Applied Water Science (2024) 14:151

https://doi.org/10.1007/s13201-024-02183-6

ORIGINAL ARTICLE

Simultaneous localization and mapping (SLAM)‑based robot

localization and navigation algorithm
Junfu Qiao1,2 · Jinqin Guo1,2 · Yongwei Li1,2

Received: 4 January 2024 / Accepted: 16 April 2024

© The Author(s) 2024

Abstract
This research paper presents a comprehensive study of the simultaneous localization and mapping (SLAM) algorithm for
robot localization and navigation in unknown environments. The SLAM algorithm is a widely used approach for building a
map of an environment and estimating the robot’s position within it, which is especially useful in dynamic and unstructured
environments. The paper discusses various SLAM techniques, including the Kalman filter (KF) and GraphSLAM algorithms,
and their use in probabilistic estimation of the robot’s position and orientation. The paper also explores different path-
planning techniques that can be used with the map created by the SLAM algorithm to generate collision-free paths for the
robot to navigate toward its goal. The paper also discusses recent advances in deep learning-based SLAM algorithms and
their applications in indoor navigation with ORB and RGB-D cameras. The research concludes that SLAM-based robot
localization and navigation algorithms are a promising approach for robots navigating in unstructured environments and
present various opportunities for future research.

Keywords SLAM · Kalman filter · Robot

Introduction safely. Localization and mapping are crucial aspects of robot

navigation, allowing robots to understand their surroundings
Robots are becoming an integral part of our daily lives, from and estimate their position accurately. The Simultaneous
autonomous cars to drones and service robots. An intelligent Localization and Mapping (SLAM) algorithm is a popular
robot possesses the ability to plan, organize, and adapt to approach for robot localization and mapping in unknown
complex environments without human intervention (Li environments (Wu et al. 2021).
et al. 2019). In order to achieve autonomous navigation, the Considering enhanced precision and effectiveness,
robot requires a reliable determination of its own position SLAM innovation is now focusing on improving computing
and pose; it functions as a framework for the robot’s effectiveness, data incorporation, as well as looping
surroundings investigation as well as intuitive navigating. completion. Regardless of setbacks in native investigations,
One of the essential requirements for autonomous robots important advances for mapping participation, mapping
is the ability to navigate through an unknown environment development, location, navigating, and additional fields
while avoiding obstacles and reaching their destination have been accomplished. Publications have investigated
SLAM methodology that uses the combination of sound
* Junfu Qiao waves as well as optical knowledge, leading in increased
qiaojunfu@163.com locating as well as mapping precision and resilience. Its
Jinqin Guo inertial navigational system (INS) determines a carrier’s
guojq@tit.edu.cn location by doubling its integration of momentum with
Yongwei Li duration, providing considerable benefits in autonomous
liyongwei27@163.com as well as camouflage. As robotics technology progresses,
so do its algorithmic hardware enhancements, providing
1
Department of Automation, Taiyuan Institute of Technology the groundwork for intelligent internal robot mobility
University, Taiyuan 030008, China
and location (Yu et al. 2019). Nevertheless, technological
2
Intelligent Detection and Control Engineering (Technology) constraints have restricted the broad acceptance of internal
Research Centre, Taiyuan 030008, China

