Soft robots can perform effectively inspecting than rigid robots in some special environments such as nuclear pipelines and high-voltage cables. This article presents a versatile quadruped soft rod-climbing robot (SR-CR) that consists of four bending actuators and a telescopic actuator. The bending actuator is composed of flexible bellows with multiple folding air chambers, elastic telescopic layer (ETL), and strain-limiting layer (SLL). The telescopic actuator provides the energy for the robot to climb forward. The SR-CR is activated by a control strategy that alternates the body deformation and feet pneumatic clenched for stable climbing. The robot can climb rods at 90°, with the maximum speed of up to 2.33 mm/s (0.018 body length/s). At 0.83 HZ, the maximum moving speed of the robot in climbing horizontally parallel rods can reach 18.43 mm/s. In addition, the SR-CR can also achieve multiple impressive functions, including turning around a corner at a rate of 7 mm/s (0.054 body length/s), carrying a payload of 3.7 times its self-weight on horizontal rods at a speed of 9 mm/s (0.069 body length/s).

A new stable adaptive controller based on a neural network for underactuated systems is proposed in this paper. The control scheme has been developed for two underactuated systems as examples. The Furuta pendulum and the Inertia Wheel Pendulum (IWP) have been examined in this paper. The presented approach aims to address the control problem of the given system in swing up, stabilization, and disturbance rejection. To avoid oscillations, two adaptive neural networks (ANNs) are implemented. The first one is used to approximate the equivalent control online and the second one to minimize the oscillations.

Efficient algorithm integration is a key issue in aerial robotics. However, only a few integration solutions rely on a cognitive approach. Cognitive approaches break down complex problems into independent units that may deal with progressively lower-level data interfaces, all the way down to sensors and actuators. A cognitive architecture defines information flow among units to produce emergent intelligent behavior. Despite the improvements in autonomous decision-making, several key issues remain open. One of these issues is the selection, coordination, and decision-making related to the several specialized tasks required for fulfilling mission objectives. This work addresses decision-making for the cognitive unmanned-aerial-vehicle architecture coined as ARCog. The proposed architecture lays the groundwork for the development of a software platform aligned with the requirements of the state-of-the-art technology in the field. The system is designed to provide high-level decision-making. Experiments prove that ARCog works correctly in its target scenario.

We present a 3D reconstruction method using brightness and camera motion estimation for registering local colon structure in colonoscopy. The proposed method is based on reverse projection from 2D fold contours to 3D space, motion estimation from 3D reconstructed points between neighboring frames, and model registration to reconstruct the fold structure. On the synthetic colon, the average percentages of the reconstructed depth error and circumference error are about 14.2% and 15.2%, respectively. The accuracy is enough for the navigation and control in capsule robot. This work demonstrates that the proposed method is superior to the methods using single-frame-based brightness intensity.

A novel 3-R(RRR)R+R (R as revolute joint) hybrid antenna mechanism (HAM) is proposed for noncircular polarized antenna. First, its mobility characteristic is analyzed. Besides, its kinematics is deduced, and the velocity and acceleration are obtained. Afterward, its dynamic model is established. The actuation torques of each actuation joint are obtained. Its actuation torques are verified by mathematical model analysis and dynamic simulation. Furthermore, its workspace is also presented. Finally, the motion characteristics experimental results show that the 3-R(RRR)R+R HAM can carry out the azimuth and pitch motion. This research work serves as a fundamental theoretical basis for its further application.

This paper deals with the multi-objective optimal design of a novel 6-degree of freedom (DOF) hybrid spray-painting robot. Its kinematic model is obtained by dividing it into serial and parallel parts. The dynamic equation is formulated by virtual work principle. A performance index for evaluating the compactness of robot is presented. Taking compactness, motion/force transmissibility, and energy consumption as performance indices, the optimal geometric parameters of the robot are selected in the Pareto-optimal set by constructing a comprehensive performance index. This paper is very useful for the development of the spray-painting robot.

In recent years, omnidirectional wheels have found more applications in the design of automated guided vehicles (AGV). In this work, LuGre friction model is used for an omnidirectional wheel. A test setup that includes a single omnidirectional wheel is designed and constructed to identify the model parameters. With the help of the constructed test setup, the longitudinal friction characteristic of the omnidirectional wheel is obtained, and the model is verified via validation tests. In addition, for the first time, the effect of lateral frictional force on longitudinal motion is examined for an omnidirectional wheel through experiments.

Interaction between a robot and its environment requires perception about the environment, which helps the robot in making a clear decision about the object type and its location. After that, the end effector will be brought to the object’s location for grasping. There are many research studies on the reaching and grasping of objects using different techniques and mechanisms for increasing accuracy and robustness during grasping and reaching tasks. Thus, this paper presents an extensive review of research directions and topics of different approaches such as sensing, learning and gripping, which have been implemented within the current five years.

A data association algorithm for simultaneous localization and mapping (SLAM) based on central difference joint compatibility (CDJC) criterion and clustering is proposed to obtain the data association results. Firstly, CDJC criterion is designed to calculate joint Mahalanobis distance. Secondly, ordering points to identify the clustering structure is used to divide all observed features into several groups. Thirdly, CDJC branch and bound method is designed to be performed in each group. The results based on simulation data and benchmark dataset show that the proposed algorithm has low computational complexity and provide accurate association results for SLAM of mobile robot.

