Robot Pose Research Articles

A Measurement Method for Robot Peg-in-Hole Prealignment Based on Combined Two-Level Visual Sensors

Vision measurement plays a significant role in robot automatic assembly. In this study, a new measurement method for robot peg-in-hole prealignment via a combined two-level vision system is proposed. The assembly system and a global coordinate system calibration procedure based on a dynamic coordinate system are developed to construct an accurate transformation between the coordinate systems. The subsequent hole pose is obtained with the proposed image processing method and the hole edge matching method, followed by the 3-D hole reconstruction and spatial circle fitting algorithm. A low-cost pose determination is proposed based on hole edge point selection. The experiment and analysis indicate that the hybrid measurement system has high precision in the local hole pose and global robot pose measurement accuracy. The peg-in-hole assembly results verify the measurement and calibration accuracy sideways. Our hybrid measurement system enhances the vision measurement range, local accuracy, and robot automation.

A Deep-Learning-based Strategy for Kidnapped Robot Problem in Similar Indoor Environment

We present a deep-learning-based strategy that only uses a 2D LiDAR sensor to solve the kidnapped robot problem in similar indoor environments. First, we converted a set of 2D laser data into an RGB-image and an occupancy grid map and stacked them into a multi-channel image. Then, a neural network structure with five convolutional layers and four fully connected layers was designed to regress the 3-DOF robot pose. Finally, the network was trained using multi-channel images as input. We also improved the network structure to identify the scene where the robot is localized. Extensive experiments have been conducted in practice with a real mobile robot, verifying the effectiveness of the proposed strategy. Our network can obtain approximately 2m and 5∘ accuracy indoors, and the scene classification accuracy of our network reaches up to 98%.

Global Localization With a Single-Line LiDAR by Dense 2D Signature and 1D Registration

Global localization is a key problem that needs to be solved for single-line LiDAR based robot navigation since it will directly affect the estimation accuracy of the robot's initial pose and the success rate of recovering the robot's state when it loses its local pose. Existing studies to deal with this problem usually extract feature points from laser beams and then resort to fast retrieval and registration methods to further determine the robot's pose. Although these methods have achieved good results in specific scenes, they often fail to perform well when the robot is far away from the map-building trajectory. It is therefore highly desirable to develop more robust techniques for this problem. In this work, we propose a novel solution which is based on “Dense 2D Signature and 1D Registration”, D2S1R for short. By establishing a dense signature database for 2D locations and combining with the fast retrieval technology, the 2D search space is extremely compressed. Furthermore, fast yaw angle determination is achieved by converting scan points to 1D space and measuring the difference of scan contours based on relative entropy. Experimental results on several complex indoor scenes show that D2S1R can complete global localization within 0.03s on an ordinary CPU in an area of nearly 4,000m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> . Besides, on the premise of achieving a location accuracy of 0.08±0.04m and an orientation accuracy of 0.72±0.60°, it can achieve an average success rate of 95% on all test datasets.

Probabilistic information fusion to model the pose-dependent dynamics of milling robots

Conventional industrial robots are increasingly used for milling applications of large workpieces due to their workspace and their low investment costs in comparison to conventional machine tools. However, static deflections and dynamic instabilities during the milling process limit the efficiency and productivity of such robot-based milling systems. Since the pose-dependent dynamic properties of the industrial robot structures are notoriously difficult to model analytically, machine learning methods are recently gaining more and more popularity to derive system models from experimental data. In this publication, a modeling concept based on a modern information fusion scheme, fusing simulation and experimental data, is proposed. This approach provides a precise model of the robot’s pose-dependent structural dynamics and is validated for a one-dimensional variation of the robot pose. The results of two information fusion algorithms are compared with a conventional, data-driven approach and indicate a superior model accuracy regarding interpolation and extrapolation of the pose-dependent dynamics. The proposed approach enables decreasing the necessary amount of experimental data needed to assess the vibrational properties of the robot for a desired pose. Additionally, the concept is able to predict the robot dynamics at poses where experimental data is very costly to gather.