Vol.:(0123456789)
151 Page 2 of 8 Applied Water Science (2024) 14:151

robotics for tracking, routing, and location in new areas. Simultaneous Localization and Mapping (SLAM) is a
Hence, precise real-time posture data are essential for popular technique used in robotics to address the problem
entirely self-sufficient navigating as well as compositions of robot navigation and localization. The technique allows a
in any interior surroundings (Dai 2022). robot to build a map of its environment and simultaneously
SLAM-based robot localization and navigation locate itself within that map, without relying on external
algorithms have been a topic of active research in robotics sensors or prior knowledge of the environment. The SLAM
for several decades, and many techniques and approaches problem is complex, as it requires the robot to integrate
have been proposed and tested in various scenarios. SLAM data from multiple sensors and make inferences about the
algorithms typically consist of two components: mapping environment while simultaneously updating its own position
and localization. The mapping component involves building estimate.
a map of the environment using sensor data, such as laser Research on SLAM-based robot localization and
range finders, cameras, or sonar sensors. The localization navigation algorithms has been an active area of research
component involves estimating the robot’s position in recent years, driven by the increasing demand for
within the mapped environment, often using probabilistic autonomous robots in a wide range of applications such as
techniques such as particle filters. search and rescue, agriculture, and transportation. The key
The SLAM algorithm has been successfully applied objective of this research is to develop algorithms that are
in various scenarios, such as autonomous driving, indoor robust, accurate, and efficient in real-world environments
navigation, and exploration missions. For example, the (Wang et al. 2007).
SLAM algorithm has been used in autonomous vehicles There are several different approaches to SLAM-
for mapping the environment and estimating the vehicle’s based localization and navigation, including graph-based
position and orientation, allowing the vehicle to navigate approaches, filter-based approaches, and particle filters.
safely and reach its destination. Similarly, in indoor Graph-based approaches use graph theory to model the
environments, SLAM-based algorithms have been used environment, while filter-based approaches use Bayesian
for robot navigation, enabling the robot to move through filters to estimate the robot’s position. Particle filters use a
dynamic and unstructured environments, avoiding obstacles particle-based representation of the environment to estimate
and reaching its goal. the robot’s position.
Recent advances in deep learning-based SLAM Recent research has focused on developing SLAM
algorithms have also shown promising results, using neural algorithms that can handle large-scale environments, operate
networks to learn the mapping and localization tasks. For in real-time, and deal with dynamic obstacles. Other areas
example, deep learning-based SLAM algorithms have been of research include exploring the use of machine learning
used in indoor navigation scenarios with RGB-D cameras, techniques to improve SLAM performance and developing
allowing the robot to navigate through an environment with SLAM algorithms that are robust to sensor noise and other
varying lighting conditions (Thrun and Montemerlo 2006). sources of uncertainty.
The aim of this research paper is to present a Current SLAM research focuses on speeding up
comprehensive study of the SLAM algorithm and its computing, improving data linkage, and detecting when
use in robot localization and navigation. This paper will loops occur in data (Kun et al. 2019). Although initial
discuss various SLAM techniques, including the extended exploration in this area was slow, advances were made in
Kalman filter (EKF) and GraphSLAM algorithms, and their mapping, location, and circulation. Some studies combine
applications in probabilistic estimation of the robot’s position sonar and visual information in SLAM, improving the
and orientation. The paper will also explore different path- accuracy of positioning and mapping (Dai 2022). The
planning techniques that can be used with the map created other method, called inertial path, uses speed to determine
by the SLAM algorithm to generate collision-free paths position. This is good because it can work on its own and
for the robot to navigate toward its goal. Additionally, the can be hard to find. As robotic technology evolves, so do
paper will discuss recent advances in deep learning-based the control systems, helping to navigate indoors. However,
SLAM algorithms and their potential applications in robot there are still challenges for indoor mobile robots, such as
navigation. mapping and moving around new areas. Accurate and fast
According to (Thrun and Montemerlo 2006), SLAM is a detection of the robot indoors is essential for unassisted
fundamental problem in robotics, and its solution is essential movement (Alhmiedat et al. 2023).
for robot navigation in unknown environments. This research An important contribution of this research is the detailed
paper aims to contribute to the existing body of research on analysis of simultaneous localization and mapping (SLAM)
SLAM-based robot localization and navigation algorithms, algorithms and their applications in robotic localization and
providing insights into different SLAM techniques and their navigation Traditional methods such as extended Kalman
applications in various scenarios (Wang et al. 2003). filter (EKF) and GraphSLAM, and three days yield advances
Applied Water Science (2024) 14:151 Page 3 of 8 151

