A Stereo Visual-Inertial Odometry Using Structural Lines for Localizing Indoor Wheeled Robots

2021 ◽  
Author(s):  
Yanfeng Tang ◽  
Chenchen Wei ◽  
Shoulong Cheng ◽  
Zhi Huang
Keyword(s):  
Real World ◽  
Computational Efficiency ◽  
Indoor Environment ◽  
Positioning Accuracy ◽  
Wheeled Robots ◽  
Wheeled Robot ◽  
Challenging Environment ◽  
Benchmark Datasets ◽  
Orientation Information ◽  
Interior Environment

Abstract This paper proposes an optimization-based stereo visual-inertial odometry (VIO) to locate indoor wheeled robots. Multiple Manhattan worlds assumption is adopted to model the interior environment. Instead of treating these worlds as isolated ones, we fuse the latest Manhattan world with the previous ones if they are in the same direction, reducing the calculated errors on the orientation of the latest Manhattan world. Then the structural lines which encode the orientation information of these worlds are taken as additional landmarks to improve positioning accuracy and reduce accumulated drift of the system, especially when the system is in a challenging environment (i.e., scenes with continuous turning and low textures). Besides, the structural lines are parameterized by only two variables, which improves the computational efficiency and simplifies the initialization of lines. Experiments on public benchmark datasets and in real-world environments demonstrate that the proposed VIO system can accurately position the wheeled robot in a complex indoor environment.

scholarly journals Characterization of Carrier Phase-Based Positioning in Real-World Jamming Conditions

2021 ◽  
Vol 13 (14) ◽  
pp. 2680
Author(s):  
Søren Skaarup Larsen ◽  
Anna B. O. Jensen ◽  
Daniel H. Olesen
Keyword(s):  
Real World ◽  
Carrier Phase ◽  
Reference Station ◽  
Baseline Length ◽  
Dual Frequency ◽  
Positioning Accuracy ◽  
The Impact ◽  
Single Versus ◽  
Selection Of

GNSS signals arriving at receivers at the surface of the Earth are weak and easily susceptible to interference and jamming. In this paper, the impact of jamming on the reference station in carrier phase-based relative baseline solutions is examined. Several scenarios are investigated in order to assess the robustness of carrier phase-based positioning towards jamming. Among others, these scenarios include a varying baseline length, the use of single- versus dual-frequency observations, and the inclusion of the Galileo and GLONASS constellations to a GPS only solution. The investigations are based on observations recorded at physical reference stations in the Danish TAPAS network during actual jamming incidents, in order to realistically evaluate the impact of real-world jamming on carrier phase-based positioning accuracy. The analyses performed show that, while there are benefits of using observations from several frequencies and constellations in positioning solutions, special care must be taken in solution processing. The selection of which GNSS constellations and observations to include, as well as when they are included, is essential, as blindly adding more jamming-affected observations may lead to worse positioning accuracy.

Multi-resolution Visual Positioning and Navigation Technique for Unmanned Aerial System Landing Assistance

2017 ◽  
Vol 70 (6) ◽  
pp. 1276-1292
Author(s):  
Chong Yu ◽  
Jiyuan Cai ◽  
Qingyu Chen
Keyword(s):  
Real World ◽  
State Of The Art ◽  
Unmanned Aerial System ◽  
Detection Accuracy ◽  
Relative Positioning ◽  
Positioning Accuracy ◽  
Visual Positioning ◽  
Positioning Technique ◽  
Technique Comparison ◽  
Resolution Simulation

To achieve more accurate navigation performance in the landing process, a multi-resolution visual positioning technique is proposed for landing assistance of an Unmanned Aerial System (UAS). This technique uses a captured image of an artificial landmark (e.g. barcode) to provide relative positioning information in the X, Y and Z axes, and yaw, roll and pitch orientations. A multi-resolution coding algorithm is designed to ensure the UAS will not lose the detection of the landing target due to limited visual angles or camera resolution. Simulation and real world experiments prove the performance of the proposed technique in positioning accuracy, detection accuracy, and navigation effect. Two types of UAS are used to verify the generalisation of the proposed technique. Comparison experiments to state-of-the-art techniques are also included with the results analysis.