Control Parameters Design Based on Dynamic Characteristics of a Hybrid Robot With Parallelogram Structures

Control parameter designing is an essential issue for industrial robot applications, in which the dynamic characteristics of robots play an important role. This article investigates the dynamic and control parameter design of a hybrid spray-painting robot with parallelogram structures to improve its tracking performance. The dynamic model of the robot is derived, and its intrinsic dynamic properties, such as time-varying characteristics, decoupling driving properties, and the contribution of each component to the total driving torque, are investigated. Based on the robot dynamic analysis, the comprehensive performance of the robotic mechatronic system is examined, and several principles for control parameter design are presented. Finally, on the basis of the small noise excitation method, a strategy to determine the robot pose for control parameter tuning is proposed. The strategy is experimentally verified to improve the consistency of motion accuracy in the entire workspace effectively.

Penerapan SLAM Gmapping dengan Robot Operating System Menggunakan Laser Scanner pada Turtlebot

The manouver ability from one place to another in order to accomplish some tasks safely is a basic requirement of mobile robotics. Current robotic’s navigation systems require a ’real world’ map data, acquired by on-board sensors, to carry out simultaneous localisation and navigation (SLAM) algorithm. There are several SLAM algorithms. In this article we used SLAM gmapping using robot operating system (ROS) and laser scanner. The gmapping slam algorithm used particle filter method to localize robot pose within the environment and generate 2D occupancy grid map. The map is in gray-scale informed the free space, wall, and unexplored space. The implementation of gmapping slam conducted with turtlebot 3 from Robotics as well as 3D simulation using gazebo.

TRAJECTORY SIMULATION OF BADMINTON ROBOT BASED ON FRACTAL BROWN MOTION

This paper focuses on the design of badminton robots, and designs high-precision binocular stereo vision synchronous acquisition system hardware and multithreaded acquisition programs to ensure the left and right camera exposure synchronization and timely reading of data. Aiming at specific weak moving targets, a shape-based Brown motion model based on dynamic threshold adjustment based on singular value decomposition is proposed, and a discriminative threshold is set according to the similarity between the background and the foreground to improve detection accuracy. The three-dimensional trajectory points are extended by Kalman filter and the kinematics equation of badminton is established. The parameters of the kinematics equation of badminton are solved by the method of least squares. Based on the fractal Brownian motion algorithm, a real-time robot pose estimation algorithm is proposed to realize the real-time accurate pose estimation of the robot. A PID control model for the badminton robot executive mechanism is established between the omnidirectional wheel speed and the robot’s translation and rotation movements to achieve the precise movement of the badminton robot. All the algorithms can meet the system’s requirements for real-time performance, realize the badminton robot’s simple hit to the ball, and prospect the future research direction.

Navigation of a mobile robot in a dynamic environment using a point cloud map

In this paper, we consider autonomous navigation of a wheeled mobile robot in a dynamic environment using a 3D point cloud map. We consider four kinds of 2D maps: static global map, dynamic global map, global cost map, and local cost map; to plan a feasible path of the robot to adapt to a dynamic environment. We consider a mobile robot for plant patrolling in a 3D environment with plane slopes but not rough terrain for which a 2D environment map suffices. We propose 2D static global map for robot navigation by projecting prior measured 3D point cloud map data on a horizontal plane with considering the climbing ability of the robot. We also build a 2D dynamic global map by projecting a real-time 3D point cloud on the 2D static global map by SLAM. Accumulated errors of SLAM can be canceled using some landmarks placed in the environment. A global planner calculates an optimal global path that minimizes the distance from an initial robot pose (position and orientation) to a goal pose (position and orientation) by A* algorithm based on the global cost map which is built from the dynamic global map. However, this process should take much time. To avoid moving obstacles, the TEB (Timed Elastic Band) local planner is used to calculate an optimal local path based on a local cost map which is given by a real-time local 3D point cloud. To demonstrate the effectiveness of the proposed system, experiments were carried out. In the experiment, we use an AR card as a landmark for simplification of implementation. We prove that the robot can navigate in a dynamic environment and accumulated errors can be canceled by the AR cards placed in the environment as landmarks.

