Robot Navigation Algorithm Research Articles

Mobile robot navigation based on intrinsic reward mechanism with TD3 algorithm

Deep reinforcement learning methods have been applied to mobile robot navigation to find the optimal path to the target. The rewards are usually given when the task is completed, which may lead to the local optima during the training procedure. It seriously affects the training efficiency and navigation performance of the mobile robot. To this end, this paper proposes an intrinsic reward mechanism with intrinsic curiosity module and randomness enhanced module, combining the TD3 (twin-delayed deep deterministic policy gradient) reinforcement learning algorithm for mobile robot navigation. It effectively resolves the issue of slow convergence caused by sparse rewards in continuous action spaces. It also encourages mobile robots to explore unknown areas and reduces the occurrence of local optima. The experimental results show that the proposed navigation method significantly improves the training efficiency of mobile robots. Out of 1000 test episodes, only 3 exceeded the maximum step limit. This approach significantly reduces the occurrence of local optima. Furthermore, it increases the success rate to an impressive 83.5%, outperforms the existing navigation methods.

A hybrid sampling-based RRT* path planning algorithm for autonomous mobile robot navigation

The path-planning algorithms for autonomous mobile robot navigation are crucial, often relying on sampling-based methods. RRT* is a robust, sampling-based path planning algorithm. The sampling process in RRT* plays a pivotal role, where uniform sampling can lead to slow convergence, while non-uniform sampling offers faster convergence but may struggle in complex environments due to its limited exploration. Thus, achieving a balance between exploitation and exploration is essential when selecting the sampling method for the RRT* path-planning algorithm. To address this issue, this research paper introduces Hybrid-RRT*, a path planning method that utilizes hybrid sampling. This unique approach generates samples using both non-uniform and uniform samplers. Hybrid-RRT* is evaluated against three baseline path planning algorithms—RRT*-N, Informed RRT*, and RRT*—across three different 384x384 2D simulation environments. Compared to these baseline methods, Hybrid-RRT* achieves superior results across all five performance metrics: convergence rate, success rate, number of nodes visited, path length, and planning time. According to the numerical results, the proposed algorithm achieves a faster average convergence rate that is 76.14% higher than RRT*, 24% higher than Informed RRT*, and 3.33% higher than RRT*-N. Moreover, it reduces node exploration by an average of 48.53% compared to RRT* and 40.83% compared to Informed RRT*. The simulation results demonstrate that the proposed Hybrid-RRT* algorithm effectively addresses the issue of slow convergence with uniform sampling and the challenge of limited exploration with non-uniform sampling methods.

Simultaneous localization and mapping (SLAM)-based robot localization and navigation algorithm

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.

Indoor Quadruped Robot Navigation Algorithm Based on ORB-SLAM

In recent years, the development of artificial intelligence, big data, and the Internet of Things technologies has revealed unprecedented potential and value in mobile robots across various sectors of automation and intelligence. Among these, quadruped robots have shown unique applications in the domain of indoor security and inspection, as they can navigate multi-storey buildings by ascending and descending stairs. To enhance the stability of visual navigation in indoor inspection environments for quadruped robots, this paper builds on the ORB-SLAM framework. It introduces the AGC algorithm to address the issue of reduced feature point extraction during night patrols, thereby increasing the number of feature points extracted. Additionally, to tackle the problem of high oscillation intensity during the movement of quadruped robots, the EKF algorithm has been incorporated for sensor fusion with IMU, enhancing the robustness of visual navigation. This has been validated through physical experiments.

Review Paper: Key Points on Robot Navigation and Its Practical Uses in the Field of Manufacturing

Key aspects are covered in this review article, along with a brief explanation of mobile robot navigation and its uses in the industrial sector. This study emphasizes the significance of robot navigation in enhancing productivity, efficiency, and safety in manufacturing processes by compiling important ideas from the body of research and literature. This study investigates several robot navigation algorithms and strategies, from simple algorithms to sophisticated ones like SLAM (Simultaneous Localization and Mapping). This study also examines particular issues and concerns about the application of robot navigation systems in industrial settings, such as path planning, obstacle avoidance, and worker cooperation. This paper presents some noted applications of robot navigation, such as material handling, assembly, quality control, and logistics, using case studies and examples. The conversation also touches on new developments and prospective paths for robot navigation technology, highlighting the possibility for more innovation and connection with Industry 4.0 projects. All things considered, this review article is an invaluable tool for scholars, practitioners, and business experts who want to comprehend the function of robot navigation in contemporary manufacturing processes and how it will affect industrial automation in the future.

