When robots replicate human actions in peg-in-hole assembly tasks, such as USB Type-A insertion and removal, the complexity of the process and frequent obstructions from the inner walls make it difficult for robots to handle collisions or avoid jamming. These difficulties contribute to a low success rate in assembly. This paper proposes a vision-guided reinforcement learning pre-assembly combined with tactile feedback-based pose estimation adjustment method for peg-in-hole assembly, achieving significant improvement in success rates for complex assembly tasks. First, during the pretraining process of reinforcement learning, high-reward sample data is collected, and a behaviour cloning (BC) algorithm is constructed based on sample data structure. The network is pretrained as a policy regression layer. Under sparse reward conditions, outputs of the twin delayed deep deterministic policy gradient (TD3) network and the BC network are combined to improve training stability and accelerate convergence, enhancing the efficiency of vision-based assembly. Then, to address the instability caused by collisions with the inner and outer walls of the hole when vision-based assembly remains incomplete, an in-hand pose estimation algorithm based on the Gelsight visuotactile sensor is integrated. This algorithm facilitates real-time adjustments to the position of the robot’s end-effector, improving the likelihood of successful peg-in-hole assembly. Finally, to validate the effectiveness of the proposed method, experiments were conducted using the V-REP simulation platform and the real Franka robot platform. In the experiments, success rates of 90-93% and 80-85%, respectively, were achieved.

In the field of robotics, particularly in human–robot interaction, rapid and precise torque control is crucial. This study presents a closed-loop iterative optimized (CIO) approach designed to improve current tracking in servo systems, positioning it as a feasible alternative to traditional proportional-integral controllers. The proposed method innovatively combines a fractional-order proportional-integral-derivative (FOPID) controller with linear matrix inequality (LMI) technique and genetic algorithm in a closed-loop iterative setting. This integration not only boosts the FOPID controller's response speed, but also leverages the robustness of LMI, enhancing stability under various operating conditions. The inclusion of heuristic algorithms in this system enables a more dynamic and efficient search for optimal control parameters, aligning the controller's performance with the complex requirements of contemporary robotics. Experimental data underscore that this approach significantly increases torque response speed and the control system's bandwidth, vital for satisfying the dynamic needs of current robotic applications.

This paper describes the control of a novel Magnetic Actuated Flexible-joint Robotic Surgical (MAFRS) camera system with four degrees of freedom (4-DOF) for single incision laparoscopic surgery. Based on the idea of motion decoupling, we designed a novel MAFRS system which is consists of an external driving device and a motor-free insertable wireless robotic device with a hollow flexible joint. Due to the problems of abdominal wall obstruction and variability in abdominal wall thickness during the actual application of the MAFRS system, as well as the existence of multiple permanent magnets and magnetically conductive media, high- precision position and attitude control of the insertable device without onboard motors has always been a challenge. We use the external driving device to generate a magnetic field to control the position and attitude of the internal robotic device. Aiming at the automatic precise tilt motion control of the novel MAFRS camera system, we have developed a closed-loop control scheme using the Deep Deterministic Policy Gradient (DDPG) algorithm. By referring to the damping characteristics of human muscles, a virtual-muscle method is proposed to eliminate the chattering problem of the MAFRS camera at specific angles. The experimental investigations indicate that the internal robotic device can be effectively controlled under different abdominal wall thicknesses. The tilt motion control accuracy is within 0.5°, and it has good adaptability and antiinterference performance.

This paper presents the design and implementation of a novel magnetic actuated flexible-joint robotic surgery (MAFRS) camera system with four-degree-of-freedom(4-DOF) for single incision laparoscopic surgery. The design is based on the idea of motion decoupling and consists of an external driving device and a motor-free insertable wireless camera device with a flexible joint. Meanwhile, the design features a unified mechanism for anchoring, navigating, and tilting an insertable camera by an externally generated magnetic field. The control of the insertable camera without onboard motors has always been a problem. We have creatively adopted flexible materials and the new magnetic circuit design. It not only simplifies the structural design of the insertable camera but also meets the requirements of application scenarios. The initial prototype results in a compact insertable camera robot with a 19mm diameter and a 108.5mm length. The design concepts are analyzed theoretically and verified experimentally. The experiments validate that the proposed capsule robot design provides reliable camera anchoring and translation capabilities under various testing conditions, and the tilt angle of the camera can meet the practical application requirements.

To improve the search efficiency of robotic grasping detection, this paper presents a novel search algorithm based on the image pyramid. It significantly reduces the search space for grasping position detection using the coarse-to-fine strategy. The proposed method searches the positions from the top layer of the pyramid, and initializes the search area at the next layer. The sparse automatic encoder is employed to construct the model which is used to evaluate the grasp quality. The experimental results demonstrate that the proposed search algorithm can improve efficiency of the robotic grasping detection with the comparative performance on the grasp quality.

