In the field of laparoscopic surgery, research is currently focusing on the development of new robotic systems to assist practitioners in complex operations, improving the precision of their medical gestures. In this context, the performance of these robotic platforms can be conditioned by various factors, such as the robot’s accessibility and dexterity in the task workspace. In this paper, we present a new strategy for improving the kinematic and dynamic performance of a 7-degrees of freedom robot-assisted camera-holder system for laparoscopic surgery. This approach involves the simultaneous optimization of the robot base placement and the laparoscope mounting orientation. To do so, a general robot capability representation approach is implemented in an innovative multiobjective optimization algorithm. The obtained results are first evaluated in simulation and then validated experimentally by comparing the robot’s performances implementing both the existing and the optimized solution. The optimization result led to a 2% improvement in the accessibility index and a 14% enhancement in manipulability. Furthermore, the dynamic performance criteria resulted in a substantial 43% reduction in power consumption.

Prostate cancer is the second most common malignancy in American men. High-dose-rate brachytherapy is a popular treatment technique in which a large, localized radiation dose is used to kill cancer. Utilization of curvilinear catheter implantation inside the prostate gland to provide access channels to host the radiation source has shown superiority in terms of improved dosimetric constraints compared to straight needles. To this aim, we have introduced an active needle to curve inside the prostate conformal to the patient’s specific anatomical relationship for improved dose distribution to the prostate and reduced toxicity to the organs at risk. This work presents closed-loop control of our tendon-driven active needle in water medium and air using the position feedback of the tip obtained in real time from an ultrasound (US) or an electromagnetic (EM) tracking sensor, respectively. The active needle consists of a compliant flexure section to realize bending in two directions via actuation of two internal tendons. Tracking errors using US and EM trackers are estimated and compared. Results show that the bending angle of the active needle could be controlled using position feedback of the US or the EM tracking system with a bending angle error of less than 1.00 degree when delay is disregarded. It is concluded that the actuation system and controller, presented in this work, are able to realize a desired bending angle at the active needle tip with reasonable accuracy paving the path for tip tracking and manipulation control evaluations in a prostate brachytherapy.

Performing tasks in agriculture, such as fruit monitoring or harvesting, requires perceiving the objects’ spatial position. RGB-D cameras are limited under open-field environments due to lightning interferences. So, in this study, we state to answer the research question: “How can we use and control monocular sensors to perceive objects’ position in the 3D task space?” Towards this aim, we approached histogram filters (Bayesian discrete filters) to estimate the position of tomatoes in the tomato plant through the algorithm MonoVisual3DFilter. Two kernel filters were studied: the square kernel and the Gaussian kernel. The implemented algorithm was essayed in simulation, with and without Gaussian noise and random noise, and in a testbed at laboratory conditions. The algorithm reported a mean absolute error lower than 10 mm in simulation and 20 mm in the testbed at laboratory conditions with an assessing distance of about 0.5 m. So, the results are viable for real environments and should be improved at closer distances.

The ability of quadruped robots to overcome obstacles is a critical factor that limits their practical application. Here, a design concept and a control algorithm are presented that aim at enhancing the explosive force of quadruped robots during jumping by utilizing elastic energy storage components. The hind legs of the quadruped robot are designed as energy storage units. Tension springs are utilized as components for storing energy and are installed in a parallel structure on the hind leg. Energy is stored during the compression process of the robot’s torso and released during the jumping phase. The optimal foot force is calculated using a single rigid body model. The mapping relationship between the force applied to the foot and the resulting joint torque is established by developing a dynamic model of the hind legs. Simulation experiments were conducted using the Webots physics engine to compare the impact of varying spring stiffness on joint torque during the jumping process. This study determined the optimal spring stiffness under specific conditions. The hind legs’ torque saving ratio reaches 19%, and the energy-saving ratio reaches 13%, which validates the effectiveness and feasibility of integrating elastic energy storage components.

When generating simultaneous joint movements of a humanoid with multiple degrees of freedom to replicate human-like movements, the approach of joint synergy can facilitate the generation of whole-body robotic movement with a reduced number of control inputs. However, the trade-off of minimizing control inputs and keeping characteristics of movements makes it difficult to improve movement performance in a simple control manner. In this paper, we introduce an approach by connecting and constraining these joints. It is inspired by the fascia network of the human body, which constrains the whole-body movements of a human. Compared to when only joint synergy is used, the effectiveness of the proposed method is verified by calculating the errors of joint positions of generated movements and human movements. The paper provides a detailed exploration of the proposed method, presenting simulation-experimental results that affirm its effectiveness in generated movements that closely resemble human movements. Furthermore, we provide one possible method on how these concepts can be implemented in actual robotic hardware, offering a pathway to improve movement control in humanoid robots within their mechanical limitations.

