scholarly journals A Hybrid Technique for Active SLAM Based on RPPO Model with Transfer Learning

2022 ◽  
Author(s):  
Shuhuan Wen ◽  
Zhixin Ji ◽  
Ahmad B. Rad ◽  
Zhengzheng Guo
Keyword(s):  
Transfer Learning ◽  
Autonomous Navigation ◽  
Action Plan ◽  
A Priori ◽  
Hybrid Technique ◽  
Free Exploration ◽  
Unknown Environments ◽  
Localization And Mapping ◽  
Slam Algorithm ◽  
Policy Optimization

Abstract The problem of exploration in unknown environments is still a great challenge for autonomous mobile robots due to the lack of a priori knowledge. Active Simultaneous Localization and Mapping (SLAM) is an effective method to realize obstacle avoidance and autonomous navigation. Traditional Active SLAM is usually complex to model and difficult to adapt automatically to new operating areas. This paper presents a novel Active SLAM algorithm based on Deep Reinforcement Learning (DRL). The Relational Proximal Policy Optimization (RPPO) model with deep separable convolution and data batch processing is used to predict the action strategy and generate the action plan through the acquired environment RGB images, so as to realize the autonomous collision free exploration of the environment. Meanwhile, Gmapping is applied to locate and map the environment. Then, based on Transfer Learning, Active SLAM algorithm is applied to complex unknown environments with various dynamic and static obstacles. Finally, we present several experiments to demonstrate the advantages and feasibility of the proposed Active SLAM algorithm.

scholarly journals Active SLAM for Autonomous Underwater Exploration

2019 ◽  
Vol 11 (23) ◽  
pp. 2827 ◽  
Author(s):  
Narcís Palomeras ◽  
Marc Carreras ◽  
Juan Andrade-Cetto
Keyword(s):  
Autonomous Underwater Vehicles ◽  
A Priori ◽  
Underwater Vehicles ◽  
View Planning ◽  
Localization And Mapping ◽  
Entropy Reduction ◽  
Graph Slam ◽  
Slam Algorithm ◽  
Iterative Closest Point Algorithm ◽  
Active Localization

Exploration of a complex underwater environment without an a priori map is beyond the state of the art for autonomous underwater vehicles (AUVs). Despite several efforts regarding simultaneous localization and mapping (SLAM) and view planning, there is no exploration framework, tailored to underwater vehicles, that faces exploration combining mapping, active localization, and view planning in a unified way. We propose an exploration framework, based on an active SLAM strategy, that combines three main elements: a view planner, an iterative closest point algorithm (ICP)-based pose-graph SLAM algorithm, and an action selection mechanism that makes use of the joint map and state entropy reduction. To demonstrate the benefits of the active SLAM strategy, several tests were conducted with the Girona 500 AUV, both in simulation and in the real world. The article shows how the proposed framework makes it possible to plan exploratory trajectories that keep the vehicle’s uncertainty bounded; thus, creating more consistent maps.

scholarly journals SISTEM NAVIGASI MOBILE ROBOT DALAM RUANGAN BERBASIS AUTONOMOUS NAVIGATION

2019 ◽  
Vol 4 (2) ◽  
pp. 78 ◽  
Author(s):  
Dwiky Erlangga ◽  
Endang D ◽  
Rosalia H S ◽  
Sunarto Sunarto ◽  
Kuat Rahardjo T.S ◽  
...  
Keyword(s):  
Mobile Robot ◽  
Autonomous Navigation ◽  
Local Planning ◽  
Localization And Mapping ◽  
Monte Carlo Localization ◽  
Computer Based ◽  
Slam Algorithm ◽  
Main Components ◽  
Window Approach ◽  
Global Planning