Possessing two manipulators heightens the ability of dual-arm robots (DAR) to conduct complex tasks, while raising hazard that the two manipulators might collide with each other or with other objects. DARs are usually equipped with a collision-free motion planning algorithms (CFMPA) to prevent the two manipulators from colliding. The CFMPA searches the motion paths of robot manipulators, which are expected to be as short and smooth as possible under the premise of ensuring safety. It is important to ensure that the algorithm is correct and efficient. It is not enough to apply traditional test methods to determine whether DARs can work in safety-critical applications. In this paper, theorem proving technology is employed to analyze the correctness and efficiency of a classical CFMPA. The CFMPA is outlined, and then formalized in high order logic with the theorem prover HOL4. An inconsistency in the range of motions of the robot manipulators in the algorithm is discovered. An improved algorithm is therefore proposed. Formal verification with HOL4 proves the correctness and efficiency of the proposed algorithm that has already run on a real DAR as well, in conformity with our expectation.

Sambot is a module robot system, with the advantages of self-assembly. A target robotic configuration can be organized by a group of Sambots. A novel motion planning method for Sambot configuration using model checking is presented in this paper. This hierarchical method contains two layers. The abstract logic layer is responsible for the discrete planning of Sambots configuration. The robot and the environment are all modeled as timed automata. System requirements are formalized as Computational Tree Logic (CTL) formulas. Model checking is applied on the system model. The verification result gives the optimal discrete plans for the configuration of Sambot. In physical layer, a sample-based planner generates the trajectory trace considering the dynamics of Sambot and the suggested high level plans. The experiment results illustrate the effectiveness of our approach.

Recently, the open-source robot operating system (ROS) has been growing rapidly in the robotics community. However, the ROS runs on Linux, which does not provide timing guarantees for robot motion. This paper present a hybrid real-time ROS architecture on multi-core processor “RGMP-ROS”, which consists of two parts including the non-real-time subsystem “GPOS (General Operating system)” and the real-time one “RTOS (Real-time Operating system)”. The GPOS is comprised of non-real-time ROS nodes running in Linux, while the RTOS only contains real-time ROS nodes running in Nuttx. To get higher operational efficiency, the RGMP-ROS system is executed by a dual-core processor, one CPU for GPOS and the other for RTOS. The RGMP-ROS has used in the controller of a 6-DOF modular manipulator, and its effectiveness and efficiency are demonstrated by software testing and experiments. The main contributions of the present work lie in the realization of real-time ROS architecture and the application of multi-core processor in the hybrid control of an industrial robot.

Coverage control is one of the fundamental problems in WSN (wireless sensor network) and determines the ability to monitor the entire WSN system. Based on the Voronoi diagram and the CVT (Centralized Voronoi Tessellation) theory, and combined with the Lloyd's algorithm, we propose a dynamic covering algorithm of WSN to achieve a dynamic coverage among different areas by adjusting the geometric boundaries to the target coverage area and synchronously collaboratively dispatching many WSN nodes. In the simulations, we performed covering experiments with static boundary and dynamic boundary, respectively. The coverage degree and coverage efficiency are compared under different shapes of the target coverage area and different number of nodes. It is indicated that the control algorithm is effective.

A latitude method for the trajectory planning of spraying on spherical surface is presented. The latitude method is used to optimize the time and coating thickness in the spray painting. The start curve, the velocity of the spray gun and the width between neighboring paths are the main factors to affect the final coating quality. Spray painting time is determined by the start curve of the gun, while selection of the velocity and width contribute to the coating thickness together. Based on the paint deposition model of flat surface, the deposition model on the cylindrical surface is derived. The start curve on the spherical surface is derived from the Bounding-Box method. The spray gun velocity and the width between neighboring paths are determined through the optical function in which the coating thickness is the optimized target. The simulation shows that the latitude method presented in this paper can solve the problem of the trajectory planning on spherical surface.

The propulsive efficiency is the key issue related to the practical application of the robotic fish. The negative work of the muscle of the biological fish reveals the efficient propulsion mechanism of swimming. In this paper, a distributed control system is presented for the robotic fish in an experiment platform. In order to study the relationship among the parameters, the negative work and the propulsive efficiency, this system can real time control each joint of the robotics fish and feedback the information. So the system is composed of three parts: the master-slave controller, the network and the driver of the joint motor. FPGA is chosen to accomplish the motor control and the data transition. Also the network based on LVDS has a high transfer rate to guarantee real-time and reliability of the system operation.

This paper presents a monitoring system of building electricity using IPv6 to establish a network. This smart metering system consists of three parts: the host software, the network and the sensor nodes. The network, whose data transmits via Zigbee wireless communication protocol, is designed based-on IPv6 protocol, and builds the IPv6 protocol on IEEE 802.15.4 wireless network. The Sensor node has a unique IP address and the sampling rate is set according to the host system. With real-time measurement of power, current and voltage values including RMS, instantaneous value and peak value, each node achieved accurate data sampling and communication stability. The host software is designed for building test characteristics, having a tree hierarchy and friendly interface to user. The reliability and accuracy of this monitoring system are verified in the experiment.