In order to improve the positioning accuracy of industrial robots, this paper proposes a global calibration method for planar parallel robot considering joint errors, which solves the problem that the existing calibration methods only consider part of the error sources and the calibration accuracy is poor, and improves the calibration efficiency and robot positioning accuracy. Consequently, it improves calibration efficiency and the overall precision of robot positioning. Firstly, the error model of overdetermined equations combined with structural parameters is established, and the global sensitivity of each error source is analyzed. Based on the measurement data of laser tracker, the local error source is identified by the least square method, which improves the local error accuracy by 88.6%. Then, a global error spatial interpolation method based on inverse distance weighting method is proposed, and the global accuracy is improved by 59.16%. Finally, the radial basis function neural network error prediction model with strong nonlinear approximation function is designed for global calibration, and the accuracy is improved by 63.05%. Experimental results verify the effectiveness of the proposed method. This study not only provides technical support for the engineering application of this experimental platform but also provides theoretical guidance for the improvement of the accuracy of related robot platforms.

Visual odometry (VO) is a key technology for estimating camera motion from captured images. In this paper, we propose a novel RGB-D visual odometry by constructing and matching features at the superpixel level that represents better adaptability in different environments than state-of-the-art solutions. Superpixels are content-sensitive and perform well in information aggregation. They could thus characterize the complexity of the environment. Firstly, we designed the superpixel-based feature SegPatch and its corresponding 3D representation MapPatch. By using the neighboring information, SegPatch robustly represents its distinctiveness in various environments with different texture densities. Due to the inclusion of depth measurement, the MapPatch constructs the scene structurally. Then, the distance between SegPatches is defined to characterize the regional similarity. We use the graph search method in scale space for searching and matching. As a result, the accuracy and efficiency of matching process are improved. Additionally, we minimize the reprojection error between the matched SegPatches and estimate camera poses through all these correspondences. Our proposed VO is evaluated on the TUM dataset both quantitatively and qualitatively, showing good balance to adapt to the environment under different realistic conditions.

In this paper, an unmanned bicycle (UB) with a reaction wheel is designed, and a second-order mathematical model with uncertainty is established. In order to achieve excellent balancing performance of the UB system, an adaptive controller is designed, which is composed of nominal feedback control, compensating control using extreme learning machine observer and reaching control via integral terminal sliding mode (ITSM) and barrier function (BF)-based adaptive law. Owing to the features of BF-based ITSM (BFITSM), not only any uncertainty or disturbance upper bound is not needed any longer but also the finite-time convergence of the closed-loop system can be ensured with a predefined error bound. Moreover, the BF-based control gain can be adaptively adjusted according to the update of the lumped uncertainty such that the overestimation is removed. The stability analysis of the closed-loop system is given according to Lyapunov theory. Comparable experimental results on an actual UB are carried out to validate the superior balancing performance of the proposed controller.

In order to solve the problem of the insufficient adaptability of the current small- and medium-sized casting sorting robot gripper, we have designed a casting sorting robot bionic gripper with rigid–flexible coupling structures based on the robot topology theory. The second-order Yeoh model was used to statically model the clamping belt in the gripper to derive the relationship between the external input air pressure and the bending angle of the driving layer, and the feasibility of multiangle bending of the driving layer was verified by finite element analysis. The maximum gripping diameter of the gripper is 140 mm, and in order to test the adaptive gripping ability of the gripper, a prototype of the casting sorting robot gripper is prepared, and the pneumatic control system and human–machine interface of the gripper are designed. After several experimental analyses, the designed casting sorting robot gripper is characterized by strong adaptability and high robustness, with a maximum load capacity of 930 g and a maximum wrap angle of 296°, which can complete the gripping operation within 1 s, and the comprehensive gripping success rate reaches 96.4%. The casting sorting robot gripper designed in the paper can provide a reference for the design and optimization of various types of shaped workpiece gripping manipulators.

