed based on existence conditions of the discrete-time sliding mode control system. Given this, a discrete-time sliding mode based finite-time velocity tracking controller is proposed to achieve stable velocity tracking over a large sampling period range. Finally, all tracking errors are demonstrated to converge within a finite time to a small region near zero. Two examples of comparative simulations validate the efficacy of the developed control strategy.

Inspired by the digital twinning systems, a novel real-time digital double framework is developed to enhance robot perception of the terrain conditions. Based on the very same physical model and motion control, this work exploits the use of such simulated digital double synchronized with a real robot to capture and extract discrepancy information between the two systems, which provides high dimensional cues in multiple physical quantities to represent differences between the modelled and the real world. Soft, non-rigid terrains cause common failures in legged locomotion, whereby visual perception solely is insufficient in estimating such physical properties of terrains. We used digital double to develop the estimation of the collapsibility, which addressed this issue through physical interactions during dynamic walking. The discrepancy in sensory measurements between the real robot and its digital double are used as input of a learning-based algorithm for terrain collapsibility analysis. Although trained only in simulation, the learned model can perform collapsibility estimation successfully in both simulation and real world. Our evaluation of results showed the generalization to different scenarios and the advantages of the digital double to reliably detect nuances in ground conditions.

Current 3D detection networks either rely on 2D object proposals or try to directly predict bounding box parameters from each point in a scene. While former methods are dependent on performance of 2D detectors, latter approaches are challenging due to the sparsity and occlusion in point clouds, making it difficult to regress accurate parameters. In this work, we introduce a novel approach for 3D object detection that is significant in two main aspects: a) cascaded modular approach that focuses the receptive field of each module on specific points in the point cloud, for improved feature learning and b) a class agnostic instance segmentation module that is initiated using unsupervised clustering. The objective of a cascaded approach is to sequentially minimize the number of points running through the network. While three different modules perform the tasks of background-foreground segmentation, class agnostic instance segmentation and object detection, through individually trained point based networks. We also evaluate bayesian uncertainty in modules, demonstrating the over all level of confidence in our prediction results. Performance of the network is evaluated on the SUN RGB-D benchmark dataset, that demonstrates an improvement as compared to state-of-the-art methods.

Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge features in point clouds. Our PAG is constructed by several novel modules, such as Point Atrous Convolution (PAC), Edgepreserved Pooling (EP) and Edge-preserved Unpooling (EU). Similar with atrous convolution, our PAC can effectively enlarge receptive fields of filters and thus densely learn multi-scale point features. Following the idea of non-overlapping maxpooling operations, we propose our EP to preserve critical edge features during subsampling. Correspondingly, our EU modules gradually recover spatial information for edge features. In addition, we introduce chained skip subsampling/upsampling modules that directly propagate edge features to the final stage. Particularly, our proposed auxiliary loss functions can further improve our performance. Experimental results show that our PAG outperform previous state-of-the-art methods on various 3D semantic perception applications.

This paper addressed a challenging problem of wheeled-legged robots with high degrees of freedom exploring in unknown rough environments. The proposed method works as a pipeline to achieve prioritized exploration comprising three primary modules: traversability analysis, frontier-based exploration and hybrid locomotion planning. Traversability analysis provides robots an evaluation about surrounding terrain according to various criteria ( roughness, slope etc.) and other semantic information (small step, stair, bridge etc.), while novel gravity point frontier-based exploration algorithm can effectively decide which direction to go even in unknown environments based on robots' current pose and desired one. Given all these information, hybrid locomotion planner will generate a path with motion mode (driving or walking) encoded by optimizing among different objectives and constraints. Lastly, our approach was well verified in both simulation and experiment on a wheeled quadrupedal robot Pholus.