A real-time multi-constraints obstacle avoidance method using LiDAR

Obstacle avoidance is one of the essential and indispensable functions for autonomous mobile robots. Most of the existing solutions are typically based on single condition constraint and cannot incorporate sensor data in a real-time manner, which often fail to respond to unexpected moving obstacles in dynamic unknown environments. In this paper, a novel real-time multi-constraints obstacle avoidance method using Light Detection and Ranging(LiDAR) is proposed, which is able to, based on the latest estimation of the robot pose and environment, find the sub-goal defined by a multi-constraints function within the explored region and plan a corresponding optimal trajectory at each time step iteratively, so that the robot approaches the goal over time. Meanwhile, at each time step, the improved Ant Colony Optimization(ACO) algorithm is also used to re-plan optimal paths from the latest robot pose to the latest defined sub-goal position. While ensuring convergence, planning in this method is done by repeated local optimizations, so that the latest sensor data from LiDAR and derived environment information can be fully utilized at each step until the robot reaches the desired position. This method facilitates real-time performance, also has little requirement on memory space or computational power due to its nature, thus our method has huge potentials to benefit small low-cost autonomous platforms. The method is evaluated against several existing technologies in both simulation and real-world experiments.

Inverted pendulum model for turn-planning for biped robot

Based on the inverted pendulum model, gait planning of biped robot is carried out, which makes it walk steadily and realizes steering in one step. Aiming at the stability of the turning poses of the humanoid robot, this paper studies the landing stability analysis of the robot, the planning and control of landing after turning, improves the inverted pendulum model, and introduces the turning angle to the model of trajectory generation. By this method, the robot can plan a more reasonable gait trajectory of the real robot when turning, and achieve a single-step sharp turn at any angle, thereby making the robot walk more smoothly. Based on ROS and V-rep, the robot simulation platform was constructed, the hardware experimental platform was self-made, and the feasibility of gait planning method was verified by simulation and experiments respectively. The experiment results showed that the turning error of the robot on the plane was less than 6°.

Design of the navigation system through the fusion of IMU and wheeled encoders

Mobile robots must autonomously navigate in structured environments. In this paper, we proposed a new navigation system for mobile robots, where lost-cost components were used to complete accurate navigation tasks. To accomplish the navigation task, we designed and validated a set of algorithms for obstacle avoidance and estimation of the robot pose. The proposed navigation system consists of three main modules: local occupancy map generation, extended Kalman filter (EKF)-based localization and modified obstacle avoidance algorithm. The system initially performed visual feature point tracking followed by feature point classification using an inverse perspective transformation for obstacle detection. When the estimated obstacle position is provided, a local obstacle avoidance algorithm is activated to generate motion commands for safe navigation. When the local occupancy map is generated, a modified artificial potential field based on boundary detection is developed for navigation through an indoor environment. Moreover, we proposed a strategy to localize a mobile robot using an IMU, a camera and wheel encoders. The EKF is adopted to reduce the sensor noise and bias. Experiments demonstrate that our navigation system is useful and can significantly benefit other reactive navigations.

An On-chip Spiking Neural Network for Estimation of the Head Pose of the iCub Robot.

In this work, we present a neuromorphic architecture for head pose estimation and scene representation for the humanoid iCub robot. The spiking neuronal network is fully realized in Intel's neuromorphic research chip, Loihi, and precisely integrates the issued motor commands to estimate the iCub's head pose in a neuronal path-integration process. The neuromorphic vision system of the iCub is used to correct for drift in the pose estimation. Positions of objects in front of the robot are memorized using on-chip synaptic plasticity. We present real-time robotic experiments using 2 degrees of freedom (DoF) of the robot's head and show precise path integration, visual reset, and object position learning on-chip. We discuss the requirements for integrating the robotic system and neuromorphic hardware with current technologies.