Quadrotors are unmanned aerial vehicles with many potential applications ranging from mapping to supporting rescue operations. A key feature required for the use of these vehicles under complex conditions is a technique to analytically solve the problem of trajectory planning. Hence, this paper presents a heuristic approach for optimal path planning that the optimization strategy is based on the indirect solution of the open-loop optimal control problem. Firstly, an adequate dynamic system modeling is considered with respect to a configuration of a commercial quadrotor helicopter. The model predicts the effect of the thrust and torques induced by the four propellers on the quadrotor motion. Quadcopter dynamics is described by differential equations that have been derived by using the Newton–Euler method. Then, a path planning algorithm is developed to find the optimal trajectories that meet various objective functions, such as fuel efficiency, and guarantee the flight stability and high-speed operation. Typically, the necessary condition of optimality for a constrained optimal control problem is formulated as a standard form of a two-point boundary-value problem using Pontryagin’s minimum principle. One advantage of the proposed method can solve a wide range of optimal maneuvers for arbitrary initial and final states relevant to every considered cost function. In order to verify the effectiveness of the presented algorithm, several simulation and experiment studies are carried out for finding the optimal path between two points with different objective functions by using MATLAB software. The results clearly show the effect of the proposed approach on the quadrotor systems.

This work presents a multimode flight framework control scheme for a quadrotor based on the super twisting algorithm. The controller design stages for six flight control modes are presented. The stability proof for each flight mode is carried out by means of Lyapunov functions, while the stability analysis for the complete control scheme, when a transition from one flight mode to another occurs, is demonstrated using the switching nonlinear systems theory. The performance of the proposed framework is shown in a 3D simulation environment considering a forest fire detection task, which takes into account external disturbances.

Effective motion planning and localization are necessary tasks for swarm robotic systems to maintain a desired formation while maneuvering. Herein, we present an inchworm-inspired strategy that addresses both these tasks concurrently using anchor robots. The proposed strategy is novel as, by dynamically and optimally selecting the anchor robots, it allows the swarm to maximize its localization performance while also considering secondary objectives, such as the swarm’s speed. A complementary novel method for swarm localization, that fuses inter-robot proximity measurements and motion commands, is also presented. Numerous simulated and physical experiments are included to illustrate our contributions.

For acquiring a broad view in an unknown environment, we proposed a control strategy based on the Bézier curve for the snake robot raising its head. Then, an improved discretization method was developed to accommodate the backbone curves with more complex shapes. Besides, in order to determine the condition of using the improved discretization method, energy of framed space curve is introduced originally to estimate the shape complexity of the backbone curve. At last, based on degree elevation of the Bézier curve, an obstacle avoidance strategy of the head-raising motion was proposed and validated through simulation.

The current contribution presents a new sinkage sensor specified for an unmanned ground vehicle to find the exact sinkage zone of a wheel interacting with the soil particles. This sensor will be wrapped around the wheel, and consequently, contact analog outputs will be used in soil deposition and bulldozing effect prediction. Furthermore, the new sensor will be used for a novel soil flow calculation estimating the total mass variation of the control volume of soil particles beneath the wheel. Accordingly, the spiral model simulating the displacement of the particle is implemented to calculate the soil deposition.

This paper presents the detailed dynamic modeling of a quadruped robot. The forward and inverse kinematic analysis of each leg of the proposed model is deduced using Denavit-Hartenberg (D-H) parameters. It desires to calculate the optimal feet forces of the quadruped robot’s joint torque, which is essential for its online control. To find out the optimal feet force distribution, two approaches are implemented to fulfill the locomotion objective. The four-legged quadruped robot and torso body’s detailed dynamics are modeled to generate an equation of motion for the robot control system. The Euler–Langrage theory has been used to find out the joint motion. The computer simulation results are presented to verify the effectiveness of the dynamic model.

Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.

In this paper, the k-valued logic control network is introduced to study the cooperative pursuit control problem of multiple underactuated underwater vehicles (UUVs) with time delay in three-dimensional space. The semi-tensor product of matrices is used to solve the complex calculation problem of the large dimension matrix. The influence of communication delay on multiple UUVs’ optimization and cooperative pursuit control is expressed in a matrix. Under the leadership of evader UUV, the control algorithm can ensure that all the pursuit UUVs reach the desired position. The stability of the closed loop system is proved.

Wheel slip prediction on rough terrain is crucial for secure, long-term operations of planetary exploration rovers. Although rough, unstructured terrain hampers mobility, prediction by modeling wheel–terrain interactions remains difficult owing to unclear terrain conditions and complexities of terramechanics models. This study proposes a vision-based approach with machine learning for predicting wheel slip risk by estimating the slope from 3D information and classifying terrain types from image information. It considers the slope estimation accuracy for risk prediction under sharp increases in wheel slip due to inclined ground. Experimental results obtained with a rover testbed on several terrain types validate this method.