<p><em>Autonomous navigation is absolutely necessary in mobile-robotic, which consists of four main components, namely: perception, localization, path-planning, and motion-control. Mobile robots create maps of space so that they can carry out commands to move from one place to another using the autonomous-navigation method. Map making using the Simultaneous-Localization-and-Mapping (SLAM) algorithm that processes data from the RGB-D camera sensor and bumper converted to laser-scan and point-cloud is used to obtain perception. While the wheel-encoder and gyroscope are used to obtain odometry data which is used to construct travel maps with the SLAM algorithm, gmapping and performing autonomous navigation. The system consists of three sub-systems, namely: sensors as inputs, single-board computers for processes, and actuators as movers. Autonomous-navigation is regulated through the navigation-stack using the Adaptive-Monte-Carlo-Localization (AMCL) algorithm for localization and global-planning, while the Dynamic-Window-Approach (DWA) algorithm with Robot-Operating-System-(ROS) for local -planning. The results of the test show the system can provide depth-data that is converted to laser-scan, bumper data, and odometry data to single-board-computer-based ROS so that mobile-controlled teleoperating robots from workstations can build 2-dimensional grid maps with total accuracy error rate of 0.987%. By using maps, data from sensors, and odometry the mobile-robot can perform autonomous-navigation consistently and be able to do path-replanning, avoid static obstacles and continue to do localization to reach the destination point.</em></p>

scholarly journals REINFORCEMENT LEARNING HELPS SLAM: LEARNING TO BUILD MAPS

2020 ◽  
Vol XLIII-B4-2020 ◽  
pp. 329-335
Author(s):  
N. Botteghi ◽  
B. Sirmacek ◽  
R. Schulte ◽  
M. Poel ◽  
C. Brune
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
A Priori ◽  
Simultaneous Localization And Mapping ◽  
Indoor Environments ◽  
Robot Localization ◽  
Robust Solution ◽  
Localization And Mapping ◽  
Reward Functions ◽  
Slam Algorithm

Abstract. In this research, we investigate the use of Reinforcement Learning (RL) for an effective and robust solution for exploring unknown and indoor environments and reconstructing their maps. We benefit from a Simultaneous Localization and Mapping (SLAM) algorithm for real-time robot localization and mapping. Three different reward functions are compared and tested in different environments with growing complexity. The performances of the three different RL-based path planners are assessed not only on the training environments, but also on an a priori unseen environment to test the generalization properties of the policies. The results indicate that RL-based planners trained to maximize the coverage of the map are able to consistently explore and construct the maps of different indoor environments.

A NOVEL ADAPTIVE NEURO-FUZZY UNSCENTED KALMAN FILTER FOR SLAM

2011 ◽  
Vol 08 (01) ◽  
pp. 223-243 ◽  
Author(s):  
RAMAZAN HAVANGI ◽  
MOHAMMAD TESHNEHLAB ◽  
MOHAMMAD ALI NEKOUI
Keyword(s):  
Kalman Filter ◽  
Fuzzy Inference ◽  
Unscented Kalman Filter ◽  
A Priori ◽  
Inference System ◽  
Localization And Mapping ◽  
Neuro Fuzzy ◽  
Measurement Noise Covariance ◽  
Slam Algorithm ◽  
Sampling Instant

Extended Kalman filter (EKF) has been used as a popular choice to solve simultaneous localization and mapping (SLAM) problem. However, SLAM algorithm based on EKF-SLAM has two serious drawbacks, namely the linear approximation of nonlinear functions and the calculation of Jacobin matrices. For solving these problems, SLAM algorithm based on unscented Kalman filter (UKF-SLAM) has been recently proposed. However, the performance of the UKF-SLAM and thus the quality of the estimation depends on the correct a priori knowledge of process and measurement noise covariance matrices respectively denoted by Qk and Rk. Imprecise knowledge of these statistics can cause significant degradation in performance. This article proposes the development of an adaptive neuro-fuzzy UKF (ANFUKF) for SLAM. The Adaptive neuro-fuzzy attempts to estimate the elements of Rk matrix in the UKF-SLAM algorithm at each sampling instant when measurement updating step is carried out. The adaptive neuro-fuzzy inference system (ANFIS) supervises the performance of the UKF-SLAM with the aim of reducing the mismatch between the theoretical and actual covariance of the innovation sequences. The free parameters of ANFIS are trained using the steepest gradient descent (GD) to minimize the differences of the actual value of the covariance of the residual with its theoretical value as much as possible. The simulation results show the effectiveness of the proposed algorithm.