Observing the absence of predominant planar features in most previous RGB-D simultaneous localization and mapping (SLAM) systems, we introduce a dense RGB-D SLAM, which meanwhile detects and visualizes large planes in the reconstructed indoor scenes. The major challenges are threefold. Firstly, large indoor planes are usually partially observed. Moreover, loop-closure problems should not undermine those detected and reconstructed 3D planes. At last, the efficiency, especially the processing time analysis, is always a major concern in SLAM systems. To unravel these problems, we detect plane segments in each new observed depth map. The detected new and old planes are matched and updated in a frame-to-model fashion. Hence, our plane detection results are directly related to the reconstructed 3D scenes, which eliminates the influence of loop closures. We enhance the efficiency of our system by considering those detected integral plane segments instead of individual points during camera motion tracking. Furthermore, our system accelerates all the processes by heavily applying parallel computations. Experimental results demonstrate that our system can densely reconstruct 3D scenes with detected planes, which also achieves near real-time property.

Performance of current 3D point based detectors is limited by the number of points they can process, consequently limiting their accuracy. In this paper we propose a novel architecture coined as Edge-Aware PointNet, that incorporates geometric shape priors as binary maps, integrated in parallel with the PointNet++ framework, through convolutional neural networks (CNNs). The proposed architecture takes individual object instances as input and learns the task of object recognition for 3D shapes. To train the network, we present a dataset of 31k 2.5D synthetic point clouds rendered from ModelNet40. Through 2.5D representation, the network learns object recognition despite occlusion that enables improved performance on objects from real world, while 2D binary maps enable feature learning that is independent of number of points in the point cloud. Comprehensive experimentation shows that the proposed network is able to improve performance by 2.5% on ModelNet40 and 2.6% on ModelNet10 datasets, as compared to the baseline PointNet++. We also show improved performance as compared to state-of-the-art methods, on a real world RGBD dataset where our network improves results by 8%. Our code and dataset is publicly available at github.com/Merium88/Edge-Aware-PointNet.

Surface blasting operation, for many years, have been an essential step in surface maintenance of a ship hull. Ships in preparation of fresh coat of paint requires its surface to be cleared of contaminants to allow good adherence of paints. In many shipyards, the operation is carried out manually by workers standing at elevated platform dozens meters high with boom lifts or rigging platforms. The working environment is extremely hazardous as other workers are also exposed to air pollutants and sound hazard due to grits impacting the surface. This paper proposes an inexpensive semi-automated grit-blasting system mountable on the boom lift or other platforms that can be moved up and down to perform blasting operations in an enclosed chamber to prevent dispersion of grits and dusts into the atmosphere. The system contains a mechanical blasting module, which performs the blasting operation, and a vision module, which is the `eye' of the system. The vision module can detect the rusted area and implement adaptive path planning for higher blasting efficiency and less grits wastage. To continue the current work, the vision module will be improved to be applicable on surfaces with any color and defects with degree of rusts. The system is also versatile to be used for other cleaning operations, such as water jet cleaning.

Abrasive grit blasting process is widely used in many industries. Cleanliness level of the blasted surface is a critical criterion in abrasive blasting process. Modelling of abrasive blasting process is important to understand the effect of blasting parameters, such as moving speed of the blasting gun, on blasting productivity and quality. Based on the assumption that blasting process is the kinematic energy exchange between the abrasive grits and the removed material from workpiece surface, cleanliness level is modelled by the total energy consumed on the elemental blasted surface for given blasting parameters. Furthermore, as the moving speed affects the energy distribution on the surface, the effect of moving speed of the blasting gun on cleanliness level is analysed. According to the required surface cleanliness level (For example, the required surface quality in shipyard is SA 2.5), the effective productivity is calculated, which can guide the user to select the proper moving speed to improve the productivity and reduce the wastage of the abrasive grits. Finally, the proposed model is validated by experiments, and the result shows a good agreement between the predicted and measured results.

In this paper, we propose novel edge and corner detection algorithms for unorganized point clouds. Our edge detection method evaluates symmetry in a local neighborhood and uses an adaptive density based threshold to differentiate 3D edge points. We extend this algorithm to propose a novel corner detector that clusters curvature vectors and uses their geometrical statistics to classify a point as corner. We perform rigorous evaluation of the algorithms on RGB-D semantic segmentation and 3D washer models from the ShapeNet dataset and report higher precision and recall scores. Finally, we also demonstrate how our edge and corner detectors can be used as a novel approach towards automatic weld seam detection for robotic welding. We propose to generate weld seams directly from a point cloud as opposed to using 3D models for offline planning of welding paths. For this application, we show a comparison between Harris 3D and our proposed approach on a panel workpiece.