Direction-Aware User Recommendation Based on Asymmetric Network Embedding

2022 ◽  
Vol 40 (2) ◽  
pp. 1-23
Author(s):  
Sheng Zhou ◽  
Xin Wang ◽  
Martin Ester ◽  
Bolang Li ◽  
Chen Ye ◽  
...  
Keyword(s):  
Social Networks ◽  
Random Walk ◽  
Real World ◽  
Directed Network ◽  
Network Embedding ◽  
The Social ◽  
Benchmark Datasets ◽  
Direction Information ◽  
User Recommendation ◽  
Asymmetric Proximity

User recommendation aims at recommending users with potential interests in the social network. Previous works have mainly focused on the undirected social networks with symmetric relationship such as friendship, whereas recent advances have been made on the asymmetric relationship such as the following and followed by relationship. Among the few existing direction-aware user recommendation methods, the random walk strategy has been widely adopted to extract the asymmetric proximity between users. However, according to our analysis on real-world directed social networks, we argue that the asymmetric proximity captured by existing random walk based methods are insufficient due to the inbalance in-degree and out-degree of nodes. To tackle this challenge, we propose InfoWalk, a novel informative walk strategy to efficiently capture the asymmetric proximity solely based on random walks. By transferring the direction information into the weights of each step, InfoWalk is able to overcome the limitation of edges while simultaneously maintain both the direction and proximity. Based on the asymmetric proximity captured by InfoWalk, we further propose the qualitative (DNE-L) and quantitative (DNE-T) directed network embedding methods, capable of preserving the two properties in the embedding space. Extensive experiments conducted on six real-world benchmark datasets demonstrate the superiority of the proposed DNE model over several state-of-the-art approaches in various tasks.

Continuous reinforcement learning based ramp jump control for single-track two-wheeled robots

2021 ◽  
pp. 014233122110378
Author(s):  
Qingyuan Zheng ◽  
Duo Wang ◽  
Zhang Chen ◽  
Yiyong Sun ◽  
Bin Liang
Keyword(s):  
Reinforcement Learning ◽  
Energy Savings ◽  
Control Method ◽  
Learning Control ◽  
Action Space ◽  
Gradient Algorithm ◽  
Single Track ◽  
Wheeled Robots ◽  
Reward Function ◽  
Wheeled Robot

Single-track two-wheeled robots have become an important research topic in recent years, owing to their simple structure, energy savings and ability to run on narrow roads. However, the ramp jump remains a challenging task. In this study, we propose to realize a single-track two-wheeled robot ramp jump. We present a control method that employs continuous action reinforcement learning techniques for single-track two-wheeled robot control. We design a novel reward function for reinforcement learning, optimize the dimensions of the action space, and enable training under the deep deterministic policy gradient algorithm. Finally, we validate the control method through simulation experiments and successfully realize the single-track two-wheeled robot ramp jump task. Simulation results validate that the control method is effective and has several advantages over high-dimension action space control, reinforcement learning control of sparse reward function and discrete action reinforcement learning control.

A Localization Algorithm Research to Eliminate the Indoor NLOS Error

2014 ◽  
Vol 989-994 ◽  
pp. 2232-2236 ◽  
Author(s):  
Jia Zhi Dong ◽  
Yu Wen Wang ◽  
Feng Wei ◽  
Jiang Yu
Keyword(s):  
Indoor Environment ◽  
Arrival Time ◽  
Channel Model ◽  
Indoor Positioning ◽  
Superior Performance ◽  
Line Of Sight ◽  
Localization Algorithm ◽  
Positioning Accuracy ◽  
Software Simulation ◽  
Positioning Algorithm

Currently, there is an urgent need for indoor positioning technology. Considering the complexity of indoor environment, this paper proposes a new positioning algorithm (N-CHAN) via the analysis of the error of arrival time positioning (TOA) and the channels of S-V model. It overcomes an obvious shortcoming that the accuracy of traditional CHAN algorithm effected by no-line-of-sight (NLOS). Finally, though MATLAB software simulation, we prove that N-CHAN’s superior performance in NLOS in the S-V channel model, which has a positioning accuracy of centimeter-level and can effectively eliminate the influence of NLOS error on positioning accuracy. Moreover, the N-CHAN can effectively improve the positioning accuracy of the system, especially in the conditions of larger NLOS error.

scholarly journals CityLearn: Diverse Real-World Environments for Sample-Efficient Navigation Policy Learning

2020 ◽  
Author(s):  
Marvin Chancán
Keyword(s):  
Real World ◽  
Autonomous Driving ◽  
Visual Navigation ◽  
Place Recognition ◽  
Visual Appearance ◽  
Learning Techniques ◽  
Benchmark Datasets ◽  
Image Representations ◽  
Visual Place Recognition ◽  
Self Motion

<div>Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end manner, these algorithms require large amounts of experience to learn navigation policies from high-dimensional data, which is generally impractical for real robots due to sample complexity. In this paper, we address these problems with two main contributions. We first leverage place recognition and deep learning techniques combined with goal destination feedback to generate compact, bimodal image representations that can then be used to effectively learn control policies from a small amount of experience. Second, we present an interactive framework, CityLearn, that enables for the first time training and deployment of navigation algorithms across city-sized, realistic environments with extreme visual appearance changes. CityLearn features more than 10 benchmark datasets, often used in visual place recognition and autonomous driving research, including over 100 recorded traversals across 60 cities around the world. We evaluate our approach on two CityLearn environments, training our navigation policy on a single traversal. Results show our method can be over 2 orders of magnitude faster than when using raw images, and can also generalize across extreme visual changes including day to night and summer to winter transitions.</div>

