{"title":"Ellipsoid uncertainty tether model for collision avoidance in a fleet of Remotely Operated Vehicles","authors":"Christophe Viel","doi":"10.1016/j.robot.2025.105213","DOIUrl":"10.1016/j.robot.2025.105213","url":null,"abstract":"<div><div>During collision avoidance, the tether of Remote Operated Vehicle (ROV) is subject to entanglement with obstacles or other ROVs’ tether. This specificity renders traditional multi-robot obstacle avoidance approaches inadequate for tethered multi-robot scenarios. This paper proposes a guaranteed ellipsoid model for representing the ROV’s tether and its nearby obstacles, enabling an efficient, low-computation collision avoidance method for a fleet of ROVs. The model ensures that if the ellipsoid encompassing the tether remains entirely outside the ellipsoid encompassing an obstacle, there is no risk that the tether collides with it. The approach requires only the two attachment points of the tether and its length, without needing any information about the tether’s shape, dynamics, or external disturbances such as underwater currents. A collision avoidance strategy is developed based on potential field methods combined with tether length management. When multiple ROVs are involved, personalities are added to ROV to obtain different behaviors, reducing the likelihood of deadlocks during avoidance maneuvers. Simulations demonstrate the method’s effectiveness across various scenarios, and its limitations are also discussed.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105213"},"PeriodicalIF":5.2,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Virginia Burini, Silvia Logozzo, Maria Cristina Valigi
{"title":"A new SMART gripper with soft fingers and integrated force sensors for adaptive robotic tasks","authors":"Virginia Burini, Silvia Logozzo, Maria Cristina Valigi","doi":"10.1016/j.robot.2025.105218","DOIUrl":"10.1016/j.robot.2025.105218","url":null,"abstract":"<div><div>In the last decades, robotic manipulation has been treated as a cornerstone research topic to improve, accelerate but also safeguard human work in industrial, medical and everyday activities. For this reason, robotic hands are increasingly devoted to mimicking or augmenting human abilities. In particular, the two main operations performed by a human hand are precision and power grasping with the possibility of dosing the right grasping force to avoid breaks, deformations, or drops of the grasped objects. This paper presents the design, characterization and testing of a novel underactuated tendon-driven soft robotic gripper with sensing fingertips to regulate the applied contact force mimicking the ability of the human hand. The evolution of the design phases is presented and discussed together with the characterization procedures. Results of the grasping tests show the successful application of the new gripper in different tasks.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105218"},"PeriodicalIF":5.2,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Formation control of multiple AUVs using decentralized self-attention based soft actor–critic model","authors":"Meiyan Zhang , Ziqiang Liu , Wenyu Cai","doi":"10.1016/j.robot.2025.105187","DOIUrl":"10.1016/j.robot.2025.105187","url":null,"abstract":"<div><div>One of most important topics studied in the field of multiple robots is cooperative formation control. Formation structure is a combination in which agents maintain the desired form and at the same time execute the assigned commands. This article deals with the formation control of multiple Autonomous Underwater Vehicles (AUVs) based on a distributed reinforcement learning algorithm. The proposed Decentralized Self-Attention based Soft Actor–Critic (DEC-ASAC in short) method uses an attention mechanism and maximum entropy reinforcement learning control, so as to enable AUVs to learn formation control independently. The corresponding environmental states, action space and reward schemes are designed for leader and follower AUVs. Simulations and lake test verify that the proposed DEC-ASAC algorithm can stably and effectively learn control policies during training process, achieving effective control of multiple AUVs to keep different formation shapes.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105187"},"PeriodicalIF":5.2,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FG-PE: Factor-graph approach for multi-robot pursuit–evasion","authors":"Messiah Abolfazli Esfahani , Ayşe Başar , Sajad Saeedi","doi":"10.1016/j.robot.2025.105216","DOIUrl":"10.1016/j.robot.2025.105216","url":null,"abstract":"<div><div>With the increasing use of robots in daily life, there is a growing need to provide robust collaboration protocols for robots to tackle more complicated and dynamic problems effectively. This paper presents a novel, factor graph-based approach to address the pursuit–evasion problem, enabling accurate estimation, planning, and tracking of an evader by multiple pursuers working together. It is assumed that there are multiple pursuers and only one evader in this scenario. The proposed method significantly improves the accuracy of evader estimation and tracking, allowing pursuers to capture the evader in the shortest possible time and distance compared to existing techniques. In addition to these primary objectives, the proposed approach effectively minimizes uncertainty while remaining robust, even when communication issues lead to some messages being dropped or lost. Through a series of comprehensive experiments, this paper demonstrates that the proposed algorithm consistently outperforms traditional pursuit–evasion methods across several key performance metrics, such as the time required to capture the evader and the average distance traveled by the pursuers. Additionally, the proposed method is tested in real-world hardware experiments, further validating its effectiveness and applicability.