An Efficient Calibration Method of Line Structured Light Vision Sensor in Robotic Eye-in-Hand System

For line structured light vision sensor in robotic eye-in-hand system, the calibration of camera parameters, robot hand eye parameters and structured light plane parameters is an indispensable procedure before conducting 3-D measurement. Traditionally, these three sets of parameters are calibrated separately, making the calibration process complicated and inefficient. To address this, an efficient calibration method is proposed in this paper. By changing the poses of robot and calibration target, a set of images of the calibration target is captured, upon which the camera calibration is conducted. The extrinsic parameters obtained from camera calibration are utilized in the calibration of the structured light plane parameters and hand eye parameters, using the same set of images. Therefore, the three sets of parameters can be simultaneously calibrated with simple on-site operations. Moreover, the calibration target used in this method is only a planar checkerboard, which can be easily acquired at low cost. It is verified in the experiment that the proposed method is efficient and accurate, with the calibration duration within 10 minutes and the measurement accuracy within 0.40mm. Additionally, object pose measurement experiment is conducted to validate the effectiveness of the proposed method in practical application.

Tube-based nonlinear model predictive control for autonomous skid-steer mobile robots with tire–terrain interactions

This work addresses the problem of robust tracking control for skid-steer mobile platforms, using tube-based Nonlinear Model Predictive Control. The strategy seeks to mitigate the impact of disturbances propagated to autonomous vehicles originated by traction losses. To this end, a dynamical model composed by two coupled sub-systems stands for lateral and longitudinal vehicle dynamics and tire behavior. The controller is aimed at tracking prescribed stable operation points of the slip and side-slip beyond the robot pose and speeds. To reach robust tracking performance on the global system, a centralized control scheme operates under a predictive control framework composed by three control actions. The first one compensates for disturbances using the reference trajectory-feedforward control. The second control action corrects the errors generated by the modeling mismatch. The third one is devoted to ensure robustness on the closed-loop system whilst compensating for deviations of the state trajectories from the nominal ones (i.e. disturbance-free). The strategy ensures robust feasibility even when tightening constraints are met. Such constraints are calculated on-line based on robust positively invariant sets characterized by polytopic sets (tubes), including a terminal region to guarantee robustness. The benefits of the controller regarding tracking performance, constraint satisfaction and computational practicability were tested through simulations with a Cat® 262C skid-steer model. Then, in field tests, the controller evidenced high tracking accuracy against terrain disturbances when benchmarking performance with respect to inherent robust predictive controllers.

Backstepping controller for laser ray tracking of a target mobile robot

Tracking control, which is applied to the target mobile robots in the process of rushing toward the trainees, is one of the critical technologies in the advancement of anti-terrorist training. Considering the disadvantages of various types of traditional tracking methods, this paper proposes a novel laser ray tracking mechanism and a backstepping controller for the target mobile robot that is used in shooting ranges. The mechanism and principle of the laser ray tracking is illustrated in detail. Based on the unique structure, the light intensity distributions are measured to further locate the laser spots on the cut-ray boards. Then, the relationship between the positions of the laser spots on the cut-ray boards and the pose of the target mobile robot is demonstrated. According to the features of the tracking situation, a backstepping controller is designed to achieve the laser ray tracking. After that, the inverse kinematics of the wheeled skid-steering mobile robot is analyzed to map the linear and angular velocities of the robot to the velocities of its left wheels and right wheels. The conventional proportional–integral–derivative controller is applied in the experiments to compare with the proposed backstepping controller. The experimental results show that the proposed controller is more robust, and converges faster for the laser ray tracking.

Cost-effective Indoor Localization for Autonomous Robots using Kinect and WiFi Sensors

Indoor localization has been considered to be the most fundamental problem when it comes to providing a robot with autonomous capabilities. Although many algorithms and sensors have been proposed, none have proven to work perfectly under all situations. Also, in order to improve the localization quality, some approaches use expensive devices either mounted on the robots or attached to the environment that don't naturally belong to human environments. This paper presents a novel approach that combines the benefits of two localization techniques, WiFi and Kinect, into a single algorithm using low-cost sensors. It uses separate Particle Filters (PFs). The WiFi PF gives the global location of the robot using signals of Access Point devices from different parts of the environment while it bounds particles of the Kinect PF, which determines the robot's pose locally. Our algorithm also tackles the Initialization/Kidnapped Robot Problem by detecting divergence on WiFi signals, which starts a localization recovering process. Furthermore, new methods for WiFi mapping and localization are introduced.

