Search results

Image‐based localisation has been widely investigated in mobile robotics. However, traditional image‐based localisation approaches do not work when the environment appearance changes. The purpose of this paper is to propose a new system for image‐based localisation, which enables the approach to work also in highly dynamic environments.

The proposed technique is based on the use of a distributed vision system (DVS) composed of a set of cameras installed in the environment and of a camera mounted on a mobile robot. The localisation of the robot is achieved by comparing the current image grabbed by the robot with the images grabbed, at the same time, by the DVS. Finding the DVS's image, most similar to the robot's image, gives a topological localisation of the robot.

Experiments reported in the paper proved the system to be effective, even exploiting a pre‐existent DVS not designed for this application.

Whilst, aware that DVSs, as the one used in this work, are not diffuse nowadays, this work is significant because a novel idea is proposed for dealing with dynamic environments in the image‐based localisation approach and the idea is validated with experiments. Camera Sensor networks currently are an emerging technology and they may be introduced in several daily environments in the future.

This study aims to develop a real-time algorithm, which can detect people even in arbitrary poses. To cover poor and changing light conditions, it does not rely on color information. The developed method is expected to run on computers with low computational resources so that it can be deployed on autonomous mobile robots.

The method is designed to have a people detection pipeline with a series of operations. Efficient point cloud processing steps with a novel head extraction operation provide possible head clusters in the scene. Classification of these clusters using support vector machines results in high speed and robust people detector.

The method is implemented on an autonomous mobile robot and results show that it can detect people with a frame rate of 28 Hz and equal error rate of 92 per cent. Also, in various non-standard poses, the detector is still able to classify people effectively.

The main limitation would be for point clouds similar to head shape causing false positives and disruptive accessories (like large hats) causing false negatives. Still, these can be overcome with sufficient training samples.

The method can be used in industrial and social mobile applications because of its robustness, low resource needs and low power consumption.

The paper introduces a novel and efficient technique to detect people in arbitrary poses, with poor light conditions and low computational resources. Solving all these problems in a single and lightweight method makes the study fulfill an important need for collaborative and autonomous mobile robots.

The purpose of this paper is to promote the efficiency of RGB-depth (RGB-D)-based object recognition in robot vision and find discriminative binary representations for RGB-D based objects.

To promote the efficiency of RGB-D-based object recognition in robot vision, this paper applies hashing methods to RGB-D-based object recognition by utilizing the approximate nearest neighbors (ANN) to vote for the final result. To improve the object recognition accuracy in robot vision, an “Encoding+Selection” binary representation generation pattern is proposed. “Encoding+Selection” pattern can generate more discriminative binary representations for RGB-D-based objects. Moreover, label information is utilized to enhance the discrimination of each bit, which guarantees that the most discriminative bits can be selected.

The experiment results validate that the ANN-based voting recognition method is more efficient and effective compared to traditional recognition method in RGB-D-based object recognition for robot vision. Moreover, the effectiveness of the proposed bit selection method is also validated to be effective.

Hashing learning is applied to RGB-D-based object recognition, which significantly promotes the recognition efficiency for robot vision while maintaining high recognition accuracy. Besides, the “Encoding+Selection” pattern is utilized in the process of binary encoding, which effectively enhances the discrimination of binary representations for objects.

The purpose of this study is solving the hand–eye calibration issue for line structured light vision sensor. Only after hand–eye calibration the sensor measurement data can be applied to robot system.

In this paper, the hand–eye calibration methods are studied, respectively, for eye-in-hand and eye-to-hand. Firstly, the coordinates of the target point in robot system are obtained by tool centre point (TCP), then the robot is controlled to make the sensor measure the target point in multiple poses and the measurement data and pose data are obtained; finally, the sum of squared calibration errors is minimized by the least square method. Furthermore, the missing vector in the process of solving the transformation matrix is obtained by vector operation, and the complete matrix is obtained.

On this basis, the sensor measurement data can be easily and accurately converted to the robot coordinate system by matrix operation.

This method has no special requirement for robot pose control, and its calibration process is fast and efficient, with high precision and has practical popularized value.

