Problem In Robotics Research Articles

Research on autonomous mobile robot maze navigation problem based on Dijkstras algorithm

In recent years, the field of autonomous mobile robotics has garnered significant attention due to its potential applications in various domains such as logistics, surveillance, and search and rescue operations. A crucial challenge in this area is the efficient navigation of robots within complex and dynamic environments, particularly when navigating through maze-like structures. The maze navigation problem involves finding optimal paths for robots to traverse from their initial positions to designated destinations while avoiding obstacles and making intelligent decisions to ensure timely and safe navigation. This study aims to investigate and apply Dijkstras algorithm to solve the maze navigation problem for autonomous mobile robots. By analyzing the navigation challenges faced by autonomous mobile robots in maze environments, a solution based on Dijkstras algorithm is proposed. In conclusion, this study contributes to the field of autonomous mobile robotics by proposing and evaluating the application of Dijkstras algorithm for maze navigation. The experimental results validate its potential to address the challenges of navigating intricate maze environments. However, it is acknowledged that further refinement and innovation are possible to continue improving the performance of autonomous mobile robots in maze navigation scenarios.

Navigation Path Following Platform for a Greenhouse Shuttle Robot Using the State-flow Method

Localization is an important method for autonomous indoor robots to recognize their positions. Generally, the navigation of a mobile robot is conducted using a camera, Lidar, and global positioning system. However, for an indoor environment, GPS is unavailable. Therefore, a, state-trajectory tracking method is utilized based on a Lidar map. This paper presents the path following of an autonomous indoor mobile robot, that is, a shuttle robot, using a state-flow method via a robot operating system network. MATLAB and Linux high-level computers and an inertial measurement unit sensor are used to obtain the Cartesian coordinate information of a bicycle-type mobile robot. The path following problem can be solved in the state-flow block by setting appropriate time and linear and angular velocity variables. After the predetermined time, the linear and angular velocities are set based on the length of the path and radius of the quarter-circle of the left and right turns in the state-flow block, path planning, which can execute the work effectively, is established using the state-flow algorithm. The state-flow block produces time-series data that are sent to Linux system, which facilitates real-time mobile platform path following scenario. Several cases within the path-following problem of the mobile robot were considered, depending on the linear and angular velocity settings: the mobile robot moved forward and backward, turned in the right and left directions on the circular path. The effectiveness of the method was demonstrated using the desktop-based indoor mobile robot control results. Thus, the paper focuses on the application of the state-flow algorithm to the shuttle robot specifically in the narrow indoor environment.

A Multi-strategy Enhanced Arithmetic Optimization Algorithm and Its Application in Path Planning of Mobile Robots

A multi-strategy enhanced arithmetic optimization algorithm called MSEAOA is proposed to address the issues of low population diversity, imbalanced exploration and exploitation capabilities, and low accuracy of optimal solution in the Arithmetic Optimization Algorithm. Firstly, using the good point set strategy for population initialization to improve population diversity and thus accelerate convergence speed. Secondly, we integrate the exploration and exploition capabilities of differential self-learning strategy, best example learning strategy, and second-order differential perturbation strategy balancing algorithm. Finally, the introduction of somersault foraging strategy improves the accuracy of the optimal solution. We select 14 classical benchmark test functions and the CEC2019 function test set to test the optimization ability of MSEAOA, and apply MSEAOA to the path planning problem of mobile robots. MSEAOA is compared with other meta-heuristic optimization algorithms, and the experimental results are statistically analyzed by the Wilcoxon rank-sum test. The simulation experimental results show that MSEAOA performs the best among 14 benchmark functions, but for 10 CEC2019 functions, MSEAOA has the best optimization performance among 5 of them (50%). In the path optimization problem of mobile robots, the path obtained by MSEAOA is also the best among all algorithms, its path shortening rate exceeds 8.8% in 83% of environments. The results indicate that MSEAOA is a reliable algorithm suitable for function optimization and practical optimization problems.

Vision-Based Adaptive Trajectory Tracking Control of Wheeled Mobile Robot With Unknown Translational External Parameters

In this article, the vision-based trajectory tracking control problem of wheeled mobile robot is addressed, and different from the traditional vision-based adaptive control methods, the case that the camera is not installed in the center of the mobile robot is considered. In this case, the visual model needs to consider the influence of unknown translational external parameters. To solve this problem, a novel adaptive vision-based trajectory tracking control method is proposed, and a two-stage switching trajectory tracking control law is designed, where the adaptive control method is used to compensate the unknown external parameters. The asymptotic convergence of tracking errors are strictly proved by applying the Lyapunov method. Simulation and experimental results show that proposed approach can effectively control the mobile robot to track the desired trajectory in the presence of unknown external translational parameters.