such as deep learning-based approaches Discussed; the paper approach has the capability of lowering the impact of
provides valuable insights into how state-of-the-art robotic numerous unknown elements (Liu et al. 2021).
communication technologies. Furthermore, by addressing Despite the challenges, several robots have achieved
the latest challenges and developments in SLAM research, autonomous positioning and navigation using techniques like
the study contributes to the ongoing efforts to improve SLAM, computer vision-based positioning, and Fast SLAM.
the capabilities of autonomous robots in safe and efficient SLAM (simultaneous localization and mapping) technology
navigation in the unknown areas. is widely used to achieve autonomous navigation tasks for
Overall, the research on SLAM-based robot localization robots in unknown environments. For instance, literature
and navigation algorithms is critical for advancing the uses SLAM technology to provide map updates for autos
capabilities of autonomous robots and enabling them to and enable them to navigate freely in any part of the world
operate in a wide range of environments and applications. in a comparable vein, the research investigates SLAM in
interior spaces using laser extending and a monocular sight
to perform navigational autonomy missions for robotics (Li
Literature review et al. 2019).
A different strategy utilized for robotic positioning as well
Robot navigation and positioning are a critical task that as localization was rapid SLAM. The method above creates
involves identifying the robot’s location and determining mappings and determines the robotic position by using
its movement in a given environment. For precise robotic recursion heuristics to figure out the robotic position as
exploration as well as location, many methods have been well as generate the whole probabilistic pattern of mapping
implemented, notably optical exploration as well as location, indications. An optimized reprocessing approach is proposed
electromagnetism guidance as well as location, GPS throughout the scientific community to drive sub-plasmas
worldwide location, as well as light-reflecting exploration into outstanding particulates, conserving the population’s
along with tracking. These strategies make use of several variety as well as decreasing deterioration (Wang et al.
detectors to assist robotics in correctly navigating various 2019).
settings. A different approach prominent option includes
Recent research has proposed several algorithms to computational vision-based orientation gadgets, which
achieve high-precision robot navigation and positioning. employ frame rates recorded through a camera to determine
One such algorithm is the square-root unscented KF the machine’s stance. This approach extracts pointed features
(Kalman filter) proposed in literature (Wang et al. 2003). as well as characteristics from every image framework
The above method broadens the limited spectrum of the using detector computations, whereby both the translating
UKF (unmanned Kalman filtering) as well as was applicable and rotational matrices across the component’s position
to Gauss regression algorithms. The unmanned particulate framework as well as, the camera’s orientation framework
filtering method merges standard UKF using a novel may be produced. Lastly, the objective’s area can be
hotspot technique termed Particulate Filtering to generate identified using a specialized procedure by considering the
a higher accuracy unmanned particulate filtering technique. pertinent connection across the locations of all those points
Furthermore, this study indicates that UKF be used to solve of interest and characteristics throughout the picture.
the positioning issue related to nonlinear transitions (Wen Robot navigation and positioning is a challenging task
et al. 2019). that requires the use of different sensors and algorithms
A different strategy employed in robotic localized to achieve high-precision localization and navigation.
includes particulate filtering when coupled using the Techniques like SLAM, computer vision-based positioning,
machine’s odometer as well as detector models. The and Fast SLAM have enabled robots to navigate
likelihood is given through the dispersed particulate group autonomously in unknown environments, providing a
dispersion under the aforementioned method, along with promising future for robotics (Dai 2022).
the location as well as the distribution of barriers can be The researchers developed a navigation system based on
estimated using the probabilistic densities. Over several SLAM. This system allows robots to locate and move around
rounds, the location dispersion was properly estimated. The large indoor spaces. Using SLAM techniques, social robots
samples procedure has been optimized according to previous can explore unfamiliar indoor environments, mapping on
research by minimizing the variety of computational the go and tracking their location (Alhmiedat et al. 2023).
samplings followed by presenting a Monte Carlo technique Many SLAM algorithms share similar steps in their
utilizing the Gauss mixing concept. The existing research design. Each time the robot takes a step, it gathers data
suggests that the particulate filtering technique be improved from its onboard sensors and extracts features from that data.
by merging the fuzzier connect mechanism and the These objects are compared with objects previously detected
particulate filtering reprocessing procedure. The above by the robot, which are stored in its internal map. To improve
151 Page 4 of 8 Applied Water Science (2024) 14:151