Bi-directional adaptive enhanced A* algorithm for mobile robot navigation

PurposeThe present paper aims to address challenges associated with path planning and obstacle avoidance in mobile robotics. It introduces a pioneering solution called the Bi-directional Adaptive Enhanced A* (BAEA*) algorithm, which uses a new bidirectional search strategy. This approach facilitates simultaneous exploration from both the starting and target nodes and improves the efficiency and effectiveness of the algorithm in navigation environments. By using the heuristic knowledge A*, the algorithm avoids unproductive blind exploration, helps to obtain more efficient data for identifying optimal solutions. The simulation results demonstrate the superior performance of the BAEA* algorithm in achieving rapid convergence towards an optimal action strategy compared to existing methods.Design/methodology/approachThe paper adopts a careful design focusing on the development and evaluation of the BAEA* for mobile robot path planning, based on the reference [18]. The algorithm has remarkable adaptability to dynamically changing environments and ensures robust navigation in the context of environmental changes. Its scale further enhances its applicability in large and complex environments, which means it has flexibility for various practical applications. The rigorous evaluation of our proposed BAEA* algorithm with the Bidirectional adaptive A* (BAA*) algorithm [18] in five different environments demonstrates the superiority of the BAEA* algorithm. The BAEA* algorithm consistently outperforms BAA*, demonstrating its ability to plan shorter and more stable paths and achieve higher success rates in all environments.FindingsThe paper adopts a careful design focusing on the development and evaluation of the BAEA* for mobile robot path planning, based on the reference [18]. The algorithm has remarkable adaptability to dynamically changing environments and ensures robust navigation in the context of environmental changes. Its scale further enhances its applicability in large and complex environments, which means it has flexibility for various practical applications. The rigorous evaluation of our proposed BAEA* algorithm with the Bi-directional adaptive A* (BAA*) algorithm [18] in five different environments demonstrates the superiority of the BAEA* algorithm.Research limitations/implicationsThe rigorous evaluation of our proposed BAEA* algorithm with the BAA* algorithm [18] in five different environments demonstrates the superiority of the BAEA* algorithm. The BAEA* algorithm consistently outperforms BAA*, demonstrating its ability to plan shorter and more stable paths and achieve higher success rates in all environments.Originality/valueThe originality of this paper lies in the introduction of the bidirectional adaptive enhancing A* algorithm (BAEA*) as a novel solution for path planning for mobile robots. This algorithm is characterized by its unique characteristics that distinguish it from others in this field. First, BAEA* uses a unique bidirectional search strategy, allowing to explore the same path from both the initial node and the target node. This approach significantly improves efficiency by quickly converging to the best paths and using A* heuristic knowledge. In particular, the algorithm shows remarkable capabilities to quickly recognize shorter and more stable paths while ensuring higher success rates, which is an important feature for time-sensitive applications. In addition, BAEA* shows adaptability and robustness in dynamically changing environments, not only avoiding obstacles but also respecting various constraints, ensuring safe path selection. Its scale further increases its versatility by seamlessly applying it to extensive and complex environments, making it a versatile solution for a wide range of practical applications. The rigorous assessment against established algorithms such as BAA* consistently shows the superior performance of BAEA* in planning shorter paths, achieving higher success rates in different environments and cementing its importance in complex and challenging environments. This originality marks BAEA* as a pioneering contribution, increasing the efficiency, adaptability and applicability of mobile robot path planning methods.

A comprehensive review of bug algorithms in path planning

The bug algorithm family is the well-known navigation algorithm for robots in unknown environments. However, different types of bug algorithms have their own priorities and weaknesses based on different environmental conditions. According to the characteristics of the bug navigation algorithms, the bug algorithm family is mainly divided into 4 parts. In this paper, four types of bug algorithms (original bug algorithm, M-line Bug, Angel Bug and Range Bug) are presented along with typical samples of each type. Each type of algorithm will be thoroughly explained and exemplified, highlighting its unique characteristics and the suitable environmental conditions for each algorithm. By presenting the basic logic behind each algorithm and examining the environmental conditions they are best suited for, this paper aims to provide researchers with a comprehensive understanding of the bug algorithm family. Ultimately, this knowledge will contribute to the advancement of navigation capabilities in robots operating in unknown and challenging environments.