Many policy search algorithms have been proposed for robot learning and proved to be practical in real robot applications. However, there are still hyperparameters in the algorithms, such as the exploration rate, which requires manual tuning. The existing methods to design the exploration rate manually or automatically may not be general enough or hard to apply in the real robot. In this paper, we propose a learning model to update the exploration rate adaptively. The overall algorithm is a combination of methods proposed by other researchers. Smooth trajectories for the robot can be produced by the algorithm and the updated exploration rate maximizes the lower bound of the expected return. Our method is tested in the ball-in-cup problem. The results show that our method can receive the same learning outcome as the previous methods but with fewer iterations.

Manta ray's pectoral fins have been a great source of inspiration for propulsive mechanism of autonomous underwater vehicles, due to their propulsive capability. The geometry (shape) and flexibility factors of these fins have been hypothesized to be determinants of the propulsive capability of the fins in terms of thrust generation. In particular, the sweep angle factor has been omitted from previous studies, where it has been commonly set to about 30 degrees. This paper investigates the effects of sweep angle on thrust generation of oscillatory pectoral fins. Forty different fins were designed and fabricated to be experimented in a water channel, which involved measurement of thrust generated by the fins. The experiment was conducted under free stream (0.5 m/s) and still water conditions. Five different sweep angles (0, 10, 20, 30, 40 degrees) were incorporated into eight base designs of different flexibility characteristics to make up the 40 fins. To consider only sweep angle, other geometrical factors were not varied. Within the range of the sweep angle considered, the experimental results showed that sweep angle has no significant influence on the fins' thrust generation, under both free stream and still water conditions. Overall, it can be concluded that sweep angle may not be a determinant of oscillatory pectoral fins' thrust generation.

Frogs are capable of multiple locomotion modes including jumping and swimming, which enables them to adapt to various environmental conditions. This paper demonstrates a frog-inspired robot, which can mimic the swimming motion of a natural frog. The robot is developed based on dielectric elastomer actuators, which exhibits muscle-like behavior such as large voltage-induced deformation, high energy density, fast response and low weight. Inspired by the webbed feet of a frog, the foot actuator of the swimming robot is able to increase its projected area by 66% when subject to high voltage. Actuation of the foot actuators can significantly improve the averaged peak thrust by 34.5%. The total mass of the two dielectric elastomer actuators is 14g which only accounts for 13% of its total mass of 108g. The measured average swimming speed for a square wave voltage of 5kV and 0.25Hz is 19mm/s for the swimming robot. Future work of the project includes optimal design and control of this soft robot.

Blasting and painting operations involve high consumption of materials such as blasting grits and paint. In Singapore, most of the ship hull cleaning and blasting process are manual operations in the shipyard environment. The shipyard workers need to use fork lifts or cherry pickers, which cause several problems such as low efficiency, harmful pollution to operators' health, and inconsistent blasting quality. In order to improve blasting efficiency, this paper proposes a new design for enclosed blasting chamber mechanism to mimic the manual movements of the blasting guns. To replace the manual blasting operations and increase the efficiency, this mechanism realizes automatic motion control of blasting guns and integrates three blasting guns. A prototype blasting chamber is fabricated for testing experiments. This research is jointly conducted with our industry partner.

Surface cleaning and blasting for the ship hull of oil tankers and passenger ships are conventional operations in a ship yard with surface roughness requirements. Several process parameters affect the blasting quality outcome, such as the distance between the blasting nozzles and ship hull, feed rate of copper grit, grit size, etc. In this paper, a mathematical model is derived to describe the relationship between several input parameters and blasting quality. In addition, a blasting experiment is designed using the Taguchi method in order to reduce the number of experiments required for validating the proposed model. Due to resource and time constraints, the experiments will be carried out as future work.

Automatic welding of tubular TKY joints is an important and challenging task for the marine and offshore industry. In this paper, a framework for tubular joint detection and motion planning is proposed. The pose of the real tubular joint is detected using RGB-D sensors, which is used to obtain a real-to-virtual mapping for positioning the workpiece in a virtual environment. For motion planning, a Bi-directional Transition-based Rapidly exploring Random Tree (BiTRRT) algorithm is used to generate trajectories for reaching the desired goals. The complete framework is verified with experiments, and the results show that the robot welding torch is able to transit without collision to desired goals which are close to the tubular joint.

