With the rapid advancement of mechanical automation and intelligent processing technology, accurately measuring the surfaces of complex parts has emerged as a significant research challenge. Robotic measurement technology plays a crucial role in facilitating rapid quality inspections during the manufacturing process due to its inherent flexibility. However, the irregular shapes and viewpoint occlusions of complex parts complicate precise measurement. To address these challenges, this work proposes a point cloud registration network for robotic scanning systems and introduces a DBR-Net (Dual-line Registration Network) to overcome the issues of low overlap rates and perspective occlusion that currently impede the registration of certain workpieces. First, feature extraction is performed using a bilinear encoder and multi-level feature interactions of both point-wise and global features. Subsequently, the features are sampled through unanimous voting and fed into the RANSAC (Random Sample Consensus) algorithm for pose estimation, enabling multi-view point cloud registration. Experimental results demonstrate that this method significantly outperforms many existing techniques in terms of feature extraction and registration accuracy, thereby enhancing the overall performance of point cloud registration.

The development of autonomous robots and the wide range of communication resources hold significant potential for enhancing multi-robot collaboration and its applications. Over the past decades, there has been a growing interest in autonomous navigation and multi-robot collaboration. Consequently, a comprehensive review of current trends in this field has become crucial for both novice and experienced researchers. This paper focuses on automation systems and multi-robot navigation to support their operations. The review is structured around three potential benefits: perception, planning, and collaboration. This review has systematically explored a broad spectrum of autonomous robots and multi-robot navigation strategies with over 170 references. Also, we point out the challenges of the existing work, as well as the development direction. We believe that this review can build a bridge between autonomous robots and their applications.

In natural, aquatic and amphibians creatures have evolved exceptional impulsive-based, momentum-based, and mixed water-air cross domain locomotion capabilities through long-term natural selection, providing significant reference and inspiration for the design of aquatic jumping robots. In recent years, inspired by nature and biology, researchers have turned to jumping as a potential mode of locomotion for aquatic robots, aiming to improve their adaptability across water-air environment. However, the performance of these robots remains significantly limited, far from meeting practical application requirements, due to issues like inadequate propulsion efficiency, high structural resistance, and excessive weight. This paper summarizes the key features of bioinspired aquatic jumping robots, including their bioinspired structural designs, jumping mechanisms, and actuators, while evaluating their jumping performance. Finally, the current challenges are analyzed, and future prospects for development are discussed.

Path planning is important for mobile robot to ensure safe and efficient navigation. This paper proposes a hybrid artificial bee colony with genetic augmented exploration mechanism (HABC-GA) that enables mobile robot to achieve safe and smooth path planning. Considering the characteristics of path planning problem, a mathematical model is constructed to balance three objectives: path length, path safety, and path smoothness. In the employed bee phase, a genetic augmented exploration mechanism is designed, which encompasses redesigned path crossover, adaptive obstacle-aware mutation, and dynamic elite selection operators. In the onlooker bee phase, an objective-guided optimization strategy is investigated to improve local search ability. In the scout bee phase, a dual exploration restart strategy is developed to increase the activity of individuals in the population, in which stagnant individuals in the evolution are replaced by more promising ones. Finally, the proposed HABC-GA is compared with five efficient algorithms in 24 instances of six representative environments. Simulation results demonstrate the effectiveness and high performance of HABC-GA in obtaining safe and smooth paths.

Geolocalization is a crucial process that leverages environmental information and contextual data to accurately identify a position. In particular, cross-view geolocalization utilizes images from various perspectives, such as satellite and ground-level images, which are relevant for applications like robotics navigation and autonomous navigation. In this research, we propose a methodology that integrates cross-view geolocalization estimation with a land cover semantic segmentation map. Our solution demonstrates comparable performance to state-of-the-art methods, exhibiting enhanced stability and consistency regardless of the street view location or the dataset used. Additionally, our method generates a focused discrete probability distribution that acts as a heatmap. This heatmap effectively filters out incorrect and unlikely regions, enhancing the reliability of our estimations. Code is available at https://github.com/nathanxavier/CVSegGuide.

Currently, the ultra-wideband (UWB) positioning scheme is widely applied to indoor robot positioning and has achieved high positioning accuracy. However, in some narrow and complex environments, its accuracy is still significantly degraded by the multipath effect or non-line-of-sight situations. In addition, the current single tag-based pure UWB positioning methods only estimate the tag position and ignore the rotation estimation of the robot. Therefore, in this paper, we propose a multiple tags-based UWB positioning method to estimate the position and rotation simultaneously, and further improve the position estimation accuracy. To be specific, we first install four fixed tags on the robot. Then, based on the ranging measurements, anchor positions and geometric relationships between each tag, we design five different geometric constraints and smooth constraints to build a whole optimization function. With this optimization function, both the rotations and positions at each time step can be estimated by the iterative optimization algorithm, and the results of tag positions can be improved. Both simulation and real-world experiments are conducted to evaluate the proposed method. Furthermore, we also explore the effect of relative distances between multiple tags on the rotations in the experiments. The experimental results suggest that the proposed method can effectively improve the position estimation performance, while the large relative distances between multiple tags benefit the rotation estimation.