Autonomous navigation of mobile robots in unknown environments using off-policy reinforcement learning with curriculum learning

Reinforcement learning (RL) is effective for autonomous navigation tasks without prior knowledge of the environment. However, traditional mobile robot navigation algorithms, based on off-policy RL, often face challenges such as low sample efficiency during training and lack of adequate safety mechanisms. In this paper, we present an off-policy RL navigation model named Soft Actor-Critic with Curriculum Prioritization and Fuzzy Logic (SCF). The model uses energy as a prioritized evaluation metric for experience replay. And through task-level curriculum, the agent’s learning sequence is formulated, thereby enhancing sampling efficiency and safety. We propose a Curriculum-based Energy Prioritization (CEP) approach. It selects a replay trajectory that matches the current agent’s capability based on trajectory energy. Our results show that robots using off-policy RL often have limitations in dynamic obstacle avoidance. To rectify this, our model uses a fuzzy logic controller to enhance real-time obstacle avoidance. The SCF approach enables mobile robots to navigate adeptly in unpredictable and dynamic environments, ensuring optimal planning control while being safe and robust. Experiments in Gazebo simulation environment and real world confirm the effectiveness of our proposed method. The comparison results show the superior performance of this method, especially in unknown and dynamic environments.

Novel Fuzzy Reinforcement Algorithm for Mobile Robot Navigation in Automated Storage

Novel Fuzzy Reinforcement Algorithm for Mobile Robot Navigation in Automated Storage

Human-Aware Trajectory Optimization for Enhancing D* Algorithm for Autonomous Robot Navigation (May 2024)

Human-Aware Trajectory Optimization for Enhancing D* Algorithm for Autonomous Robot Navigation (May 2024)

Obstacle Avoidance Learning for Robot Motion Planning in Human–Robot Integration Environments

In the human-robot integration environment, it is essential for mobile robots to pass through the crowd and complete the navigation task smoothly. However, the current mainstream robot navigation algorithms only treat pedestrians as dynamic obstacles and passively avoid pedestrians in local planning. When encountering fast-moving pedestrians, local path planning often fails, causing the robot to stagnate, spin or shake in place, which in turn reduces the navigation efficiency and results in unnatural navigation trajectories. To address this problem, it is desirable for the robot to find a safe and convenient temporary target to avoid the collision with fast-moving pedestrians. In this paper, we propose an obstacle avoidance learning method with the temporary target for the robot motion planning in the human-robot integration environment. The temporary target distribution is learned from imitations by using a Conditional Variational Autoencoder (CVAE) framework, whereby the dynamic scenario information including pedestrian information, the environmental information, and the robot information are considered as the generation conditions. With the proposed method, the mobile robot first navigates to the temporary target area, and then plans the path toward the final target point. Experimental studies reveal that the proposed method can achieve satisfactory performance with respect to different scenario conditions.

Research on hybrid navigation algorithm and multi-objective cooperative planning method for electric inspection robot

For mobile robots working in the power inspection environment, navigation algorithms and collaborative path planning are the keys to understanding and reproducing human power inspection’s thinking mode. Firstly, the paper proposed a hybrid navigation algorithm of reflector and laser based on the generalized inverse of the least squares solution. Secondly, to solve the problem of multi-robot inspection cooperative path planning, the traffic rule reservation table generated a dynamic weighted map representing traffic congestion in power inspection to prevent multi-robot collision. Thirdly, through the distributed control method, the robot used the dynamic weighted map to improve the RRT (Rapidly-Exploring Random Trees)algorithm to achieve the purpose of active cooperative path planning, reducing the trajectory’s critical path points and solving the cooperative congestion. Finally, the positioning and calibration compensation can be carried out through the experiment by the reflector navigation algorithm in a large-scale complex environment. Comparing the path planning methods of the A* algorithm and the dynamic weighted RRT algorithm, the dynamic weighted RRT algorithm reduces the number of extended nodes. It solves the multi-robot planning collision problem while ensuring the search path’s completeness. Meanwhile, the dynamic weighted RRT algorithm can save the running time of the multi-robot system and effectively improve the efficiency of the power inspection system.