Welding joints for offshore oil rigs present a complicated geometry and require multiple passes. This paper introduces a complete collision-free offline path planning approach for such joints. Collision detection is performed using A* search on a three dimensional grid, where triangular mesh representations of the welding joint and its fixture form the objects. A workflow is proposed for the complete planning process which involves two primary steps; multi-pass planning and intermediate path planning. The paper demonstrates results on a `brace-to-chord' joint, which illustrates the feasibility of the proposed approach.

An automated bead layout methodology is proposed for multi-pass welding on varying seam angle. This methodology will replace the tedious process of ‘teaching and playback’ in the current line of robotic welding. To develop the proposed method, manual flux cored arc welding has been conducted on several workpieces. It is then ascertained that the bead size varies from 25 to 30 mm2in a more ideal welding zone. Therefore, this leads to the assumption of a constant bead size for automated welding. Based on the results from this experiment, the bead layout and welding parameters for new workpiece with different seam angles can be determined. The simulation result show that a uniform bead layout is achieved.

In this paper, a modified entropy-based algorithm is proposed for identification and reconstruction of a complex weld geometry. The edge of the weld geometry is identified based on minimizing a modified entropy-type cost function, and the weld geometry is reconstructed based on the detected edge. In addition, the volume of the weld geometry is computed using the point cloud samples of the identified weld geometry, and the effects of Gaussian noise are also considered. Our simulation results using the proposed reconstruction algorithm demonstrate efficient identification and reconstruction of a complex weld geometry in the presence of Gaussian noise.

We present a deep learning approach to estimation of the bead parameters in welding tasks. Our model is based on a four-hidden-layer neural network architecture. More specifically, the first three hidden layers of this architecture utilize Sigmoid function to produce their respective intermediate outputs. On the other hand, the last hidden layer uses a linear transformation to generate the final output of this architecture. This transforms our deep network architecture from a classifier to a non-linear regression model. We compare the performance of our deep network with a selected number of results in the literature to show a considerable improvement in reducing the errors in estimation of these values. Furthermore, we show its scalability on estimating the weld bead parameters with same level of accuracy on combination of datasets that pertain to different welding techniques. This is a nontrivial result that is counter-intuitive to the general belief in this field of research.

In this paper, we propose a functional task based assistance controller to aid user in the walking task with our Lower Extremity Assistive Device (LEAD). Firstly, a gait period detector, which utilizes a Gaussian Mixture Model (GMM), is developed to estimate the user's current gait period among the six major periods. Then, an impedance based controller is used to apply assistive torques to the hip and knee joints of the user based on the functional task intended at the current gait period. To validate the above control scheme, preliminary experiments have been performed with one healthy subject walking on a treadmill. The results show that the gait period detector can effectively detect each gait period for the whole cycle. Based on measurements of the heart rate, the proposed assistance method has shown that it can effectively assist a human user in walking at speed of 1 km/h.

This paper presents a novel approach employing nonlinear control for stabilization of standing posture for a humanoid robot using only hip joint. The robot is modeled as an acrobot where model parameters are estimated through adaptive algorithm. A `non-collocated partial feedback' controller is applied. This is integrated with a linear feedback control, through LQR. Improved robustness to external push is demonstrated through evaluation in Webots simulator and on a physical humanoid robot, NUSBIP-III ASLAN. Performance comparison with other controllers verifies the effectiveness of the proposed control system.

Teleoperated grasping requires the abilities to follow the intended trajectory from the user and autonomously search for a suitable pre-grasp pose relative to the object of interest. Challenges include dealing with uncertainty due to the noise of teleoperator, human elements and calibration errors in the sensors. To address these challenges, an effective and robust algorithm is introduced to assist grasping during teleoperation. Although without premature object contact or regrasping strategies, the algorithm enable the robot to perform online adjustments to reach a pre-grasp pose for a final grasping. We use three infra-red (IR) sensors that are mounted on the robot hand, and design an algorithm that controls the robot hand to grasp objects using the information from the sensors readings and the interface component. Finally, a series of experiments demonstrate that the system is robust when grasping a wide range of objects and even tracks mobile objects. Empirical data from a 5-subject user study allows us to tune the relative contributions from the IR sensors and the interface component, so as to achieve a balance of grasp assistance and teleoperation.

