In recent years, unmanned aerial vehicles (UAVs) have been applied in underground mine inspection and other similar works depending on their versatility and mobility. However, accurate localization of UAVs in perceptually degraded mines is full of challenges due to the harsh light conditions and similar roadway structures. Due to the unique characteristics of the underground mines, this paper proposes a semantic knowledge database-based localization method for UAVs. By minimizing the spatial point-to-edge distance and point-to-plane distance, the relative pose constraint factor between keyframes is designed for UAV continuous pose estimation. To reduce the accumulated localization errors during the long-distance flight in a perceptual-degraded mine, a semantic knowledge database is established by segmenting the intersection point cloud from the prior map of the mine. The topological feature of the current keyframe is detected in real time during the UAV flight. The intersection position constraint factor is constructed by comparing the similarity between the topological feature of the current keyframe and the intersections in the semantic knowledge database. Combining the relative pose constraint factor of LiDAR keyframes and the intersection position constraint factor, the optimization model of the UAV pose factor graph is established to estimate UAV flight pose and eliminate the cumulative error. Two UAV localization experiments conducted on the simulated large-scale Edgar Mine and a mine-like indoor corridor indicate that the proposed UAV localization method can realize accurate localization during long-distance flight in degraded mines.

This article presents a detailed examination of circular target localization techniques for measuring robot pose and performing online pose correction. The investigated target localization methods include centroiding, ellipse fitting with point data and gradient information, and ellipse fitting methods with augmented and corrected input data. The performance of each method is evaluated in terms of accuracy and precision of measurements through experimental comparison with a laser tracker. This study provides technical and practical insights for selecting an appropriate target localization method in robotic applications. It also introduces a vision-based solution for robot relative error correction, comprising the calibration procedure and a closed-loop control with a proportional–integral-derivative controller for pose correction. Results show enhanced accuracy in robot positioning relative to workpiece, highlighting the effectiveness of the proposed solution in robotic drilling applications.

In mobile robot localization with multiple sensors, myriad problems arise as a result of inadequacies associated with each of the individual sensors. In such cases, methodologies built upon the concept of multisensor fusion are well-known to provide optimal solutions and overcome issues such as sensor nonlinearities and uncertainties. Artificial neural networks and fuzzy logic (FL) approaches can effectively model sensors with unknown nonlinearities and uncertainties. In this article, a robust approach for localization (positioning) of a mobile robot in indoor as well as outdoor environments is proposed. The neural network is utilized as a pseudo-sensor that models the global positioning system (GPS) and is used to predict the robot’s position in case of GPS signal loss in indoor environments. The data from proprioceptive sensors such as inertial sensors and GPS are fused using the Kalman and the complementary filter-based fusion schemes in the outdoor case. To eliminate the position inaccuracies due to wheel slippage, an expert FL system (FLS) is implemented and cascaded with the sensor fusion module. The proposed technique is tested both in simulation and in real scenarios of robot movements. The simulations and results from the experimental platform validate the efficacy of the proposed algorithm.

Determining an appropriate grasp configuration for multi-finger grasping is difficult due to the complexity of robotic hands. The multi-finger grasp planning should consider not only geometry constraints of objects but also kinematics and dynamics of robotic hand. In this paper, a precision grasp-planning framework is presented for multi-finger hand to grasp unknown objects. First, the manipulation capabilities of the robotic hand are analyzed. The analysis results are further used as bases for the precision grasp planning. Second, the superquadric (SQ) fitting method is used for approximating unknown object models. Finally, a local–global optimization method is implemented to find appropriate grasp configurations for dexterous hand. The presented planning framework is validated in simulation experiments. Simulation results demonstrated that the presented grasp-planning framework enables the multi-finger hand to grasp unknown objects effectively.

In this paper, we present a novel stochastic framework for network-based bilateral teleoperation systems. A Bayesian approach, which provides robust tracking performance in real-world applications, is proposed to estimate and predict the stochastic variables and compensate for the unreliable network conditions. Combining with a practical approach in transport and application layers of the Internet, this paper demonstrates a high performance and efficient prediction and estimation method for bilateral teleoperation system. Experimental results show that the proposed Bayesian approach estimates and predicts true position and force data over unreliable network conditions, and therefore, improves the performance of overall teleoperation systems.

It has become a common practice to use simulation to generate large databases of good grasps for grasp planning in robotics research. However, the existence of a generic simulation context that enables the generation of high quality grasps that can be used in several different contexts such as bin-picking or picking objects from a table, has to our knowledge not yet been discussed in the literature.

In this paper, we investigate how well the quality of grasps simulated in a commonly used “generic” context transfers to a specific context, both, in simulation and in the real world.

We generate a large database of grasp hypotheses for several objects and grippers, which we then evaluate in different dynamic simulation contexts e.g., free floating (no gravity, no obstacles), standing on a table and lying on a table.

We present a comparison on the intersection of the grasp outcome space across the different contexts and quantitatively show that to generate reliable grasp databases, it is important to use context specific simulation.

We furthermore evaluate how well a state of the art grasp database transfers from two simulated contexts to a real world context of picking an object from a table and discuss how to evaluate transferability into non-deterministic real world contexts.