Research on performance comparison of patrol path planning techniques for mobile robots in nuclear power plants

Path planning, as a basic problem of mobile robots, is important in the application of industrial patrol robots. This paper takes the nuclear power plant as an example and solves the problem of multi-target patrol path of patrol robot. Firstly, this paper processes multi-target points applying Euler's formula to obtain a reasonable order of patrol target points. Then three path planning algorithms, A* algorithm based on graph search, RRT* algorithm based on sampling and Q-learning algorithm based on reinforcement learning, are applied on path planning, and combined with Minimal-Jerk algorithm for optimizing trajectories. The performance of the results is finally compared using two evaluation metrics. The acceleration variance and route analysis in planar images are used as evaluation metrics in this paper. It is considered that the smaller the acceleration variance, the more smoothly the robot can move. The gentler the route is, the more effective the robot movement is.

Path Planning of Obstacle-Crossing Robot Based on Golden Sine Grey Wolf Optimizer

This paper proposes a golden sine grey wolf optimizer (GSGWO) that can be adapted to the obstacle-crossing function to solve the path planning problem of obstacle-crossable robot. GSGWO has been improved from the gray wolf optimizer (GWO), which provide slow convergence speed and easy to fall into local optimum, especially without obstacle-crossing function. Firstly, aiming at the defects of GWO, the chaotic map is introduced to enrich the initial population and improve the convergence factor curve. Then, the convergence strategy of the golden sine optimizer is introduced to improve the shortcomings of GWO, such as insufficient convergence speed in the later stage and the ease with which it falls into the local optimum. Finally, by adjusting the working environment model, path generation method and fitness function, the path-planning problem of the obstacle-crossing robot is adapted. In order to verify the feasibility of the algorithm, four standard test functions and three different scale environment models are selected for simulation experiments. The results show that in the performance test of the algorithm, the GSGWO has higher convergence speed and accuracy than the GWO under different test functions. In the path-planning experiment, the length, number and size of inflection points and stability of the path planned by the GSGWO are better than those of the GWO. The feasibility of the GSGWO is verified.

A Vision Dynamics Learning Approach to Robotic Navigation in Unstructured Environments

Autonomous legged navigation in unstructured environments is still an open problem which requires the ability of an intelligent agent to detect and react to potential obstacles found in its area. These obstacles may range from vehicles, pedestrians, or immovable objects in a structured environment, like in highway or city navigation, to unpredictable static and dynamic obstacles in the case of navigating in an unstructured environment, such as a forest road. The latter scenario is usually more difficult to handle, due to the higher unpredictability. In this paper, we propose a vision dynamics approach to the path planning and navigation problem for a quadruped robot, which navigates in an unstructured environment, more specifically on a forest road. Our vision dynamics approach is based on a recurrent neural network that uses an RGB-D sensor as its source of data, constructing sequences of previous depth sensor observations and predicting future observations over a finite time span. We compare our approach with other state-of-the-art methods in obstacle-driven path planning algorithms and perform ablation studies to analyze the impact of architectural changes to our model components, demonstrating that our approach achieves superior performance in terms of successfully generating collision-free trajectories for the intelligent agent.

An efficient reinforcement learning scheme for the confinement escape problem

Crucial real-world problems in robotics like trajectory planning during convoy missions and autonomous rescue missions can be framed as a confinement escape problem (CEP) (a type of pursuit-evasion game). In a typical CEP, an evader attempts to escape a confinement region by sequentially making decisions to plan an escape while the region is patrolled by multiple smart pursuers. The evader has a limited sensing range and does not know the total number of pursuers and their pursuit strategies making it difficult to model the environment and obtain a generalizable escape strategy. In this paper, the CEP is formulated in a reinforcement learning (RL) framework to overcome the above difficulties. The state function is designed independent of the total number of pursuers and the shape of the confinement region thereby making the RL approach scalable. To handle training consistency issues in deep RL and convergence issues due to sparse rewards, a Scaffolding Reflection based Reinforcement Learning (SR2L) approach is presented in this paper where the SR2L employs an actor–critic method with a motion planner scaffold to accelerate its training speed. Performance evaluation of SR2L shows that it trains twice as fast compared to other existing state-of-the-art actor–critic RL methods. Performance results show that the convergence of SR2L is more consistent than the corresponding conventional actor–critic RL methods and interactive reinforcement learning methods. Monte-Carlo simulation results show that SR2L outperforms other conventional RL methods and the motion planner with at least 28% and 10% faster escape times respectively while having the lowest variance in escape times against different pursuit strategies. Ablation studies done by changing different environmental parameters clearly show the scalability and generalizability of the proposed SR2L approach.