In order to provide a user-friendly system with simple operation command to grasp different objects successfully, this paper describes a combined approach of real time remote vision-based teleoperation and autonomy for a human-aided robotic grasping. In the teleoperation process, motion tracking is carried out by Kinect in real time to detect the positions of the human shoulder, elbow and hand joints such that the robot can imitate the human. Hand gestures are recognized and used to activate autonomous grasping, which can save time and generate more natural grasping poses. In our system, the robot fulfills some special tasks such as picking up objects using easy commands with Kinect as object sensor. Experiment results show that it is effective and user-friendly.

In this paper, we propose a new model called Augmented Linear Inverted Pendulum (ALIP) in which an augmented function F is added to the dynamic equation of the linear inverted pendulum. The purpose of adding the function F is to modify/adjust the inverted pendulum dynamics in such a way that disturbance caused by un-modeled dynamics (legs, arms, etc.) can be compensated or minimized. By changing the key parameters of the augmented function we can easily modify the inverted pendulum dynamics. The desired walking motion with maximized stability margin is achieved by optimizing the key parameters using genetic algorithm. The disturbance created by the un-modeled dynamics is minimized because full robot dynamics is considered in the optimization process. Simulations results show that the walking gait obtained using the proposed method is more stable than that obtained using the Linear Inverted Pendulum Mode (LIPM).

We present a new method to generate biped walking patterns for biped robots on uneven terrains. Our formulation uses a universal stability criterion that checks whether the resultant of the gravity wrench and the inertia wrench of a robot lies in the convex cone of the wrenches resulting from contacts between the robot and the environment. We present an algorithm to compute the feasible acceleration of the robot's CoM (center of mass) and use that algorithm to generate biped walking patterns. Our approach is more general and applicable to uneven terrains as compared with prior methods based on the ZMP (zero-moment point) criterion. We highlight its applications on some benchmarks.

Based on the distance algorithm by Gilbert et al., this paper presents a numerical algorithm for computing the intersection of the boundary of a compact convex set with a ray emanating from an interior point of the set, which is known as the ray-shooting problem. Affinely independent points on the boundary of the convex set are also determined such that the intersection point can be written as their convex combination. Because of its high efficiency and other good qualities, this algorithm provides superior solutions to three fundamental problems in robotic grasping, i.e., force-closure test, contact force optimization, and grasp quality evaluation, which can be formulated as the ray-shooting problem.

This paper presents an algorithm to compute the minimum distance from a point to a convex cone inn-dimensional space. The convex cone is represented as the set of all nonnegative combinations of a given set. The algorithm generates a sequence of simplicial cones in the convex cone, such that their distances to the single point converge to the desired distance. In many cases, the generated sequence is finite, and therefore, the algorithm has finite-convergence property. Recursive formulas are derived to speed up the computation of distances between the single point and the simplicial cones. The superior efficiency and effectiveness of this algorithm are demonstrated by applications to force-closure test, system equilibrium test, and contact force distribution, which are fundamental problems in the research of multicontact robotic systems. Theoretical and numerical comparisons with previous work are provided.

Biological inspired control approaches based on central pattern generator (CPG) have been used to generate human-like rhythmic locomotion for bipedal robots. CPG consists of several oscillators with coupled mutual inhibition. In the application of CPG to bipedal walking, one of the important problem is how to coordinate oscillators so as to achieve stable walking, since without proper coordination the rhythmic trajectory generated by CPG may fail to control the walking. To solve this problem, this paper presents a method of coordination between two oscillators using phase information. In the method, approximated phase values of the oscillators are derived and used as the feedback to coordinate two oscillators. Furthermore, coordination between multiple oscillators with different frequencies and phases has also been explored. This method is verified with a 2D robust walking controlled by four oscillators. Several walking scenarios are tested: adding external force, change walking frequency and step length during walking. Robust walking is achieved in our simulation.