Autonomous mobile robots (AMRs) play a crucial role in industrial and service fields. The paper aims to build a LiDAR-based simultaneous localization and mapping (SLAM) system used by AMRs to overcome challenges in dynamic and changing environments.

This research introduces SLAM-RAMU, a lifelong SLAM system that addresses these challenges by providing precise and consistent relocalization and autonomous map updating (RAMU). During the mapping process, local odometry is obtained using iterative error state Kalman filtering, while back-end loop detection and global pose graph optimization are used for accurate trajectory correction. In addition, a fast point cloud segmentation module is incorporated to robustly distinguish between floor, walls and roof in the environment. The segmented point clouds are then used to generate a 2.5D grid map, with particular emphasis on floor detection to filter the prior map and eliminate dynamic artifacts. In the positioning process, an initial pose alignment method is designed, which combines 2D branch-and-bound search with 3D iterative closest point registration. This method ensures high accuracy even in scenes with similar characteristics. Subsequently, scan-to-map registration is performed using the segmented point cloud on the prior map. The system also includes a map updating module that takes into account historical point cloud segmentation results. It selectively incorporates or excludes new point cloud data to ensure consistent reflection of the real environment in the map.

The performance of the SLAM-RAMU system was evaluated in real-world environments and compared against state-of-the-art (SOTA) methods. The results demonstrate that SLAM-RAMU achieves higher mapping quality and relocalization accuracy and exhibits robustness against dynamic obstacles and environmental changes.

Compared to other SOTA methods in simulation and real environments, SLAM-RAMU showed higher mapping quality, faster initial aligning speed and higher repeated localization accuracy.

Aiming at the problem of insufficient adaptability of robot motion planners under the diversity of end-effector constraints, this paper proposes Transformation Cross-sampling Framework (TC-Framework) that enables the planner to adapt to different end-effector constraints.

This work presents a standard constraint methodology for representing end-effector constraints as a collection of constraint primitives. The constraint primitives are merged sequentially into the planner, and a unified constraint input interface and constraint module are added to the standard sampling-based planner framework. This approach enables the realization of a generic planner framework that avoids the need to build separate planners for different end-effector constraints.

Simulation tests have demonstrated that the planner based on TC-framework can adapt to various end-effector constraints. Physical experiments have also confirmed that the framework can be used in real robotic systems to perform autonomous operational tasks. The framework’s strong compatibility with constraints allows for generalization to other tasks without modifying the scheduler, significantly reducing the difficulty of robot deployment in task-diverse scenarios.

This paper proposes a unified constraint method based on constraint primitives to enhance the sampling-based planner. The planner can now adapt to different end effector constraints by opening up the input interface for constraints. A series of simulation tests were conducted to evaluate the TC-Framework-based planner, which demonstrated its ability to adapt to various end-effector constraints. Tests on a physical experimental system show that the framework allows the robot to perform various operational tasks without requiring modifications to the planner. This enhances the value of robots for applications in fields with diverse tasks.

The goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the Gaussian distribution of obstacles. A route for autonomous vehicles may be swiftly created using this algorithm.

The path planning issue is divided into three key steps by the authors. First, the tree expansion is sped up by the dynamic step size using a combination of Q-learning and the Gaussian distribution of obstacles. The invalid nodes are then removed from the initially created pathways using bidirectional pruning. B-splines are then employed to smooth the predicted pathways.

The algorithm is validated using simulations on straight and curved highways, respectively. The results show that the approach can provide a smooth, safe route that complies with vehicle motion laws.

An improved RRT algorithm based on Q-learning and obstacle Gaussian distribution (QGD-RRT) is proposed for the path planning of self-driving vehicles. Unlike previous methods, the authors use Q-learning to steer the tree's development direction. After that, the step size is dynamically altered following the density of the obstacle distribution to produce the initial path rapidly and cut down on planning time even further. In the aim to provide a smooth and secure path that complies with the vehicle kinematic and dynamical restrictions, the path is lastly optimized using an enhanced bidirectional pruning technique.