Kinematics inverse solution of assembly robot based on improved particle swarm optimization

AbstractInverse kinematics of robot is the basis of robot assembly, which directly determines the pose of robot. Because the traditional inverse solution algorithm is limited by the robot topology structure, singular pose and inverse solution accuracy, it affects the use of robots. In order to solve the above problems, an improved particle swarm optimization (PSO) algorithm is proposed to solve the inverse problem of robot. This algorithm initializes the particle population based on joint angle limitations, accelerating the convergence speed of the algorithm. In order to avoid falling into local optima and premature convergence, we have proposed a nonlinear weight strategy to update the speed and position of particles, enhancing the algorithm’s search ability, in addition introducing a penalty function to eliminate particles exceeding joint limits. Finally, the positions of common points and singular points are selected on PUMA 560 robot and redundant robot for inverse kinematics simulation verification. The results show that, compared with other algorithms, the improved PSO algorithm has higher convergence accuracy and better convergence speed in solving the inverse solution, and the algorithm has certain universality, which provides a new solution for the inverse kinematics solution of the assembly robot.

Increasing the Robustness of Deep Learning Models for Object Segmentation: A Framework for Blending Automatically Annotated Real and Synthetic Data.

Recent problems in robotics can sometimes only be tackled using machine learning technologies, particularly those that utilize deep learning (DL) with transfer learning. Transfer learning takes advantage of pretrained models, which are later fine-tuned using smaller task-specific datasets. The fine-tuned models must be robust against changes in environmental factors such as illumination since, often, there is no guarantee for them to be constant. Although synthetic data for pretraining has been shown to enhance DL model generalization, there is limited research on its application for fine-tuning. One limiting factor is that the generation and annotation of synthetic datasets can be cumbersome and impractical for the purpose of fine-tuning. To address this issue, we propose two methods for automatically generating annotated image datasets for object segmentation, one for real-world and another for synthetic images. We also introduce a novel domain adaptation approach called filling the reality gap (FTRG), which can blend elements from real-world and synthetic scenes in a single image to achieve domain adaptation. We demonstrate through experimentation on a representative robot application that FTRG outperforms other domain adaptation techniques, such as domain randomization or photorealistic synthetic images, in creating robust models. Furthermore, we evaluate the benefits of using synthetic data for fine-tuning in transfer learning and continual learning with experience replay using our proposed methods and FTRG. Our findings indicate that fine-tuning with synthetic data can produce superior results compared to solely using real-world data.

On Semidefinite Relaxations for Matrix-Weighted State-Estimation Problems in Robotics

On Semidefinite Relaxations for Matrix-Weighted State-Estimation Problems in Robotics

A novel parallel ant colony optimization algorithm for mobile robot path planning.

With the continuous development of mobile robot technology, its application fields are becoming increasingly widespread, and path planning is one of the most important topics in the field of mobile robot research. This paper focused on the study of the path planning problem for mobile robots in a complex environment based on the ant colony optimization (ACO) algorithm. In order to solve the problems of local optimum, susceptibility to deadlocks, and low search efficiency in the traditional ACO algorithm, a novel parallel ACO (PACO) algorithm was proposed. The algorithm constructed a rank-based pheromone updating method to balance exploration space and convergence speed and introduced a hybrid strategy of continuing to work and killing directly to address the problem of deadlocks. Furthermore, in order to efficiently realize the path planning in complex environments, the algorithm first found a better location for decomposing the original problem into two subproblems and then solved them using a parallel programming method-single program multiple data (SPMD)-in MATLAB. In different grid map environments, simulation experiments were carried out. The experimental results showed that on grid maps with scales of 20 $ \times $ 20, 30 $ \times $ 30, and 40 $ \times $ 40 compared to nonparallel ACO algorithms, the proposed PACO algorithm had less loss of solution accuracy but reduced the average total time by 50.71, 46.83 and 46.03%, respectively, demonstrating good solution performance.

Real-time Trajectory Planning and Tracking Control of Bionic Underwater Robot in Dynamic Environment.