Hyper-redundant cable-driven manipulators (CDMs) are widely used for operations in confined spaces due to their slender bodies and multiple degrees of freedom. Most research focuses on their path following but not path planning. This work investigates a deep deterministic policy gradient (DDPG)-based path-planning algorithm for CDMs in multi-obstacle environments. To plan passable paths under many constraints, a DDPG algorithm is modified according to features of CDMs. To improve adaptability of planned paths, a specialized reward function is newly designed. In this function, such factors as smoothness, arrival time and distance are taken into account. Results of simulations and physical experiments are presented to demonstrate the performances of the proposed methods for planning paths of CDMs.

Accurate online estimation of the payload parameters benefits robot control. In the existing approaches, however, on the one hand, only the linear friction model was used for online payload identification, which reduced the online estimation accuracy. On the other hand, the estimation models contain much noise because of using actual joint trajectory signals. In this article, a new estimation algorithm based on parameter difference for the payload dynamics is proposed. This method uses a nonlinear friction model for the online payload estimation instead of the traditionally linear one. In addition, it considers the commanded joint trajectory signals as the computation input to reduce the model noise. The main contribution of this article is to derive a symbolic relationship between the parameter difference and the payload parameters and then apply it to the online payload estimation. The robot base parameters without payload were identified offline and regarded as the prior information. The one with payload can be solved online by the recursive least squares method. The dynamics of the payload can be then solved online based on the numerical difference of the two parameter sets. Finally, experimental comparisons and a manual guidance application experiment are shown. The results confirm that our algorithm can improve the online payload estimation accuracy (especially the payload mass) and the manual guidance comfort.

The wheeled-legged robot combines the advantages of wheeled and legged robots, making it easier to assist people in completing repetitive and time-consuming tasks in their daily lives. This paper presents a study on the kinematic and dynamic modeling, as well as the controller design, of a wheeled biped robot with a parallel five-bar linkage mechanism as its leg module. During the motion of the robot, the robot relies on the tilt angle of the inverted pendulum, and this angle often results in the tilting of the chassis of the robot, presenting challenges for the installation of upper-body payloads and sensor systems. The controller proposed in this paper, which is developed by decoupling the primary motions of the robot and designing a multi-objective, multilevel controller, addresses this issue. This controller employs the pendulum pitch angle of the equivalent inverted pendulum model as the control variable and compensates for the chassis tilt angle (CTA). This control method can effectively reduce the CTA of such robots and eliminate the need for additional counterweights. It also provides a more spacious structural design for accommodating upper-body devices. The effectiveness of this control framework is verified through variable height control, walking on flat ground, and carrying loads over rough terrain and slopes.

Autonomous exploration in unknown environments has become a critical capability of mobile robots. Many methods often suffer from problems such as exploration goal selection based solely on information gain and inefficient tour optimization. Recent reinforcement learning-based methods do not consider full area coverage and the performance of transferring learned policy to new environments cannot be guaranteed. To address these issues, a dual-stage exploration method has been proposed, which combines spatial clustering of possible exploration goals and Traveling Salesman Problem (TSP) based tour planning on both local and global scales, aiming for efficient full-area exploration in highly convoluted environments. Our method involves two stages: exploration and relocation. During the exploration stage, we introduce to generate local navigation goal candidates straight from clusters of all possible local exploration goals. The local navigation goal is determined through tour planning, utilizing the TSP framework. Moreover, during the relocation stage, we suggest clustering all possible global exploration goals and applying TSP-based tour planning to efficiently direct the robot toward previously detected but yet-to-be-explored areas. The proposed method is validated in various challenging simulated and real-world environments. Experimental results demonstrate its effectiveness and efficiency. Videos and code are available at https://github.com/JiatongBao/exploration.

Evolution has shown that legged locomotion is most adequate for tasks requiring versatile movement on land, allowing animals to traverse a wide variety of environments ranging from natural terrain to artificial, man-made landscapes with great ease. By employing well-designed control schemes, this ability could be replicated for legged robots, enabling them to be used in critical situations that still pose great danger to human integrity, such as search and rescue missions, inspection of hazardous areas, and even space exploration. This work characterizes the quadruped robot and contact dynamics that will compose our in-house simulator to be used for prototyping locomotion control schemes applied to quadruped robots. The proposed simulator computes the robot dynamics using the Recursive Newton-Euler and Composite-Rigid-Body algorithms with a few modifications to make certain aspects relevant for contact detection and control more easily accessible; furthermore, a compliant contact force method alongside stick-slip friction modeled the contact dynamics. To allow the robot to move, a simple PD-independent joint controller was implemented to track a desired leg trajectory. With the same robot and controller implemented using the MuJoCo simulation software, this work evaluates the proposed simulator by comparing characteristic locomotion signals such as the trunk pose and the ground reaction forces. Results showed similar behavior for both simulators, especially with regard to the contact detection, despite the significantly different contact models. Lastly, final remarks to enhance our simulator’s performance are suggested to be explored in future works.