this matching process, the robot uses its predicted position with logarithmic processing needs. (Jeong and Lee 2005)
from the previous step. Once the connections between the created a comparable informational filtering however, failed
objects are identified, they are integrated with the map, to clarify exactly what landmark-landmark data linkages
fixing the location of the objects with the current location of are discovered. This technique was subsequently improved
the robot and in addition adding new, undiscovered objects by Leonard and Newman across an effective aligning
to the map based on the estimated current location robot. methodology, which had been executed and applied for an
This iterative process is continuous, helping the robot to automated submarine transport employing artificial-aperture
localize and simulate its surroundings at the same time acoustic. The SLAM probability is represented in a sparse
(Yarovoi and Cho 2024). hierarchy using the lightweight intersection determine
approach (Chen, 2021), as well as, (Wang et al., 2019)
created an analogous tree construction of that data matrices
Case study—different techniques for effective assessment. Covariance techniques intersecting
and algorithms is a customizable approach that has been employed on
NASA’s MARS Rovers flotilla. This SEIF method, invented
Graph SLAM by (Thrun and Montemerlo 2006), has been demonstrated to
have been sufficiently rapid to operate live on tiny data sets.
It has already been various efforts over the past few decades Neither of those methods, nevertheless, addressed
focused on recording actual landscapes utilizing movable whether to integrate sporadic GPS readings inside SLAM.
sensory systems. These comprises traditional cartography Figure 1 depicts the GraphSLAM method, wherein presents
through the air, on land, and the oceans. Indoor, outside, an illustration with quad-labeled robotic postures ­(x1,…,x4)
as well as underground habitats are all included comprise along with pair mapping characteristics (­m1, ­m2). The
this cartography. Numerous purposes drove the gathering graphical representation has a couple of kinds of edges:
of those charts, including artistic visualization, monitoring, mobility arcs, which connect successive robotics positions,
academic evaluation, as well as robotics navigation. The and measured arcs, which correlate attitudes to attributes
fundamental research on this topic has come from several that were recently detected there. Each boundary is an
scientific areas such as photography, artificial intelligence, unconventional restriction that corresponds to the evaluation
graphic design, and automation attributed to the diversified along with kinematic modeling’ negative logarithmic
aims. probability. These constitute data restrictions that would
The concept behind GraphSLAM is straightforward: it be rapidly applied to graphs without needing considerable
uses a sparse graph to represent soft constraints derived from processing. As shown in the first illustration, the total
data and then, resolves these constraints into a consistent amount of all restrictions resulted in a nonlinear minimum
global estimate of the map and robot path. Although the squares issue (Thrun and Montemerlo 2006).
constraints are generally nonlinear, they are linearized during GraphSLAM streamlines a collection of restrictions
resolution and then solved using standard optimization for calculating the mapping lateral, culminating in small
techniques. GraphSLAM provides an approach that involves data matrices as well as a metadata vector. Because the
building minimal graphs of asymmetric requirements as matrices are sparse, GraphSLAM may utilize the parameter
well as populating minimal “knowledge” matrices of linear reduction approach to turn the network toward a simpler
requirements. This is capable of handling an extensive one specified roughly by robotic postures. The trajectory of
amount of characteristics and incorporates GPS data into the probability mapping is then computed using traditional
big-scale modeling issues. Information acquired via a robotic
device intended to build 3D renderings of towns and cities
was used to evaluate the algorithms. Despite it has not yet
been released in its present state, GraphSLAM bases itself
on Lu and Milios’ foundational method since 1997 as well
as is strongly connected to Folkesson and Christensen’s work
on Pictorial SLAM. Considering hierarchies of restraints is
important when considering the whole SLAM study subject
matter, the abbreviation GraphSLAM proposed (Thrun and
Montemerlo 2006).
Graph-based representations have been used in SLAM
filtering algorithms as well. In 1997, Csorba created a
knowledge filtering that kept comparative data among a trio
comprising three attractions, paving the path for techniques Fig. 1  Graph SLAM
Applied Water Science (2024) 14:151 Page 5 of 8 151

inference strategies. GraphSLAM determines borderline

posteriors covering the representation as well; however, the
full mapping anterior is seldom retrieved simply because of
its quad dimension.