In this article, we study the trajectory planning and tracking control of a bionic underwater robot under multiple dynamic obstacles. We first introduce the design of the bionic leopard cabinet underwater robot developed in our lab. Then, we model the trajectory planning problem of the bionic underwater robot by combining its dynamics and physical constraints. Furthermore, we conduct global trajectory planning for bionic underwater robots based on the temporal-spatial Bezier curves. In addition, based on the improved proximal policy optimization, local dynamic obstacle avoidance trajectory replanning is carried out. In addition, we design the fuzzy proportional-integral-derivative controller for tracking control of the planned trajectory. Finally, the effectiveness of the real-time trajectory planning and tracking control method is verified by comparative simulation in dynamic environment and semiphysical simulation of UWSim. Among them, the real-time trajectory planning method has advantages in trajectory length, trajectory smoothness, and planning time. The error of trajectory tracking control method is controlled around 0.2 m.

Swarm Robotics in a Sustainable Warehouse Automation: Opportunities, Challenges and Solutions

The Over 90% of the jobs in the logistics industry between 2010 and 2014 came from freight transport and storage services, according to statistics from the Census and Statistics Department. With the advent of Industry 4.0 and its associated emerging technologies (such as cloud computing, Internet of Things, autonomous robots, etc.), a smart robotic warehouse management system is recommended. These innovations transform picking and put-away procedures in warehouses by enabling autonomous mobile robots to transition from man-to-goods to goods-to-man. A group of robots collaborate to solve problems in swarm robotics by putting together practical structures and behaviours that are similar to those found in flocks of birds, schools of fish, or swarms of bees. However, the transition to industrial applications has not yet been completed to a satisfactory level. There is a dearth of knowledge in the literature regarding real-world swarm applications that make use of swarm algorithms. Typically, swarm algorithm components—or what we call basic swarm behaviours —are used. This paper therefore discusses the opportunities available for this technology as well as the challenges that may come with their use. Finally, some possible solutions have been proposed to help tackle the identified challenges in sustainable warehouse automation.

Global Consensus-Based Formation Control of Nonholonomic Mobile Robots With Time-Varying Delays and Without Velocity Measurements

We propose a solution to the full consensus-based formation problem for torque-controlled nonholonomic mobile robots under time-varying communication delays and without velocity measurements. Under the assumptions of static and undirected communication topologies, and smooth and bounded delays, we propose a distributed smooth, time-varying control law which achieves the goal of acquiring a global formation pattern in a common consensus point for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">both</i> position and orientation. The controller is a combination of a simple Proportional-Plus-Damping scheme and a simple globally exponentially convergent velocity observer. Consensus is reached independently of all initial conditions. Realistic simulations in the Gazebo-ROS environment illustrate the effectiveness of the proposed algorithm and the robustness with respect to measurement noise, non-smooth delays and uncertain dynamics.

Combining closed-form and numerical solutions for the inverse kinematics of six-degrees-of-freedom collaborative handling robot

In the process of solving the inverse kinematics of six-degrees-of-freedom collaborative robots, the numerical solution has problems such as low accuracy and singular configurations. Moreover, due to the high coupling of its position and attitude, the direct closed-form solution fails. To address these problems, an inverse kinematics algorithm that combines closed-form and numerical solutions was proposed. The Jacobian matrix was established based on the forward kinematics equation of the six-degrees-of-freedom collaborative robot. Its inverse matrix was obtained by a singular value decomposition of the matrix using the Manocha elimination method to avoid the singularities of the Jacobian matrix. The optimal inverse kinematics solution was obtained using the Newton–Raphson iterative method. A computer simulation implemented in MATLAB and Visual C++ was used to evaluate the accuracy and speed of the proposed algorithm. The results of the trajectory planning experiments demonstrate that the algorithm satisfies the requirements for real-time smooth motion. This study of inverse kinematics lays the theoretical foundation for solutions to the inverse problem and real-time control of collaborative robots.

DLOAM: Real-time and Robust LiDAR SLAM System Based on CNN in Dynamic Urban Environments

Dynamic object detection, state estimation, and map-building are crucial for autonomous robot systems and intelligent transportation applications in urban scenarios. Most current LiDAR Simultaneous Localization and Mapping (SLAM) systems operate on the assumption that the observed environment is static. However, the overall accuracy and robustness of a SLAM system can be compromised by dynamic objects in the environment. Aiming at the problem of inaccurate odometry estimation and wrong mapping caused by the existing LiDAR SLAM method which cannot detect the dynamic objects, we study the SLAM problem of robots and unmanned vehicles equipped with LiDAR traveling in the dynamic urban scenes. We propose a fast LiDAR-only model-free dynamic objects detection method, which uses the spatial and temporal information of point cloud through a convolutional neural network (CNN), and the detection accuracy is improved by 35 use spatial information. We further integrate it into a state-of-the-art LiDAR SLAM framework to improve the SLAM performance. Firstly, the range image constructed by LiDAR point cloud is used for ground extraction and non-ground point clustering. Then, the motion of objects in the scene is estimated by the difference between adjacent frames, and the segmented objects are further divided into dynamic objects and static objects by their motion features. After that, the stable feature points are extracted from the static objects. Finally, the pose transformation of adjacent frames is solved by matching feature point pairs. We evaluated the accuracy and robustness of our system on datasets with different challenging dynamic environments, and the results show our system has significant improvements in accuracy and robustness of odometry and mapping, while still maintain real-time performance, which is sufficient for autonomous robot systems and intelligent transportation applications in urban scenarios.