Due to the extensive utilization in engineering designs, various vibration controller designs have been investigated to meet the design specifications. However, not all of them exactly meet the design requirements. In this paper, mechatronic design quotient (MDQ) approach and genetic algorithm are coupled together to perform this evaluation and optimization task. MDQ is presented to formulate an evaluation function of passive vibration controller design for flexible beam structures, and GA is then used to optimize this function so as to achieve a design solution with the highest MDQ value. Experimental results from one damper and two dampers are presented and compared. It showed that the linear dampers design with the proposed method can achieve the desired performance.

This paper presented a method of bipedal walking pace supervision by the adjustment of stride-frequency and step-length simultaneously. A reinforcement learning algorithm is designed to learn the walking stride-frequency; A transition plan aims to adjust the step-length or update motion phases according to the dynamic feedback; A momentum based estimation gives another layer of stride-frequency adjustment when the learning agent has not gained enough experiences. Simulation experiments showed this learning based motion supervision is effective for maintaining stable walking under perturbations with a balanced performance of energy consumption and robustness.

This paper presents a method for optimally generating stable bipedal walking gaits, based on a truncated Fourier series formulation with coefficients tuned by genetic algorithm. It also provides a way to adjust the stride-frequency, step-length or walking pattern in real-time. The proposed approach to gait synthesis is not limited by the robot kinematic structure and can be used to satisfy various motion assumptions. It is also easy to generate optimal gaits on terrains of different slopes or on stairs under different motion requirements. Dynamic simulation results show the validity and robustness of the approach. The gaits generated resulted in human-like motions optimized for stability, even walking speed and lower leg-strike velocity of the swing foot

This paper presents two frontal plane algorithms for 3D dynamic bipedal walking. One of which is based on the notion of symmetry and the other uses reinforcement learning algorithm to learn the lateral foot placement. The algorithms are combined with a sagittal plane algorithm and successfully applied to a simulated 3D bipedal robot to achieve level ground walking. The simulation results showed that the choice of the local control law for the stance-ankle roll joint could significantly affect the performance of the frontal plane algorithms.

This paper presents the design and implementation of an evolvable hardware based autonomous robot navigation system using intrinsic evolution. Distinguished from the traditional evolutionary approaches based on software simulation, an evolvable robot controller at the hardware gate-level that is capable of adapting dynamic changes in the environments is implemented. In our approach, the concept of Boolean function is used to construct the evolvable controller implemented on an FPGA-based robot turret, and evolutionary computing is applied as a learning tool to guide the artificial evolution at the hardware level. The effectiveness of the proposed evolvable autonomous robotic system is confirmed with the physical real-time implementation of robot navigation behaviors on light source following and obstacle avoidance using a robot with traction fault.

We propose a general but simple bipedal walking control architecture that incorporates intuitive control and learning algorithms. The learning algorithm is mainly used to generate the key parameters for the swing leg. The intuitive control is used to maintain the height and body posture. Based on the proposed architecture, a control algorithm is constructed and applied to a planar biped and a 3D biped. By applying an appropriate local speed control mechanism, we demonstrate that the bipeds can successfully achieve walking of 100 seconds within a reasonable number of trials. No dynamic models or nominal joint trajectory data are required for the implementations.

Simple intuitive control strategies can be used to compel bipedal robots to walk over sloped terrain. We describe an algorithm for walking dynamically and steadily over sloped terrain with unknown slope gradients and transition locations. The algorithm is developed based on geometric considerations. The overall algorithm is very simple and does not require the biped to have an extensive sensory system for walking over moderate slopes. The ground is detected blindly using only foot contact switches. Using a few simple strategies, we have compelled a simulated 7-link planar biped to walk up and down slopes and over rolling terrain.

Virtual model control (VMC) has previously been successfully applied to steady dynamic walking of a planar biped. This control methodology requires very low computation because it does not calculate the inverse dynamics of the biped. An adaptive control approach based on radial basis function neural networks (RBFNNs) has also been previously proposed to enhance VMC. However, such implementation is computationally intensive. We propose a simpler adaptive VMC that allows the biped to adapt to mass variations without using RBFNNs. We implement the resulting system and demonstrate the robustness of the implementation by simulating the biped walking over rolling terrain.