Inspired by the swarm behaviours of social insects, research into the self-assembly of swarm robots has become an attractive issue in the robotic community. Unfortunately, there are very few platforms for self-assembly and locomotion in the field of swarm robotics. The Sambot is a novel self-assembling modular robot that shares characteristics with swarm robots and self-reconfigurable robots. Each Sambot can move autonomously and connect with the other. This paper discusses the concept of combining self-assembly and locomotion for swarm robots. Distributed control algorithms for self-assembly and locomotion are proposed. Using five physical Sambots, experiments were carried out on autonomous docking, self-assembly and locomotion. Our control algorithm for self-assembly can also be used to realize the autonomous construction and self-repair of robotic structures consisting of a large number of Sambots.

This paper presents a novel self-assembly modular robot (Sambot) that also shares characteristics with self-reconfigurable and self-assembly and swarm robots. Each Sambot can move autonomously and connect with the others. Multiple Sambot can be self-assembled to form a robotic structure, which can be reconfigured into different configurable robots and can locomote. A novel mechanical design is described to realize function of autonomous motion and docking. Introducing embedded mechatronics integrated technology, whole actuators, sensors, microprocessors, power and communication unit are embedded in the module. The Sambot is compact and flexble, the overall size is 80×80×102mm. The preliminary self-assembly and self-reconfiguration of Sambot is discussed, and several possible configurations consisting of multiple Sambot are designed in simulation environment. At last, the experiment of self-assembly and self-reconfiguration and locomotion of multiple Sambot has been implemented.

Self-assembly is a process during which pre-existing components are autonomously organized into some special patterns or structures without human intervention. In this paper, we propose a new control algorithm on distributed self-assembly which is implemented on the Sambot robot platform. A directional self-assembly control model is proposed, in which a configuration connection state table is used to represent the configuration of the robotic structures composed of multiple Sambots. There are three types of Sambots, docking Sambots, SEED Sambot and Connected Sambots. All docking Sambots adopt behavior-based controller that is independent of target configuration. The SEED Sambot and Connected Sambots are used to implement configuration growth. Self-assembly experiments of snake-like and quadruped configurations are conducted on the Sambot platform with five Sambots. The experimental results show the effectiveness and scalability of the distributed self-assembly algorithm.

Componentization is an important method to improve the reusability of robot software and reduce the difficulty of system design. In this paper, we propose a component based design framework for robot software architecture. First, the robot system is functionally decomposed into reusable components. On this basis, the static model and run-time model of component are established, and a component interface definition language based on the model is designed. Second, a lightweight middleware is proposed according to the communication mode between robot components, and a component development tool and a visual component assembly environment based on the middleware are designed to facilitate the developers. Finally, an application based on the framework is introduced to verify the validation of the design framework.

With the rapid development of robot technology, It is becoming increasingly difficult to design and maintain robot systems. This makes it necessary to reuse hardware and software modules to lower the difficulty and the cost for the robot system design. In this paper we present a model of modular robot-F-Model. It uses functional component modules to construct function-oriented robot applications. Firstly the background of modular robot system is analyzed, and several basic conceptions in F-Model are elaborated. Then, the main framework of the model is constructed, and the model of functional component and its property are introduced to make a more in-depth description of the framework. Finally, the feasibility of F-Model is established by a simple instance.

As a distributed computing system, a CNC system needs to be operated reliably, dependably and safely. How to design reliable and dependable software and perform effective verification for CNC systems becomes an important research problem. In this paper, we propose a new modeling method called TTM/ATRTTL (Timed Transition Models/All-Time Real-Time Temporal Logics) for specifying CNCsystems. TTM/ATRTTL provides full supports for specifying hard real-time and feedback that are needed for modeling CNC systems. We also propose a verification framework with verification rules and theorems and implement it with STeP and SF2STeP. The proposed verification framework can check reliability, dependability and safety of systems specified by our TTM/ATRTTL method. We apply our modeling and verification techniques on an open architecture CNC (OAC) system and conduct comprehensive studies on modeling and verifying a logical controller that is the key part of OAC. The results show that our method can effectively model and verify CNC systems and generate CNC software that can satisfy system requirements in reliability, dependability and safety.

In this paper, we propose to implement hybrid operating systems based on two-level hardware interrupts. To separate real-time and non-real-time hardware interrupts by hardware, we show that it is easier to build up hybrid systems with better performance. We analyze and discuss the key issues for implementing a hybrid system based on this and implement a hybrid system called RTLinux-THIN (Real-Time LINUX with Two-level Hardware Interrupts) on the ARM architecture by combining ARM Linux kernel 2.6.9 and muC/OS-II. We conduct experiments on a set of real application programs including mplayer [20], Bonnie [4] and iperf [13] and compare the interrupt latency distributions for RTLinux-THIN (with and without cache locking), RTAI and Linux on a hardware platform based on Intel PXA270processor [12]. The experimental results show that RTLinux-THIN improves real-time interrupt latencies and provides better predictability.