Thanks to its real-time computation efficiency, deep reinforcement learning (DRL) has been widely applied in motion planning for mobile robots. In DRL-based methods, a DRL model computes an action for a robot based on the states of its surrounding obstacles, including other robots that may communicate with it. These methods always assume that the environment is attack-free and the obtained obstacles’ states are reliable. However, in the real world, a robot may suffer from obstacle localization attacks (OLAs), such as sensor attacks, communication attacks, and remote-control attacks, which cause the robot to retrieve inaccurate positions of the surrounding obstacles. In this paper, we propose a robust motion planning method ObsGAN-DRL, integrating a generative adversarial network (GAN) into DRL models to mitigate OLAs in the environment. First, ObsGAN-DRL learns a generator based on the GAN model to compute the approximation of obstacles’ accurate positions in benign and attack scenarios. Therefore, no detectors are required for ObsGAN-DRL. Second, by using the approximation positions of the surrounding obstacles, ObsGAN-DRL can leverage the state-of-the-art DRL methods to compute collision-free motion commands (e.g., velocity) efficiently. Comprehensive experiments show that ObsGAN-DRL can mitigate OLAs effectively and guarantee safety. We also demonstrate the generalization of ObsGAN-DRL.

This work investigates the use of a fuzzy logic controller (FLC) for two-wheeled differential drive mobile robot trajectory tracking control. Due to the inherent complexity associated with tuning the membership functions of an FLC, this work employs a particle swarm optimization algorithm to optimize the parameters of these functions. In order to automate and reduce the number of rule bases, the genetic algorithm is also employed for this study. The effectiveness of the proposed approach is validated through MATLAB simulations involving diverse path tracking scenarios. The performance of the FLC is compared against established controllers, including minimum norm solution, closed-loop inverse kinematics, and Jacobian transpose-based controllers. The results demonstrate that the FLC offers accurate trajectory tracking with reduced root mean square error and controller effort. An experimental, hardware-based investigation is also performed for further verification of the proposed system. In addition, the simulation is conducted for various paths in the presence of noise in order to assess the proposed controller’s robustness. The proposed method is resilient against noise and disturbances, according to the simulation outcomes.

This paper presents an artificial neural network (ANN)-based nonlinear model predictive visual servoing method for mobile robots. The ANN model is developed for state predictions to mitigate the unknown dynamics and parameter uncertainty issues of the physics-based (PB) model. To enhance both the model generalization and accuracy for control, a two-stage ANN training process is proposed. In a pretraining stage, highly diversified data accommodating broad operating ranges is generated by a PB kinematics model and used to train an ANN model first. In the second stage, the test data collected from the actual system, which is limited in both the diversity and the volume, are employed to further finetune the ANN weights. Path-following experiments are conducted to compare the effects of various ANN models on nonlinear model predictive control and visual servoing performance. The results confirm that the pretraining stage is necessary for improving model generalization. Without pretraining (i.e., model trained only with the test data), the robot fails to follow the entire track. Weight finetuning with the captured data further improves the tracking accuracy by 0.07–0.15 cm on average.

Soft robotic devices are designed for applications such as exploration, manipulation, search and rescue, medical surgery, rehabilitation, and assistance. Due to their complex kinematics, various and often hard-to-define degrees of freedom, and nonlinear properties of their material, designing and operating these devices can be quite challenging. Using tools such as optimization methods can improve the efficiency of these devices and help roboticists manufacture the robots they need. In this work, we present an extensive and systematic literature search on the optimization methods used for the mechanical design of soft robots, particularly focusing on literature exploiting evolutionary computation (EC). We completed the search in the IEEE, ACM, Springer, SAGE, Elsevier, MDPI, Scholar, and Scopus databases between 2009 and 2024 using the keywords “soft robot,” “design,” and “optimization.” We categorized our findings in terms of the type of soft robot (i.e., bio-inspired, cable-driven, continuum, fluid-driven, gripper, manipulator, modular), its application (exploration, manipulation, surgery), the optimization metrics (topology, force, locomotion, kinematics, sensors, and energy), and the optimization method (categorized as EC or non-EC methods). After providing a road map of our findings in the state of the art, we offer our observations concerning the implementation of the optimization methods and their advantages. We then conclude our paper with suggestions for future research.