Precise control of the contact force is crucial in the application of non-wearable defecation smart care (DSC) robot. A deformable shield equipped with a pressure sensing function is designed, with a bending angle that can be adjusted according to pressure feedback, thus enabling it to adapt to various body shapes. To improve the force tracking accuracy and prevent obvious force overshoot in the initial contact stage, a contact force control strategy based on fuzzy adaptive variable impedance is proposed. The proposed contact force control strategy achieves an average root-mean-square error of 0.024 and an average overshoot of 1.74%. Experimental results demonstrate that the designed deformable shield can fit the human body well, while the proposed control strategy enhances the contact force management and realizes the precise control of human-robot contact force.

The Fracture Reduction Robot (FRR) is a crucial component of robot-assisted fracture correction technology. However, long-term clinical experiments have identified significant challenges with the forward kinematics of the parallel FRR, notably slow computation speeds and low precision. To address these issues, this paper proposes a hybrid algorithm that integrates the Newton method with a genetic algorithm. This approach harnesses the rapid computation and high precision of the Newton method alongside the strong global convergence capabilities of the genetic algorithm. To comprehensively evaluate the performance of the proposed algorithm, comparisons are made against the analytical method and the Additional Sensor Algorithm (ASA) using identical computational examples. Additionally, iterative comparisons of iteration counts and precision are conducted between traditional numerical methods and the Newton-Genetic algorithm. Experimental results show that the Newton-Genetic algorithm achieves a balance between computation speed and precision, with an accuracy reaching the 10−4mm order of magnitude, effectively meeting the clinical requirements for fracture reduction robots in medical correction.

Biomimetic grasping is crucial for robots to interact with the environment and perform complex tasks, making it a key focus in robotics and embodied intelligence. However, achieving human-level finger coordination and force control remains challenging due to the need for multimodal perception, including visual, kinesthetic, and tactile feedback. Although some recent approaches have demonstrated remarkable performance in grasping diverse objects, they often rely on expensive tactile sensors or are restricted to rigid objects. To address these challenges, we introduce SoftGrasp, a novel multimodal imitation learning approach for adaptive, multi-stage grasping of objects with varying sizes, shapes, and hardness. First, we develop an immersive demonstration platform with force feedback to collect rich, human-like grasping datasets. Inspired by human proprioceptive manipulation, this platform gathers multimodal signals, including visual images, robot finger joint angles, and joint torques, during demonstrations. Next, we utilize a multi-head attention mechanism to align and integrate multimodal features, dynamically allocating attention to ensure comprehensive learning. On this basis, we design a behavior cloning method based on an angle-torque loss function, enabling multimodal imitation learning. Finally, we validate SoftGrasp in extensive experiments across various scenarios, demonstrating its ability to adaptively adjust joint forces and finger angles based on real-time inputs. These capabilities result in a 98% success rate in real-world experiments, achieving dexterous and stable grasping. Source code and demonstration videos are available at https://github.com/nubot-nudt/SoftGrasp.

The issue of aging population has become a severe problem that restricts global development. Thus, the development of bathing robots for the elderly is of great significance for the national strategy of actively addressing population aging. However, there is a lack of systematic review and analysis for the elderly bathing aids and robots, and the trend of the future development is also unclear. Therefore, by reviewing the relevant literature, this paper systematically analyzes the technical characteristics and usage scenarios of the lying, sitting and auxiliary posture, based on the bathing methods, bathing modes, and post bath care, which can clarify the current research status of bathing aids and robots for the elderly. Meanwhile, from the perspectives of the structural design, motion control and information intelligence, the key technologies and existing problems of bathing aids and robots are elaborated, and the relevant technical system is sorted out. Finally, based on the future of technological elderly care and the elderly bathing needs, the development trend of elderly bathing aids and robots is prospected, and the reference and suggestions for its research and development is provided, which has positive research significance.

In order to ensure the safety and efficiency of planetary exploration rovers, path planning and tracking control of a planetary rover are expected to consider factors such as complex 3D terrain features, the motion constraints of the rover, traversability, etc. An improved path planning and tracking control method is proposed for planetary exploration rovers on rough terrain in this paper. Firstly, the kinematic model of the planetary rover is established. A 3D motion primitives library adapted to various terrains and the rover’s orientations is generated. The state expansion process and heuristic function of the A* algorithm are improved using the motion primitives and terrain features. Global path is generated by improved A*-based algorithm that satisfies the planetary rover’s kinematic constraints and the 3D terrain restrictions. Subsequently, an optional arc path set is designed based on the traversable capabilities of the planetary rover. Each arc path corresponds to a specific motion that determines the linear and angular velocities of the planetary rover. The optimal path is selected through the multi-objective evaluation function. The planetary rover is driven to accurately track the global path by sending optimal commands that corresponds to the optimal path for real-time obstacle avoidance. Finally, the path planning and tracking control method is effectively validated during a given mission through two simulation tests. The experiment results show that the improved A*-based algorithm reduces planning time by 30.05% and generates smoother paths than the classic A* algorithm. The multi-objective arc-based method improves the rover’s motion efficiency, ensuring safer and quicker mission completion along the global path.