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105216"},"PeriodicalIF":5.2,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Context-aware proactive and adaptive conversation for human–robot interaction","authors":"Zhidong Su, Weihua Sheng","doi":"10.1016/j.robot.2025.105207","DOIUrl":"10.1016/j.robot.2025.105207","url":null,"abstract":"<div><div>Social robots are coming into our daily life. Existing conversational robots are mostly reactive in that the interactions are usually initiated by the users. With the knowledge of the environmental context such as people’s daily activities, robots can be more intelligent and proactive. In this paper, we proposed a context-aware conversation adaptation system (CACAS) for human–robot interaction (HRI). First, a context recognition module and a language processing module are developed to obtain the context information, user intent and slots, which become part of the system state. Second, a reinforcement learning algorithm is utilized to train an initial policy in a simulated HRI environment. User feedback data is collected through HRI using the initial policy. Third, a new policy that combines the reinforcement learning-based policy and a supervised learning-based policy is adapted based on the user feedback. We conducted both simulated user tests and real human subject tests to evaluate the proposed CACAS. The results show that the CACAS achieved a success rate of 85% in the real human subject test and 87.5% of participants were satisfied with the adaptation results. For the simulation test, the CACAS had the highest success rate compared with the baseline methods.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105207"},"PeriodicalIF":5.2,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MATdiff: Learning diffusion policy with multi-auxiliary task for mobile robot visual exploration","authors":"Qifei Tang , Zengmao Wang , Wei Gao","doi":"10.1016/j.robot.2025.105199","DOIUrl":"10.1016/j.robot.2025.105199","url":null,"abstract":"<div><div>The application of diffusion models into the field of robotics is gaining increasing attention due to its advantages in modeling complex data distributions. In the visual navigation task of mobile robots based on diffusion policy, existing frameworks use the current observation as the guidance condition and adopt a classifier free guidance mode for joint training. However, using diffusion models for end-to-end training may result in feature loss, as the learned features are not well understood, which leading to poor generalization in unknown environments and low navigation success rates. To address the issue of generalization, we proposed a new visual navigation framework called MATdiff from the perspective of visual representation. Our framework utilizes two auxiliary tasks to enhance the representation capability of the Conditioned Observation Network. It leverages depth estimation to extract the geometric features of the environment and employs free-space segmentation to identify safely drivable regions, which are defined as areas free from obstacles and suitable for safe navigation. After the fusion of those features, we use a conditional diffusion model to model the distribution under observation conditions and generate a fixed number of consecutive waypoints. This design of auxiliary tasks ensures that the conditional features pays attention to both geometric and semantic information simultaneously. We conduct experiments in both simulation environments and the real world. Compared with the state-of-the-art methods, our method not only has lighter model parameters but also achieves the highest navigation success rate and a longer average travel distance before collision.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105199"},"PeriodicalIF":5.2,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dynamic model and performance assessment of the natural motion of a SCARA-like manipulator in pick-and-place tasks","authors":"Luca Bruzzone, Matteo Verotti, Pietro Fanghella","doi":"10.1016/j.robot.2025.105215","DOIUrl":"10.1016/j.robot.2025.105215","url":null,"abstract":"<div><div>The energy efficiency of manipulators performing cyclic motions can be enhanced by utilizing the so-called natural motion, namely, the natural oscillations that occur when elastic elements are placed in series or parallel with the actuators. In this paper, the natural motion of the RR-4R-R robot is discussed. This manipulator exhibits a 4-DOF mobility similar to that of the widespread SCARA robot, but the vertical prismatic joint is replaced by a four-bar mechanism. This modification, along with the adoption of a direct-drive actuator for the four-bar mechanism, makes it easier to achieve the elastic balancing of the robot, allowing the exploitation of its natural motion. The robot dynamics is analysed using the Lagrangian approach. Two types of elastic balancing are considered: one using a torsional spring and one using a linear coil spring. A simplified model of the vertical motion is then proposed, decoupled from the inertial effects of the horizontal motion, and used to estimate the vertical natural period. The behaviour of the manipulator with natural elastic balancing is compared with that obtained with exact elastic balancing, which provides an indifferent equilibrium in any robot position. This comparison is first carried out in the time domain, and then the space of the robot operating conditions is sampled through multibody simulations, performed to investigate the threshold of convenience between exact and natural balancing. Simulation results indicate that exploiting the natural motion of the RR-4R-R manipulator can significantly reduce energy consumption in a wide range of industrial applications involving pick-and-place tasks.