Pose optimization in robotic machining using static and dynamic stiffness models

Abstract Industrial robots are typically not used for milling of hard materials due to their low stiffness compared to traditional machine tools. Due to milling being a five degree of freedom (dof) operation, a typical six dof serial manipulator introduces a redundant degree of freedom in the robot pose. This redundancy can be exploited to optimize the pose of the robot during milling to minimize force-induced deflections at the end-effector. Stiffness modeling and optimization techniques for industrial robots utilizing both static (no mass and damping terms) and dynamic (mass and damping terms included) models exist. This paper presents a comparative study of robot pose optimization using static and dynamic stiffness models for different cutting scenarios. Milling experiments show that while a dynamic model-based robot pose optimization yields significant improvement over a static model-based optimization for cutting conditions where the time varying cutting forces approach the robot's natural frequencies, a static model-based optimization is sufficient when the frequency content of the cutting forces are not close to the robot's natural frequencies.

Incremental 3-D pose graph optimization for SLAM algorithm without marginalization

Pose graph optimization algorithm is a classic nonconvex problem which is widely used in simultaneous localization and mapping algorithm. First, we investigate previous contributions and evaluate their performances using KITTI, Technische Universität München (TUM), and New College data sets. In practical scenario, pose graph optimization starts optimizing when loop closure happens. An estimated robot pose meets more than one loop closures; Schur complement is the common method to obtain sequential pose graph results. We put forward a new algorithm without managing complex Bayes factor graph and obtain more accurate pose graph result than state-of-art algorithms. In the proposed method, we transform the problem of estimating absolute poses to the problem of estimating relative poses. We name this incremental pose graph optimization algorithm as G-pose graph optimization algorithm. Another advantage of G-pose graph optimization algorithm is robust to outliers. We add loop closure metric to deal with outlier data. Previous experiments of pose graph optimization algorithm use simulated data, which do not conform to real world, to evaluate performances. We use KITTI, TUM, and New College data sets, which are obtained by real sensor in this study. Experimental results demonstrate that our proposed incremental pose graph algorithm model is stable and accurate in real-world scenario.

Grasping pose estimation for SCARA robot based on deep learning of point cloud

With the development of 3D measurement technology, 3D vision sensors and object pose estimation methods have been developed for robotic loading and unloading. In this work, an end-to-end deep learning method on point clouds, PointNetRGPE, is proposed to estimating the grasping pose of SCARA robot. In PointNetRGPE model, the point cloud and class number are fused into a point-class vector, and several PointNet-like networks are used to estimate the robot grasping pose, containing 3D translation and 1D rotation. Considering that rotational symmetry is very common in man-made and industrial environments, a novel architecture is introduced into PointNetRGPE to solve the pose estimation problem with rotational symmetry in the z-axis direction. Additionally, an experimental platform is built containing an industrial robot and a binocular stereo vision system, and a dataset with three subsets is set up. Finally, the PointNetRGPE is tested on the dataset, and the success rates of three subsets are 98.89%, 98.89%, and 94.44% respectively.

SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory

This letter describes an end-to-end pipeline for tree diameter estimation based on semantic segmentation and lidar odometry and mapping. Accurate mapping of this type of environment is challenging since the ground and the trees are surrounded by leaves, thorns and vines, and the sensor typically experiences extreme motion. We propose a semantic feature based pose optimization that simultaneously refines the tree models while estimating the robot pose. The pipeline utilizes a custom virtual reality tool for labeling 3D scans that is used to train a semantic segmentation network. The masked point cloud is used to compute a trellis graph that identifies individual instances and extracts relevant features that are used by the SLAM module. We show that traditional lidar and image based methods fail in the forest environment on both Unmanned Aerial Vehicle (UAV) and hand-carry systems, while our method is more robust, scalable, and automatically generates tree diameter estimations.