scholarly journals Evaluation of Bio-inspired SLAM algorithm based on a Heterogeneous System CPU-GPU

2021 ◽  
Vol 229 ◽  
pp. 01023
Author(s):  
Rachid Latif ◽  
Kaoutar Dahmane ◽  
Monir Amraoui ◽  
Amine Saddik ◽  
Abdelouahed Elouardi
Keyword(s):  
Execution Time ◽  
Autonomous Navigation ◽  
Heterogeneous System ◽  
Mobile Robotics ◽  
Simultaneous Localization And Mapping ◽  
Real Problem ◽  
System Type ◽  
Localization And Mapping ◽  
Slam Algorithm

Localization and mapping are a real problem in robotics which has led the robotics community to propose solutions for this problem... Among the competitive axes of mobile robotics there is the autonomous navigation based on simultaneous localization and mapping (SLAM) algorithms: in order to have the capacity to track the localization and the cartography of robots, that give the machines the power to move in an autonomous environment. In this work we propose an implementation of the bio-inspired SLAM algorithm RatSLAM based on a heterogeneous system type CPU-GPU. The evaluation of the algorithm showed that with C/C++ we have an executing time of 170.611 ms with a processing of 5 frames/s and for the implementation on a heterogeneous system we used CUDA as language with an execution time of 160.43 ms.

scholarly journals A SLAM Algorithm Based on Adaptive Cubature Kalman Filter

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Fei Yu ◽  
Qian Sun ◽  
Chongyang Lv ◽  
Yueyang Ben ◽  
Yanwei Fu
Keyword(s):  
Kalman Filter ◽  
A Priori ◽  
Statistical Parameters ◽  
Estimation Errors ◽  
Adaptive Estimator ◽  
Practical Applications ◽  
Localization And Mapping ◽  
Cubature Kalman Filter ◽  
Slam Algorithm ◽  
Noise Statistics

We need to predict mathematical model of the system and a priori knowledge of the noise statistics when traditional simultaneous localization and mapping (SLAM) solutions are used. However, in many practical applications, prior statistics of the noise are unknown or time-varying, which will lead to large estimation errors or even cause divergence. In order to solve the above problem, an innovative cubature Kalman filter-based SLAM (CKF-SLAM) algorithm based on an adaptive cubature Kalman filter (ACKF) was established in this paper. The novel algorithm estimates the statistical parameters of the unknown system noise by introducing the Sage-Husa noise statistic estimator. Combining the advantages of the CKF-SLAM and the adaptive estimator, the new ACKF-SLAM algorithm can reduce the state estimated error significantly and improve the navigation accuracy of the SLAM system effectively. The performance of this new algorithm has been examined through numerical simulations in different scenarios. The results have shown that the position error can be effectively reduced with the new adaptive CKF-SLAM algorithm. Compared with other traditional SLAM methods, the accuracy of the nonlinear SLAM system is significantly improved. It verifies that the proposed ACKF-SLAM algorithm is valid and feasible.

scholarly journals Autonomous Navigation Based on SEIF with Consistency Constraint for C-Ranger AUV

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Yue Shen ◽  
Hao Zhang ◽  
Bo He ◽  
Tianhong Yan ◽  
Yang Liu
Keyword(s):  
Autonomous Navigation ◽  
Large Scale ◽  
Autonomous Underwater Vehicle ◽  
State Model ◽  
State Variables ◽  
Motion Models ◽  
Localization And Mapping ◽  
Consistency Constraint ◽  
Slam Algorithm ◽  
Error State