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105215"},"PeriodicalIF":5.2,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Online learning for agile underwater maneuvering: Gaussian processes and sparse regression for data-driven model predictive control","authors":"Sriharsha Bhat , Giancarlo Troni , Ivan Stenius","doi":"10.1016/j.robot.2025.105211","DOIUrl":"10.1016/j.robot.2025.105211","url":null,"abstract":"<div><div>Autonomous underwater vehicles (AUVs) show much promise in environmental sensing, aquaculture, and security applications. Robust and adaptive control strategies can immensely benefit these scenarios by increasing autonomy and endurance. However, AUVs are nonlinear systems whose dynamics are challenging to model, especially during agile maneuvers at high angles of attack. To better capture these nonlinear effects, this paper proposes a physics-informed system identification scheme that combines prior knowledge of the system dynamics with data-driven regression. Strategies including Sparse Identification of Nonlinear Dynamics (SINDy), nonlinear least squares regression, and Gaussian processes (GPs) are used to learn the AUV dynamics online from measured data. These data-driven models are then implemented in an adaptive model predictive controller (MPC) for agile maneuvering that drives the system to a set point while updating the prediction model when new measurements are available. The performance of these three system identification strategies is evaluated on two different 6-DOF AUV platforms. All three strategies show good real-time performance, while the GP model offers the best balance between accuracy, speed and robustness. Field experimental data from the SAM AUV and the MOLA AUV are used for performance evaluation.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105211"},"PeriodicalIF":5.2,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Amin Tadayyoni , Behnam Miripour Fard , Ali Jamali
{"title":"Robust walking motion generation for biped robots using manipulability-based reinforcement learning","authors":"Amin Tadayyoni , Behnam Miripour Fard , Ali Jamali","doi":"10.1016/j.robot.2025.105209","DOIUrl":"10.1016/j.robot.2025.105209","url":null,"abstract":"<div><div>In reinforcement learning, designing an effective reward function is essential for developing and controlling humanoid robots. The criteria for replicating human learning and achieving human-like responses in bipedal robots remain unclear. Integrating kinematic and dynamic characteristics into the reward function, along with the use of detailed models, can enhance efficiency and robustness. This study proposes a novel manipulability-based reward function within an end-to-end learning framework, enabling the agent to autonomously generate robust, real-time movements. Incorporating the kinematic manipulability index into the proposed reward function significantly improves the robot's locomotion behavior and ability to handle disturbances. Results indicate that incorporating kinematic manipulability into training enhances the robot's forward speed and improves its ability to handle sagittal and lateral disturbances, as well as uncertainties in length and weight distribution. Furthermore, compared to a classical hierarchical controller, the trained agent attained higher speeds and demonstrated superior disturbance handling, validating the effectiveness of the proposed learning-based approach. These findings highlight the significance of incorporating kinematic manipulability into the reward function to enhance the agility and adaptability of bipedal robots.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105209"},"PeriodicalIF":5.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pengfei Yang , Luyu Gao , Ruixing Huang , Yuyang Xiong , Yuqing Mao , Feng Huang , Fei Dang
{"title":"Rolling mechanism and performance of a soft robot driven by local curvature loading","authors":"Pengfei Yang , Luyu Gao , Ruixing Huang , Yuyang Xiong , Yuqing Mao , Feng Huang , Fei Dang","doi":"10.1016/j.robot.2025.105212","DOIUrl":"10.1016/j.robot.2025.105212","url":null,"abstract":"<div><div>Previous rolling soft robots are usually hard to achieve balanced rolling performance (terrain adaptability, rolling velocity and energy efficiency). This paper proposes a rolling soft robot driven by local curvature loading, which demonstrates good rolling velocity, small deformation rate, good energy efficiency and excellent terrain adaptability. A theory based on the energy method is established to analyze the rolling mechanism of the soft robot and to determine the critical loading curvature, which is validated by experiments. The local curvature loading causes the deformation of the entire robot configuration and results in the shift of the gravity center, which generates a gravity torque to drive the rolling of the soft robot when the critical loading curvature is reached. The proposed soft robot has good average rolling velocity (182.9 mm/s or 0.938 body length per second, BL/s) and can adapt to a variety of complex terrains such as the stairs (stair height 15 mm), the slope (slope angle 12.4 °) and the wide broken bridge (gap length 100 mm or 0.526 BL). The study in this work demonstrates broad application prospect in the fields of biomedical therapy, exploration, searching and rescuing, which provides a new idea for the structural design and performance improvement of rolling soft robots.</div></div>","PeriodicalId":49592,"journal":{"name":"Robotics and Autonomous Systems","volume":"195 ","pages":"Article 105212"},"PeriodicalIF":5.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145270197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}