Picking up pistons in arbitrary poses is an important step on car engine assembly line. The authors usually use vision system to estimate the pose of the pistons and then guide a stable grasp. However, a piston in some poses, e.g. the mouth of the piston faces forward, is hardly to be directly grasped by the gripper. Thus, we need to reorient the piston to achieve a desired pose, i.e. let its mouth face upward, for grasping.

This paper aims to present a vision-based picking system that can grasp pistons in arbitrary poses. The whole picking process is divided into two stages. At localization stage, a hierarchical approach is proposed to estimate the piston’s pose from image which usually involves both heavy noise and edge distortions. At grasping stage, multi-step robotic manipulations are designed to enable the piston to follow a nominal trajectory to reach to the minimum of the distance between the piston’s center and the support plane. That is, under the design input, the piston would be pushed to achieve a desired orientation.

A target piston in arbitrary poses would be picked from the conveyor belt by the gripper with the proposed method.

The designed robotic bin-picking system using vision is an advantage in terms of flexibility in automobile manufacturing industry.

The authors develop a methodology that uses a pneumatic gripper and 2D vision information for picking up multiple pistons in arbitrary poses. The rough pose of the parts are detected based on a hierarchical approach for detection of multiple ellipses in the environment that usually involve edge distortions. The pose uncertainties of the piston are eliminated by multi-step robotic manipulations.

In response to the challenge of reduced efficiency or failure of robot motion planning algorithms when faced with end-effector constraints, this study aims to propose a new constraint method to improve the performance of the sampling-based planner.

In this work, a constraint method (TC method) based on the idea of cross-sampling is proposed. This method uses the tangent space in the workspace to approximate the constrained manifold pattern and projects the entire sampling process into the workspace for constraint correction. This method avoids the need for extensive computational work involving multiple iterations of the Jacobi inverse matrix in the configuration space and retains the sampling properties of the sampling-based algorithm.

Simulation results demonstrate that the performance of the planner when using the TC method under the end-effector constraint surpasses that of other methods. Physical experiments further confirm that the TC-Planner does not cause excessive constraint errors that might lead to task failure. Moreover, field tests conducted on robots underscore the effectiveness of the TC-Planner, and its excellent performance, thereby advancing the autonomy of robots in power-line connection tasks.

This paper proposes a new constraint method combined with the rapid-exploring random trees algorithm to generate collision-free trajectories that satisfy the constraints for a high-dimensional robotic system under end-effector constraints. In a series of simulation and experimental tests, the planner using the TC method under end-effector constraints efficiently performs. Tests on a power distribution live-line operation robot also show that the TC method can greatly aid the robot in completing operation tasks with end-effector constraints. This helps robots to perform tasks with complex end-effector constraints such as grinding and welding more efficiently and autonomously.

The purpose of this paper is to actively calibrate power density to match the application requirements with as small an actuator as possible. So, this paper introduces shape memory alloy to design variable stiffness elements. Meanwhile, the purpose of this paper is also to solve the problem of not being able to install sensors on shape memory alloy due to volume limitations.

This paper introduces the design, modeling and control process for a variable stiffness passive ankle exoskeleton, adjusting joint stiffness using shape memory alloy (SMA). This innovative exoskeleton aids the human ankle by adapting the precompression of elastic components by SMA, thereby adjusting the ankle exoskeleton’s integral stiffness. At the same time, this paper constructs a mathematical model of SMA to achieve a dynamic stiffness adjustment function.

Using SMA as the driving force for stiffness modification in passive exoskeletons introduces several distinct advantages, inclusive of high energy density, programmability, rapid response time and simplified structural design. In the course of experimental validation, this ankle exoskeleton, endowed with variable stiffness, proficiently executed actions like squatting and walking and it can effectively increase the joint stiffness by 0.2 Nm/Deg.

The contribution of this paper is to introduce SMA to adjust the stiffness to actively calibrate power density to match the application requirements. At the same time, this paper constructs a mathematical model of SMA to achieve a dynamic stiffness adjustment function.