An autonomous underwater vehicle (AUV) has to solve two essential problems in underwater environment, namely, localization and mapping. SLAM is one novel solution to estimate locations and maps simultaneously based on motion models and sensor measurements. Sparse extended information filter (SEIF) is an effective algorithm to reduce storage and computational costs of large-scale maps in the SLAM problem. However, there exists the inconsistency in the SEIF since the rank of the observability matrix of linearized error-state model in SLAM system is higher than that of the nonlinear SLAM system. By analyzing the consistency of the SEIF-based SLAM from the perspective of observability, a SLAM based on SEIF with consistency constraint (SEIF-CC SLAM) is developed to improve the estimator’s consistency. The proposed algorithm uses the first-ever available estimates to calculate SEIF Jacobians for each of the state variables, called the First Estimates Jacobian (FEJ). Then, the linearized error-state model can keep the same observability as the underlying nonlinear SLAM system. The capability of autonomous navigation with the proposed algorithm is validated through simulations experiments and sea trials for aC-RangerAUV. Experimental results show that the proposed SEIF-CC SLAM algorithm yields more consistent and accurate estimates compared with the SEIF-based SLAM.

Comparison of different SLAM approaches for a driverless race car

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Nick Le Large ◽  
Frank Bieder ◽  
Martin Lauer
Keyword(s):  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Ground Truth ◽  
Time Constraints ◽  
Differential Gps ◽  
Real World Data ◽  
Race Car ◽  
Localization And Mapping ◽  
Slam Algorithm ◽  
Computational Resources

Abstract For the application of an automated, driverless race car, we aim to assure high map and localization quality for successful driving on previously unknown, narrow race tracks. To achieve this goal, it is essential to choose an algorithm that fulfills the requirements in terms of accuracy, computational resources and run time. We propose both a filter-based and a smoothing-based Simultaneous Localization and Mapping (SLAM) algorithm and evaluate them using real-world data collected by a Formula Student Driverless race car. The accuracy is measured by comparing the SLAM-generated map to a ground truth map which was acquired using high-precision Differential GPS (DGPS) measurements. The results of the evaluation show that both algorithms meet required time constraints thanks to a parallelized architecture, with GraphSLAM draining the computational resources much faster than Extended Kalman Filter (EKF) SLAM. However, the analysis of the maps generated by the algorithms shows that GraphSLAM outperforms EKF SLAM in terms of accuracy.

scholarly journals A V-SLAM Guided and Portable System for Photogrammetric Applications

2021 ◽  
Vol 13 (12) ◽  
pp. 2351
Author(s):  
Alessandro Torresani ◽  
Fabio Menna ◽  
Roberto Battisti ◽  
Fabio Remondino
Keyword(s):  
Low Cost ◽  
Cost Effective ◽  
Motion Blur ◽  
Guidance System ◽  
Prototype System ◽  
Active Sensors ◽  
Localization And Mapping ◽  
Acquisition Speed ◽  
Mobile Mapping System ◽  
Slam Algorithm

Mobile and handheld mapping systems are becoming widely used nowadays as fast and cost-effective data acquisition systems for 3D reconstruction purposes. While most of the research and commercial systems are based on active sensors, solutions employing only cameras and photogrammetry are attracting more and more interest due to their significantly minor costs, size and power consumption. In this work we propose an ARM-based, low-cost and lightweight stereo vision mobile mapping system based on a Visual Simultaneous Localization And Mapping (V-SLAM) algorithm. The prototype system, named GuPho (Guided Photogrammetric System) also integrates an in-house guidance system which enables optimized image acquisitions, robust management of the cameras and feedback on positioning and acquisition speed. The presented results show the effectiveness of the developed prototype in mapping large scenarios, enabling motion blur prevention, robust camera exposure control and achieving accurate 3D results.

Autonomous Navigation via Deep Imitation and Transfer Learning: A Comparative Study

2020 ◽  
Author(s):  
Parham M. Kebria ◽  
Abbas Khosravi ◽  
Ibrahim Hossain ◽  
Navid Mohajer ◽  
HM Dipu Kabir ◽  
...  
Keyword(s):  
Comparative Study ◽  
Transfer Learning ◽  
Autonomous Navigation
Sign in / Sign up

Export Citation Format

Share Document