A widely used method for pose estimation in mobile robots is odometry. Odometry allows the robot in real time to reconstruct its position and orientation from the wheels' encoder measurements. Given to its unbounded nature, odometry calculation accumulates errors with quadratic increase of error variance with traversed distance. This paper develops a novel method for odometry calibration and error propagation identification for mobile robots. The proposed method uses a laser-based interferometer to measure distance precisely. Two variants of the proposed calibration method are examined: the two-parameter model and the three-parameter model. Experimental results obtained using a Khepera 3 mobile robot showed that both methods significantly increase accuracy of the pose estimation, validating the effectiveness of the proposed calibration method.

This paper presents a new approach to matching occupancy grid maps by means of finding correspondences between a set of sparse features detected in the maps. The problem is stated here as a special instance of generic image registration. To cope with the uncertainty and ambiguity that arise from matching grid maps, we introduce a modified RANSAC algorithm which searches for a dynamic number of internally consistent subsets of feature pairings from which to compute hypotheses about the translation and rotation between the maps. By providing a (possibly multi-modal) probability distribution of the relative pose of the maps, our method can be seamlessly integrated into large-scale mapping frameworks for mobile robots. This paper provides a benchmarking of different detectors and descriptors, along extensive experimental results that illustrate the robustness of the algorithm with a 97% success ratio in loop-closure detection for ~1700 matchings between local maps obtained from four publicly available datasets.

Reliability of a satellite attitude control system depends on accurate detection of failures in its sensors. This paper presents an observer for robust detection and isolation of a class of failures in satellite attitude sensors. The proposed observer uses measurement of a three-axis gyro together with only one attitude sensor, and generates a residual signal which is sensitive to faults and is simultaneously robust against disturbance and noise. A nonlinear model of satellite kinematics is considered for design of the observer. The structure of the observer is in the form of a delayed continuous-time differential equation ensuring its robustness properties. A realistic simulation is provided to illustrate the performance of the proposed observer in the face of the faults occurring in a magnetometer, as the attitude sensor, and also the faults occurring in the gyro.

Vision sensors are increasingly being used in the implementation of Simultaneous Localization and Mapping (SLAM). Even though the mathematical framework of SLAM is well understood, considerable issues remain to be resolved when a particular sensing modality is considered. For instance, the observation model of a small baseline stereo camera is known to be highly nonlinear. As a consequence, state estimations obtained from standard recursive estimators, such as the Extended Kalman Filter, tend to be inconsistent. Further, vision-based approaches are plagued with high feature densities, and the consequent requisite of maintaining large feature databases for loop closure and data association. This paper proposes a two-tier solution for resolving these issues, inspired by the mechanics of human navigation. The proposed two-tier solution addresses the consistency issue by formulating the SLAM problem as a nonlinear batch optimization and presents a novel method for feature management through a two-tier map representation. Simulations and experiments are carried out in an office-like environment to validate the performance of the algorithm.

This paper investigates 3-dimensional (3D) Simultaneous Localization and Mapping (SLAM) and the corresponding observability analysis by fusing data from landmark sensors and a strap-down Inertial Measurement Unit (IMU) in an adaptive Kalman filter (KF). In addition to the vehicle's states and landmark positions, the self-tuning filter estimates the IMU calibration parameters as well as the covariance of the measurement noise. The discrete-time covariance matrix of the process noise, the state transition matrix and the observation sensitivity matrix are derived in closed form, making it suitable for real-time implementation. Examination of the observability of the 3D SLAM system leads to the the conclusion that the system remains observable, provided that at least three known landmarks, which are not placed in a straight line, are observed.

Inverse kinematics (IK) is a nonlinear problem that may have multiple solutions. A modified genetic algorithm (GA) for solving the IK of a serial robotic manipulator is presented. The algorithm is capable of finding multiple solutions of the IK through niching methods. Despite the fact that the number and position of solutions in the search space depends on the position and orientation of the end-effector as well as the kinematic configuration (KC) of the robot, the number of GA parameters that must be set by a user are limited to a minimum through the use of an adaptive niching method. The only requirement of the algorithm is the forward kinematics (FK) equations which can be easily obtained from the Denavit–Hartenberg link parameters and joint variables of the robot. For identifying and processing the outputs of the proposed GA, a modified filtering and clustering phase is also added to the algorithm. For the postprocessing stage, a numerical IK solver is used to achieve convergence to the desired accuracy. The algorithm is validated on three KCs of a modular and reconfigurable robot (MRR).

When computer vision technique is used in robotics, robotic hand–eye calibration is a very important research task. Many algorithms have been proposed for hand–eye calibration. Based on these algorithms, we introduce a new hand–eye calibration algorithm in this paper, which employs the screw motion theory to establish a hand–eye matrix equation by using quaternion and gets a simultaneous result for rotation and translation by solving linear equations. The algorithm proposed in this paper has high accuracy and stable computational efficiency and can be understood easily. Both simulations and real experiments show the superiority of our algorithm over the comparative algorithms.

Large disturbances can cause a biped to fall. If an upcoming fall can be detected, damage can be minimized or the fall can be prevented. We introduce the multi-way principal component analysis (MPCA) method for the detection of upcoming falls. We study the detection capability of the MPCA method in a simulation study with the simplest walking model. The results of this study show that the MPCA method is able to predict a fall up to four steps in advance in the case of single disturbances. In the case of random disturbances the MPCA method has a successful detection probability of up to 90%.

In this paper, the robust robot localization problem with respect to uncertainties on environment features is formulated in a stochastic setting, and an extended Kalman filtering approach is proposed for the integration of odometric, video camera, and sonar measures. The environment is supposed to be only partially known, and a probabilistic method for sensor data fusion aimed at increasing the environment knowledge is considered.