Journal of Intelligent & Robotic Systems最新文献

Construction robots employ cutting-edge technology to perform tasks more accurately than traditional construction workers, producing higher-quality results and fewer mistakes. Moreover, although construction robotics is a demanding topic in construction sector research, more review studies that track and anticipate adoption trends are required in the construction sector. This study aims to bridge this gap by identifying the adoption challenges and limitations of construction robots and the opportunities offered to the construction sector. To achieve this aim, the study adopts a systematic literature review approach using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol. Additionally, the systematic literature review focuses on the framework for categorizing technological advances and potential trends in development over the past decade. The review results reveal that: (a) current robotic technology covered four critical perspectives including perception, mobility, manipulation, and collaboration; (b) promoting the sector requires attention to safety and ethical issues because of the risks associated.

Supernumerary robotic limbs (SRLs) have great potentials to assist human in daily activities and industrial manufacturing by providing extra limbs. However, current SRLs have heavy and rigid structures that may threaten the operator safety; moreover, their limited degrees of freedom and movement modes are not suitable for complicated tasks. Although soft SRLs have exhibited advantages in structure compliance and flexible manipulation to address these problems, it remains challenging to accurately design the geometrical parameters to adapt to specific tasks, and accurate control is also required to realize the expected movement. Inspired by the biological characteristics of the octopus arm muscle fibers, fiber-reinforced actuators (FRAs) are employed to realize various motions, including extension, expansion, bending, and twisting; multiple FRAs are assembled to implement the SRL to achieve complex movement trajectories. The analytic model of the FRA is established to reveal the relationship between its deformation and geometrical parameters as well as input air pressures, which is validated with finite element simulation. Trajectory and payload optimization algorithms are proposed to optimally design the SRL and its control strategy with meeting the prescribed requirement of movement trajectory and payload capacity. Finally, experiments are conducted to validate the proposed robotic system.

This paper presents a new strategy for simultaneous control of multiple magnetic Micro Robots (MRs) improving stability and robustness with respect to external disturbances. Independent control of multiple MRs, can enhance efficiency and allows for performing more challenging applications. In this study, we present a system consisting of a Helmholtz coil and 2N Permanent Magnets (PMs), rotated by servomotors, to control several MRs. We have also improved the system’s stability by adding a larger MR (stabilizer MR). This MR can be moved all around the workspace and works as a moving internal magnetic field source. Thanks to this moveable magnetic field, other MRs are more stable against environmental disturbances. By simulating simultaneous and independent control of multiple MRs, we demonstrate the advantages of using the stabilizer MR (more than 20 percent reduction in tracking error and control effort). In addition, we evaluate experimentally our proposed method to independently control the position of three MRs using a stabilizer MR demonstrating the efficacy of the strategy.

Bioinspired underwater robots can move efficiently, with agility, even in complex aquatic areas, reducing marine ecosystem disturbance during exploration and inspection. These robots can improve animal farming conditions and preserve wildlife. This study proposes a muscle-like control for an underactuated robot in carangiform swimming mode. The artifact exploits a single DC motor with a non-blocking transmission system to convert the motor’s oscillatory motion into the fishtail’s oscillation. The transmission system combines a magnetic coupling and a wire-driven mechanism. The control strategy was inspired by central pattern generators (CPGs) to control the torque exerted on the fishtail. It integrates proprioceptive sensory feedback to investigate the adaptability to different contexts. A parametrized control law relates the reference target to the fishtail’s angular position. Several tests were carried out to validate the control strategy. The proprioceptive feedback revealed that the controller can adapt to different environments and tail structure changes. The control law parameters variation accesses the robotic fish’s multi-modal swimming. Our solution can vary the swimming speed of 0.08 body lengths per second (BL/s), and change the steering direction and performance by an angular speed and turning curvature radius of 0.08 rad/s and 0.25 m, respectively. Performance can be improved with design changes, while still maintaining the developed control strategy. This approach ensures the robot’s maneuverability despite its underactuated structure. Energy consumption was evaluated under the robotic platform’s control and design. Our bioinspired control system offers an effective, reliable, and sustainable solution for exploring and monitoring aquatic environments, while minimizing human risks and preserving the ecosystem. Additionally, it creates new and innovative opportunities for interacting with marine species. Our findings demonstrate the potential of bioinspired technologies to advance the field of marine science and conservation.

The paper presents a security control scheme for unmanned aerial vehicles (UAVs) against desired trajectory attacks. The key components of the proposed scheme are the attack detector, attack estimator, and integral sliding mode security controller (ISMSC). We focus on malicious tampering of the desired trajectory sent by the ground control station (GCS) to the UAV by attackers. Firstly, we model attacks by analyzing the characteristics of desired trajectory attacks. Secondly, an integrated attack detection scheme based on an unknown input observer (UIO) and an interval observer is presented. Subsequently, a robust adaptive observer (RAO) is employed to compensate for the impact of attacks on the control system. Thirdly, an ISMSC with an attack compensation mechanism is established. Finally, simulation results are provided to verify the effectiveness of the proposed scheme. The proposed detection scheme can not only detect desired trajectory attacks but also distinguish them from abrupt unknown disturbances (AUDs). By utilizing ISMSC method, UAVs under desired trajectory attacks can fly safely. The proposed comprehensive framework of detection, estimation and compensation provides a theoretical basis for ensuring cyber security in UAVs.