Robotics positioning as well as navigating method

utilizing SLAM

Kalman filtering‑based attitude fusion (AF) algorithm

ORB-SLAM provides a flexible SLAM technology that

offers monocular, binocular, as well as RGB-D modalities
with may be utilized across a variety of situations
including massive amounts and tiny-scale, both inside
and out. It employs a multiple thread strategy, identical to
the conventional PTAM technique, to divide monitoring,
regional visualization, and looping identification across
triple threads that are running resulting in improved
effectiveness as well as productivity (Yang et al., 2022).
Our close-looping recognition process begins by Fig. 2  AF-based vision inertial flowchart
contrasting the present frame to all images within the list
of prospective closed-loop pictures as well as rating them vision-related movement prediction method. The principal
according to the procedure’s parameters. When the outcome detector for this regard is known as the Visual-Inertia (VI-)
reaches a certain level, the closure of the framework is Sensor, which provides completely validated as well as
achieved, as well as the back-office optimizing process starts. duration-synchronized IMU as well as stereoscopic digicam
The following precedes with the continuous rectification information streams. Its approach’s key processors are
of phase, which involves halting the regional mapped depicted in Fig. 3 (Perez-Grau et al. 2016).
threading as well as, adjusting the international package to The stereoscopic duo has been subjected to visual
complete the closed-off from lamination as well as critical deformation reduction for every framework, after which
mapping optimization. a collection of relevant spots is determined across both
The updated ORB-SLAM method utilizing an RGB-D the right, and left pictures. Those attention spots are
protocol includes key features including real-time mapping produced by employing the characteristics through
construction, 3D packed pointless mapping creation, loosely expedited segmentation testing (FAST) method, which
coupled orientation prediction with IMU, map storing recognizes angles quickly. However, there are instances
including studying, including perceptual repositioning where the scene may be highly uniform, or a large number of
following map overflowing. features may be clustered in a specific area of the image with
The visual SLAM procedure gives six axes of autonomy intense details, which can result in inaccurate measurements
(placement and orientation) data about a machine at any during subsequent stages of the algorithm. In order to fix
point via its vision detector. Nevertheless, the device has this challenge, just a small amount of characteristics must
inadequate operating frequencies, is sensitive to sunlight, as be taken out of evenly split sections within a picture, often
well as rapidly loses objects, leading to a large inclination attached into containers. Furthermore, a certain amount
inaccuracy. IMU offers a better periodicity as well as of characteristics should be chosen from every container
precision of orientation computation over visual SLAM, depending upon the FAST sensor description in order to
although it may produce positioning inaccuracy as time select just the greatest resilient elements. The amalgamation
passes. The optical gyroscope navigational orientation fusing of these two factors allows for a fair allocation among
estimate technique built around KF has been explained in the strongest picked characteristics across both photos.
depth during the following part, as illustrated in Fig. 2. Our technique involves categorizing the picture into 6
containers (dual rows and triple columns). Figure 4 depicts
Visual odometry‑based robot localization an illustration of the previously identified characteristics and
the traits generated through the bucketing approach (Rosten
To provide an accurate remedy for the geolocation issue, and Drummond 2006).
the robot’s movement must be estimated. This part To overcome the task of localizing the challenge, the
emphasizes the construction for a stereoscopic camera-based rotation of the robot must be accurately approximated. It
151 Page 6 of 8 Applied Water Science (2024) 14:151

Fig. 3  Primary processing

models of vision odometry
algorithm

Fig. 4  Vision odometry feature

detection

is possible thanks to a vision-related tracking system that descriptor, considered highly efficient and successful for
employs dual cameras as well as a VI Detector. Employing component monitoring over modest visual impairments, is
the characteristics from the faster segmentation testing subsequently employed to find conversations among each
(FAST) technique, the procedure begins by collecting set of characteristics. A rigorous matcher can be utilized for
the points of interest across the left as well as the right rejecting asymmetrical similarities and to decrease
pictures of the stereoscopic duo. The photograph is combining possibilities by utilizing epiploic geometries. To
partitioned divided six containers to prevent erroneous discover an assortment of additional strong characteristics,
evaluations, as well as the smallest and greatest range of bilateral component pairing develops throughout subsequent
variables are retrieved from every container. The Bilateral pictures. The EPnP methodology is subsequently employed
Reinforced Independence Elemental Features (BRIEF) to address a Perspective-n-Point (PnP) issue to calculate the
Applied Water Science (2024) 14:151 Page 7 of 8 151