Hippocampal formation-inspired global self-localization: quick recovery from the kidnapped robot problem from an egocentric perspective.

It remains difficult for mobile robots to continue accurate self-localization when they are suddenly teleported to a location that is different from their beliefs during navigation. Incorporating insights from neuroscience into developing a spatial cognition model for mobile robots may make it possible to acquire the ability to respond appropriately to changing situations, similar to living organisms. Recent neuroscience research has shown that during teleportation in rat navigation, neural populations of place cells in the cornu ammonis-3 region of the hippocampus, which are sparse representations of each other, switch discretely. In this study, we construct a spatial cognition model using brain reference architecture-driven development, a method for developing brain-inspired software that is functionally and structurally consistent with the brain. The spatial cognition model was realized by integrating the recurrent state-space model, a world model, with Monte Carlo localization to infer allocentric self-positions within the framework of neuro-symbol emergence in the robotics toolkit. The spatial cognition model, which models the cornu ammonis-1 and -3 regions with each latent variable, demonstrated improved self-localization performance of mobile robots during teleportation in a simulation environment. Moreover, it was confirmed that sparse neural activity could be obtained for the latent variables corresponding to cornu ammonis-3. These results suggest that spatial cognition models incorporating neuroscience insights can contribute to improving the self-localization technology for mobile robots. The project website is https://nakashimatakeshi.github.io/HF-IGL/.

Humanoid Motion Control using Auto Resonance Neural Network

It has been proven difficult to control robots with many mechanical joints due to a variety of problems, including redundant configurations, non-linear displacement, dynamic user surroundings, etc. Iterative computations have been applied to address inverse kinematic problems of industrial robots with up to six Degrees of Freedom (DoF). With one to three degrees of freedom in each of more than hundred joints used by humans for locomotion, the complexity is unfathomable. Consequently, in humanoid structures, algorithmic and heuristic approaches have failed. Numerous research fields that were earlier thought to be challenging to solve with computers have seen interest piqued by recent advancements in artificial intelligence and machine learning. One such domain is humanoid motion. This paper presents a novel kind of Artificial Neural Network named as Auto Resonance Neural Network (ARN). ARN uses the pull-relax mechanism applied by biological systems to control musculoskeletal motion. A variety of functions can be employed to build the pull-relax model, contingent on variables such as range, necessary coverage, and tunability. When employing ARN for joint control, inverse kinematics or some other kind of repetitive solution is not required. Its application is not influenced by the DoF or joint count. The network can use the learning methods like reinforcement learning or supervised or unsupervised learning.

Design and Implementation of a Model Predictive Formation Tracking Control System for Underwater Multiple Small Spherical Robots

Due to the characteristics of good concealment ability and strong mobility, multiple, small spherical underwater robot formations play an important role in near coast defense missions, such as cruising, reconnaissance, surveillance, and sensitive target capturing. Referring to the formation problem for underwater small spherical robots with limited energy, perception, and computation abilities, a trajectory tracking-based formation strategy that transforms the complex formation tracking problem into a simple trajectory tracking problem of a single robot is provided. Two layers are designed in the formation tracking strategy. The upper layer is a virtual structure-based formation algorithm. The bottom layer is a tracking controller based on model predictive control (MPC). The formation algorithm is in charge of calculating reference trajectory for each robot in the formation according to the global formation path. The MPC-based dynamic controller for each robot is designed to track the self reference trajectory. Compared with the model predictive control method used for the traditional trajectory tracking problem of a single robot, this paper additionally considers the formation constraints and the internal collision avoidance. In addition, the extended state observer (ESO) is utilized to estimate the lumped disturbance composed of environment disturbance and the inaccurate dynamic model of a small spherical robot. Not only are the numerical simulations based on MATLAB v.2015a, but physical simulations based on self-building multi-spherical robot formation platform are also carried out. Furthermore, through using two small spherical robots, a formation tracing experiment is conducted. All of the results prove that the proposed formation method is feasible and practical for small spherical robots.