Research on dynamic path planning method of electric inspection robot based on fuzzy neural network

In order to better address the issue of the coverage rate about power inspection robot to the working area, solving the difficulties in the navigation modeling and path planning of the intelligent control program is the focus of this paper. This paper first analyzes a multi-information fusion SLAM robot positioning and navigation algorithm, then uses the Kalman filter technology to locate through Voronoi mapping. Second, this paper proposes a five-layer neural network approach to how robots can plan and control routes in high-density scenarios. Third, the robot takes the surrounding obstacle distance, the target angle and the target distance as input parameters then the output parameters of the fuzzy neural network are the wheel speed and the steering angle. The inspection robot uses the sensors on the body to detect the surrounding environment’s parameter information. The dynamic path planning algorithm changes the path accordingly, prevents collision, and finally reaches the preset target. Finally, the paper collects the features obtained by Voronoi mapping in a large-scale simulation environment. The fuzzy neural network algorithm for detecting robots is validated in a complex environment, proving the effectiveness and accuracy of the algorithm.

Sequential batch fusion magnetic anomaly navigation for a low-cost indoor mobile robot

This paper describes a new magnetic map-matching algorithm structure based on sequential batch fusion. The proposed algorithm enables real-time computation and more stable indoor localization of mobile robots. Conventional magnetic map-matching-based localization has the disadvantage that real-time navigation is not possible when using a batch process, and navigation fails or has significant localization errors owing to similar magnetic field distortion. This study proposes that measurement updates should be performed based on the convergence of weights with several grid points by repeatedly updating the weights of the grid points using magnetic field similarity. The performance of the proposed navigation algorithm was verified using an open dataset, and the proposed technique had a position error of 1 m even in a path in which navigation using the conventional method failed. It provides an indoor mobile robot navigation algorithm that is significantly cheaper than other conventional sensor-based indoor navigation systems.

Energy Consumption Analysis of the Selected Navigation Algorithms for Wheeled Mobile Robots

The article presents the research on navigation algorithms of a wheeled mobile robot with the use of a vision mapping system and the analysis of energy consumption of selected navigation algorithms, such as RRT and A-star. Obstacle maps were made with the use of an RGBW camera, and binary occupation maps were also made, which were used to determine the traffic path. To recreate the routes in hardware, a programmed Pure Pursuit controller was used. The results of navigation were compared on the basis of the forward kinematics model and odometry measurements. Quantities such as current, except (x, y, phi), and linear and angular velocities were measured in real time. As a result of the conducted research, it was found that the RRT star algorithm consumes the least energy to reach the designated target in the designated environment.

Surveillance task optimized by Evolutionary shared Tabu Inverted Ant Cellular Automata Model for swarm robotics navigation control

Swarm robotics is an area of research that has attracted several researchers. This field is part of the collective robotics approach that is inspired by the self-organized behaviors of social animals. From interactions between agents, guided by simple rules, it is possible to design emerging collective behaviors capable of performing complex tasks in an organized manner, for the coordination and control of a large number of robots. In this article, we proposed a new model that combines different techniques of natural and evolutionary computing: we mainly focus on ideas and concepts about cellular automata, social pedestrians behavior in evacuation, genetic algorithms, inverted pheromone from ant colonies and Tabu search, as hybrid search mechanism. The objective of this new model is to provide an advance of surrogate techniques for swarm robotics as a field of science and engineering and that may be relevant to deal with the robotic surveillance task. The new model is called Genetic Shared Tabu Inverted Ant Cellular Automata, or shortly GSTIACA. Initially, it was made a meta-optimization of the surrogate parameters through a genetic algorithm. Then, we apply these new parameters for hundreds steps in a robot control and navigation algorithm based on cellular automata techniques in different environments types. The system global search takes place at different times, one of which is based on the spread of pheromone in the environment and the other which is based on the memory sharing based on Tabu search. The novelty of this work is precisely the Tabu search application as a local and used as a shared global search algorithm. Besides that, we developed a new algorithm for swarm robotics that integrates different artificial intelligence techniques and natural computing not yet used all together in precursor works. In addition, we reduced the cost of processing the pheromone decline calculation using an asynchronous cellular-automaton. Later, we contrasted the new model in different situations, and saw that the new algorithm proposed here is better than its precursors. Finally, we did a test using the e-Puck architecture within the Webots simulation environment to prove that the mathematical model proposed herein is capable of being applied in the real world application.