posture difference across the two pictures. To reduce the optimization issues, one for each feature. Appropriate
impact of accumulated mistakes in odometers, a key-framing maps may be constructed in situations with 108 varieties
strategy is used. Depending on the included IMU knowledge, or more characteristics repeatedly via the linearization as
that odometer subsystem calculates the image sensor’s well as optimization approach. This strategy builds on a long
rollover and rotation vantage points, which are merged with heritage of disconnected SLAM computations, all of which
the subjective prediction in a loose-coupled way to generate are founded upon the realization that the entire SLAM issue
the latest relevant positioning and alignment evaluations correlates to a sparsely spring-mass mechanism.
when compared to the starting posture (Perez-Grau et al. SLAM-based localization and navigation algorithms
2016). often use a probabilistic framework, such as a Kalman
filter or a particle filter, to estimate the robot’s position and
uncertainty. These algorithms are capable of handling noisy
Discussion sensor measurements and can update the robot’s position
estimate in real-time as new sensor measurements are
Simultaneous localization and mapping (SLAM) is a well- acquired.
known problem in robotics, which involves constructing One important aspect of SLAM-based localization and
a map of an unknown environment while simultaneously navigation algorithms is the ability to handle loop closures.
estimating the robot’s position within that environment. The Loop closures occur when the robot revisits a previously
goal of SLAM is to allow a robot to navigate in an unknown visited location, and the algorithm must be able to detect this
environment and accomplish tasks while avoiding obstacles. and update the map and position estimates accordingly. This
SLAM-based localization and navigation algorithms have is a challenging problem, as loop closures may occur under
been widely researched in the field of robotics, and many different lighting and environmental conditions.
different approaches have been proposed. In recent years, deep learning approaches have also
One popular approach to SLAM is the use of visual been applied to SLAM-based localization and navigation
odometry, which estimates the robot’s motion by analyzing algorithms. These approaches use neural networks to learn
the motion of visual features in a sequence of images. features from sensor data and can improve the accuracy and
This approach can be used with a single camera or stereo robustness of the system. However, these approaches require
cameras, and it has been shown to be effective in various large amounts of training data and computational resources,
indoor and outdoor environments. Visual odometry is often which may not be feasible in some applications.
combined with other sensors, such as inertial measurement Finally, SLAM-based localization and navigation
units (IMUs), to improve the accuracy and robustness of algorithms are an active area of research in robotics, with
the system. many different approaches proposed. These algorithms
Another popular approach is to use laser range finders or have the potential to enable robots to navigate in unknown
3D cameras to construct a map of the environment and then, environments and perform complex tasks, and advances in
use that map to estimate the robot’s position. This approach this field are likely to have significant impacts on robotics
is known as mapping-based localization. It has been shown and related fields.
to be effective in environments where visual odometry is
not reliable, such as in low-light conditions or environments
with few distinctive visual features.
One of the best algorithms to reduce navigation problem Conclusion
id GraphSLAM. GraphSLAM was an approach that tackles
the off-line issue associated with SLAM by gathering every SLAM-based robot localization and navigation algorithms
bit of information while mapping as well as translating are critical in enabling autonomous robots to navigate and
it onto an outline once the machine’s activity is finished. map unknown environments in real-time. The algorithms are
GraphSLAM does that by first mapping the input onto designed to process sensor data and determine the robot’s
a dense chart of restrictions followed by linearizing it position and orientation in real-time, allowing it to avoid
utilizing the Taylor extension to get a knowledge format obstacles, plan optimal paths, and accomplish complex
description. Accurate translations are used to simplify tasks.
the consequent informative structure, thus eliminating the The research on SLAM-based algorithms has shown that
location parameters that constitute the optimization issue. there are various approaches to solving the localization and
After then, a common optimization approach, including a navigation problem, each with its strengths and limitations.
conjugate curve, is used to resolve the optimization issue. Some of the commonly used techniques include visual
GraphSLAM reconstructs the visualization utilizing the SLAM, graph-based SLAM, and particle filters. Visual
posture estimate by solving a series of small-scale business SLAM, in particular, has gained significant attention in
 151 Page 8 of 8 Applied Water Science (2024) 14:151