A Measure Optimized Cost-Sensitive Learning Framework for Imbalanced Data Classification

2014 ◽  
pp. 48-75 ◽  
Author(s):  
Peng Cao ◽  
Osmar Zaiane ◽  
Dazhe Zhao
Keyword(s):  
Real World ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Support Vector ◽  
Feature Subset ◽  
Cost Sensitive Learning ◽  
Intrinsic Parameters ◽  
Real World Problem ◽  
Benchmark Datasets ◽  
Feed Forward Neural Networks

Class imbalance is one of the challenging problems for machine-learning in many real-world applications. Many methods have been proposed to address and attempt to solve the problem, including sampling and cost-sensitive learning. The latter has attracted significant attention in recent years to solve the problem, but it is difficult to determine the precise misclassification costs in practice. There are also other factors that influence the performance of the classification including the input feature subset and the intrinsic parameters of the classifier. This chapter presents an effective wrapper framework incorporating the evaluation measure (AUC and G-mean) into the objective function of cost sensitive learning directly to improve the performance of classification by simultaneously optimizing the best pair of feature subset, intrinsic parameters, and misclassification cost parameter. The optimization is based on Particle Swarm Optimization (PSO). The authors use two different common methods, support vector machine and feed forward neural networks, to evaluate the proposed framework. Experimental results on various standard benchmark datasets with different ratios of imbalance and a real-world problem show that the proposed method is effective in comparison with commonly used sampling techniques.

scholarly journals Benchmark Dataset Based on Category Maps with Indoor–Outdoor Mixed Features for Positional Scene Recognition by a Mobile Robot

Robotics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 40
Author(s):  
Hirokazu Madokoro ◽  
Hanwool Woo ◽  
Stephanie Nix ◽  
Kazuhito Sato
Keyword(s):  
Mobile Robot ◽  
Visual Information ◽  
Indoor Environment ◽  
Scene Recognition ◽  
Visual Features ◽  
Wide Field ◽  
Mixed Features ◽  
Wide Field Of View ◽  
Benchmark Datasets ◽  
Unified Method

This study was conducted to develop original benchmark datasets that simultaneously include indoor–outdoor visual features. Indoor visual information related to images includes outdoor features to a degree that varies extremely by time, weather, and season. We obtained time-series scene images using a wide field of view (FOV) camera mounted on a mobile robot moving along a 392-m route in an indoor environment surrounded by transparent glass walls and windows for two directions in three seasons. For this study, we propose a unified method for extracting, characterizing, and recognizing visual landmarks that are robust to human occlusion in a real environment in which robots coexist with people. Using our method, we conducted an evaluation experiment to recognize scenes divided up to 64 zones with fixed intervals. The experimentally obtained results using the datasets revealed the performance and characteristics of meta-parameter optimization, mapping characteristics to category maps, and recognition accuracy. Moreover, we visualized similarities between scene images using category maps. We also identified cluster boundaries obtained from mapping weights.

Energy-Optimal Motion Trajectory of an Omni-Directional Mecanum-Wheeled Robot via Polynomial Functions

Robotica ◽  
2019 ◽  
Vol 38 (8) ◽  
pp. 1400-1414
Author(s):  
Li Xie ◽  
Karl Stol ◽  
Weiliang Xu
Keyword(s):  
Energy Consumption ◽  
Polynomial Functions ◽  
Heavy Duty ◽  
Optimal Motion ◽  
Wheeled Robots ◽  
Motion Trajectories ◽  
Decision Variables ◽  
Robotic Motion ◽  
Wheeled Robot ◽  
Mecanum Wheel

SUMMARYThe Mecanum wheel is one of the practical omni-directional wheel designs in industry, especially for heavy-duty tasks in a confined floor. An issue with Mecanum-wheeled robots is inefficient use of energy. In this study, the robotic motion trajectories are optimized to minimize the energy consumption, where a robotic path is expressed in polynomial functions passing through a given set of via points, and a genetic algorithm is used to find the polynomial’s coefficients being decision variables. To attempt a further reduction in the energy consumption, the via points are also taken as decision variables for the optimization. Both simulations and experiments are conducted, and the results show that the optimized trajectories result in a significant reduction in energy consumption, which can be further lowered when the via points become decision variables. It is also found that the higher the order of the polynomials the larger the reduction in the energy consumption.

Sign in / Sign up

Export Citation Format

Share Document