The LiDAR Odometry and Mapping (LOAM) algorithm ranks in second place in the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI), Visual Odometry/SLAM Evaluations. It utilizes a feature extraction algorithm based on the evaluation of the curvature of points under test, to produce estimated smooth and non-smooth regions within typically laser based Point Cloud Data (PCD). This feature extractor (FE) however, does not take into account PCD spatial or detection uncertainty, which can result in the divergence of the LOAM algorithm. Therefore, this article proposes the use of the Curvature Scale Space (CSS) algorithm as a replacement for LOAM’s current feature extractor. It justifies the substitution, based on the CSS algorithm’s similar computational complexity but improved feature detection repeatability. LOAM’s current feature extractor and the proposed CSS feature extractor are tested and compared with simulated and real data, including the KITTI odometry-laser data set. Additionally, a recent deep learning based LiDAR Odometry (LO) algorithm, the Convolutional Auto-Encoder (CAE)-LO algorithm, will also be compared, using this data set, in terms of its computational speed and performance. Performance comparisons are made based on the Absolute Trajectory Error (ATE) and Cardinalized Optimal Linear Assignment (COLA) metrics. Based on these metrics, the comparisons show significant improvements of the LOAM algorithm with the CSS feature extractor compared with the benchmark versions.

The lack of aerial physical interaction capability is one of the choke points limiting the extension of aerial robot applications, such as rescue missions and aerial maintenance. We present a new aerial robotic manipulator (AEROM) for aerial dexterous operations in this work. It contains a robotic manipulator with 6-degree-of-freedom and a compact flight platform. Firstly, we propose a quantitative capability index to evaluate and guide the mechanical design of the AEROM. Based on the proposed quantitative index, we construct a lightweight bird-inspired manipulator to imitate a raptor hindlimb. An additional telescopic joint and an end-effector consisting of three soft fingers allow the AEROM to execute aerial interaction tasks. In addition, the wrist joints enable independent control of the end-effector attitude regardless of the flight platform. After explicitly analyzing the multi-source disturbances during the aerial operation tasks, we develop a refined anti-disturbance controller to compensate for the disturbances with different characteristics. The proposed controller further improves the position accuracy of end-effector to enable dexterous operations during aerial interaction tasks. Finally, the physical experiments verify the effectiveness of the proposed AEROM system.

This study addresses the problem of cooperative control design for a group of car-like vehicles encountering fading channels, actuator faults, and external disturbances. It is presumed that certain followers lack direct access to the states of the leader via a directed graph. This arises challenges in maintaining synchronization and coordination within the network. The proposed control strategy utilizes non-singular fast terminal sliding mode control to accelerate consensus tracking and enhance the convergence of the overall system. This controller is designed to mitigate the impact of actuator faults in the presence of fading channels in the communication network. The effects of such issues on team performance are rigorously analyzed. Based on the Lyapunov stability principle, it has been demonstrated that the controller is capable of providing satisfactory performance for the entire system despite these challenges. Moreover, vehicle synchronization can be effectively maintained. Numerical simulations are conducted to verify the theoretical findings.

To aid humans in everyday tasks, robots need to know which objects exist in the scene, where they are, and how to grasp and manipulate them in different situations. Therefore, object recognition and grasping are two key functionalities for autonomous robots. Most state-of-the-art approaches treat object recognition and grasping as two separate problems, even though both use visual input. Furthermore, the knowledge of the robot is fixed after the training phase. In such cases, if the robot encounters new object categories, it must be retrained to incorporate new information without catastrophic forgetting. To resolve this problem, we propose a deep learning architecture with an augmented memory capacity to handle open-ended object recognition and grasping simultaneously. In particular, our approach takes multi-views of an object as input and jointly estimates pixel-wise grasp configuration as well as a deep scale- and rotation-invariant representation as output. The obtained representation is then used for open-ended object recognition through a meta-active learning technique. We demonstrate the ability of our approach to grasp never-seen-before objects and to rapidly learn new object categories using very few examples on-site in both simulation and real-world settings. Our approach empowers a robot to acquire knowledge about new object categories using, on average, less than five instances per category and achieve (95%) object recognition accuracy and above (91%) grasp success rate on (highly) cluttered scenarios in both simulation and real-robot experiments. A video of these experiments is available online at: https://youtu.be/n9SMpuEkOgk

This paper presents a new fuzzy interacting multiple-model velocity obstacle (FIMVO) approach for collision avoidance of unmanned aerial vehicles (UAVs). The proposed approach adopts in one framework the advantages of geometric collision avoidance approaches, namely of the velocity (VO), reciprocal velocity (RVO), and hybrid reciprocal velocity obstacle (HRVO) avoidance approaches combined with fuzzy logic. This leads to a combined decision-making rule, with real-time efficiency. The developed approach is compared with geometric conventional velocity obstacle avoidance approaches: VO, RVO, and HRVO avoidance approaches. The proposed approach is carefully evaluated and validated in a simulation environment and over real UAVs. The case study includes three mini UAVs and a human teleoperator who can control only one of them. The other UAVs used the computer-based teleoperator with the proposed and compared approaches. The performance criteria have been defined in four parts: trajectory smoothness, task performance, algorithm simplicity, and reliability. In 1000 independently repeated simulations, the performance results showed that the proposed FIMVO approach was 10 times better than the VO approach in terms of the number of avoided collisions. The statistical analysis demonstrates that the proposed FIMVO approach outperforms geometric velocity obstacle avoidance approaches concerning reliability and real-time efficiency.