Agoraphilic Navigation Algorithm Under Dynamic Environment

This article presents a summary of the work done on the development of a new algorithm for mobile robot navigation in unknown dynamic environment. The developed humanlike algorithm uses a free-space attraction (Agoraphilic) concept for robot navigation. The algorithm presented in this article is an advanced development of the Agoraphilic navigation algorithm. The Agoraphilic algorithm does not look for obstacles (problems) to avoid but rather for free spaces toward the goal (solutions) to follow. The original Agoraphilic while it was able to overcome the limitations of the traditional algorithms had its own limitations in navigating robots in environments cluttered with moving obstacles. The new Agoraphilic Navigation Algorithm under Dynamic Environment (ANADE) was developed to overcome those limitations. ANADE consists of seven main modules reported in this article. The objects tracking and objects prediction methodologies developed for the algorithm estimate future growing free-space passages toward the goal. The algorithm generates a time-varying single attractive force to pull the robot through the free space toward the predicted (future) growing free-space passages leading to the goal. The new algorithm was tested, not only through simulation, but also through experimental work. Summary of the experimental results is presented and discussed in this article.

Implementation of Robotic Navigation Algorithms Using Partial Reconfiguration on Zynq SoC

The purpose for this research work is to design a heterogeneous method for adaptive, task-based computer hardware reconfiguration for adaptive mobile robotic applications. The proposed method uses the dynamic reconfiguration technique to modify the navigation system to meet the requirements of various navigation algorithms for accomplishing an assigned task. In this work, we have proposed an efficient architecture that satisfies the requirements with adequate hardware and software resources by dynamically reconfiguring the system. The ability to change resources allows robots to collaborate more easily, to enhance performance and fault tolerance. The method is endorsed with case studies in which a multiple mobile robots are loaded with bitfile and their behaviors are dynamically modified during runtime. This paper also proposes the hardware implementation of navigation algorithms on Zynq SoC, XC7Z020CLG484-1, using Xilinx Vivado 2017.3 to simulate and synthesize the design. Verilog is a real-time hardware description language, which is used to deploy multiple robots. Software Development Kit (SDK) is used to facilitate the generation of integrated software applications for Xilinx embedded processors. One of the important aspects of this work is adopting an FPGA-based robot in service-based applications for assisting humans in their daily lives.

Online learning for orientation estimation during translation in an insect ring attractor network

Insect neural systems are a promising source of inspiration for new navigation algorithms, especially on low size, weight, and power platforms. There have been unprecedented recent neuroscience breakthroughs with Drosophila in behavioral and neural imaging experiments as well as the mapping of detailed connectivity of neural structures. General mechanisms for learning orientation in the central complex (CX) of Drosophila have been investigated previously; however, it is unclear how these underlying mechanisms extend to cases where there is translation through an environment (beyond only rotation), which is critical for navigation in robotic systems. Here, we develop a CX neural connectivity-constrained model that performs sensor fusion, as well as unsupervised learning of visual features for path integration; we demonstrate the viability of this circuit for use in robotic systems in simulated and physical environments. Furthermore, we propose a theoretical understanding of how distributed online unsupervised network weight modification can be leveraged for learning in a trajectory through an environment by minimizing orientation estimation error. Overall, our results may enable a new class of CX-derived low power robotic navigation algorithms and lead to testable predictions to inform future neuroscience experiments.

Research on Robot Positioning and Navigation Algorithm Based on SLAM

In the industrial field, industrial robots have taken over the heavy lifting that used to be done by traditional handicraft assembly lines, greatly freeing up human resources and improving production efficiency and safety. As a result, the focus of this paper is on the SLAM-based robot localization and navigation algorithm (simultaneous localization and mapping). An attitude estimation algorithm based on KF (Kalman filtering) information fusion of vision SLAM and IMU (Inertial Measurement Unit) is proposed, and the ORB-SLAM algorithm is studied and perfected. The fusion of the two postures improves the accuracy and frequency of the robot’s attitude estimation during motion. In addition, PSO (Particle Swarm Optimization) technology is used to optimize the resampling process, and PSO optimizes the particle set to alleviate the problem of particle degradation and exhaustion caused by resampling in the FastSLAM algorithm. Finally, the algorithm is verified to meet the requirements of positioning and composition accuracy, as well as the feasibility and effectiveness of robot autonomous navigation, using the open simulation platform.