recent years due to advancements in computer vision and source, provide a link to the Creative Commons licence, and indicate
machine learning. if changes were made. The images or other third party material in this
article are included in the article's Creative Commons licence, unless
Overall, SLAM-based algorithms have demonstrated indicated otherwise in a credit line to the material. If material is not
impressive results in real-world applications, such as included in the article's Creative Commons licence and your intended
autonomous vehicles, drones, and mobile robots. However, use is not permitted by statutory regulation or exceeds the permitted
there is still much research to be done in developing more use, you will need to obtain permission directly from the copyright
holder. To view a copy of this licence, visit http://​creat​iveco​mmons.​
accurate and robust algorithms that can handle complex org/​licen​ses/​by/4.​0/.
environments and large-scale maps. Additionally, there
is a need to optimize the computational efficiency of the
algorithms to enable real-time operation on low-power References
devices.
The research on SLAM-based robot localization and Alhmiedat T, Marei AM, Messoudi W, Albelwi S, Bushnag A, Bassfar
navigation algorithms is an active field with significant Z, Alnajjar F, Elfaki AO (2023) A SLAM-based localization
potential for real-world applications. Continued research and and navigation system for social robots: the pepper robot case.
Machines 11(2):158. https://​doi.​org/​10.​3390/​machi​nes11​020158
development of these algorithms will enable the creation Chen S, Zhou B, Jiang C, Xue W, Li Q (2021) A LiDAR/Visual SLAM
of more capable and intelligent robots that can operate Backend with Loop Closure Detection and Graph Optimization.
autonomously in a variety of environments. Remote Sens 13:2720
While SLAM provides a comprehensive overview Dai Y (2022) Research on robot positioning and navigation algorithm
based on SLAM. Wirel Commun Mob Comput. https://​doi.​org/​
of algorithms and their applications, it is important to 10.​1155/​2022/​33405​29
acknowledge a few limitations. First, the paper mainly Kun F, Ma L, Sun Y (2019) Navigation of substation inspection robot
focuses on existing methods and their applications, which based on laser sensor. Sens Microsyst 38(2):118–120
can look at emerging methods or new methods that can lead Li J, Li Z, Feng Y, Liu Y, Shi G (2019) Development of a human–robot
hybrid intelligent system based on brain teleoperation and deep
to new developments in robotic navigation. Furthermore, learning SLAM. IEEE Trans Autom Sci Eng 16(4):1664–1674
the discussion mainly revolves around on technical aspects. Liu Y, Sun R, Zhang X, Li L, Shi G (2021) An autonomous positioning
Few studies have potential challenges associated with method for fire robots with multi-source sensors. Wireless Netw.
Future research could address these limitations by exploring https://​doi.​org/​10.​1007/​s11276-​021-​02566-6
Thrun S, Montemerlo M (2006) The graph SLAM algorithm with
alternative SLAM methods beyond the traditional systems, applications to large-scale mapping of urban structures. Int J
while considering the wide range of navigation system, it is Robot Res 25(5–6):403–429
independent in terms of security, privacy, and social impact Wang CC, Thorpe C, Hebert M, Thrun S, Durrant-Whyte H (2007)
as well, and there is a need for research to investigate how Simultaneous localization, mapping and moving object tracking.
Int J Robot Res 26(9):889–916
SLAM technology and other emerging technologies such Wang CC, Thorpe C, Thrun S (2003) Online simultaneous localization
as artificial intelligence, edge computing, and Internet and mapping with detection and tracking of moving objects:
of Things (IoT) are used for navigation complex and theory and results from a ground vehicle in crowded urban areas.
flexible systems that can operate in a variety of dynamic In: IEEE international conference on robotics and automation
(Cat. No. 03CH37422). IEEE, pp 842–849
environments. Furthermore, strategies for enhancing the Wen Y, Hu J, Pagilla PR (2019) A novel robotic system for finishing of
SLAM algorithm, real-time performance, and robustness freeform surfaces. In 2019 International Conference on Robotics
can significantly improve the reliability and robustness and Automation (ICRA). IEEE, pp 5571–5577
of autonomous robot navigation systems in real-world Wu H, Chen Y, Qin H (2021) MPC based trajectory tracking for an
automonous deep-sea tracked mining vehicle. ASP Trans Internet
situations. Things 1(2):1–13
Yang S, Zhao C, Wu Z, Wang Y, Wang G, Li D (2022) Visual SLAM
Acknowledgements .This study was supported by the Basic based on semantic Segmentation and geometric constraints for
Research Program of Shanxi province (free exploration type) (No. dynamic indoor environments. IEEE Access 10:69636–69649
202203021212335), the Scientific and Technologial Innovation Yarovoi A, Cho YK (2024) Review of simultaneous localization and
Programs of Higher Education Institutions in Shanxi (2019L0920), and mapping (SLAM) for construction robotics applications. Autom
Taiyuan Academician Work station Building Unit: Taiyuan Institute of Constr 162:105344
Technology (TYSYSGZZ201903). Yu N, Zhai Y, Yuan Y, Wang Z (2019) A bionic robot navigation
algorithm based on cognitive mechanism of hippocampus. IEEE
Declarations Trans Autom Sci Eng 16(4):1640–1652

Conflict of interest There is no conflict of interest among authors. Publisher’s Note Springer Nature remains neutral with regard to
jurisdictional claims in published maps and institutional affiliations.
Open Access This article is licensed under a Creative Commons
Attribution 4.0 International License, which permits use, sharing,
adaptation, distribution and reproduction in any medium or format,
as long as you give appropriate credit to the original author(s) and the