Robot Navigation Algorithm Research Articles

Prediction-Based Path Planning with Obstacle Avoidance in Dynamic Target Environment

In this paper, a new algorithm for mobile robot navigation and polygonal obstacles avoidance in dynamic target environment is introduced. In the dynamic target path planning theagent (robot) trying to reach a moving target in minimum pathcost. The introduced algorithm which called Prediction-basedpath planning with obstacle avoidance in dynamic target environment planning a path to a moving target by predicting the nexttarget location, then computing a path from the robot current location to the predicted target location representing each visibleobstacle by the smallest circle that enclosing the polygon obstacle,then determine the visible tangents between the robot and the circular obstacle that intersect its shortest path and compute theshortest path. Three target movement scenarios were suggestedand tested in different environment conditions. The results showthat the target was reached in all scenarios and under all environment conditions with good path cost.

New algorithm for behaviour-based mobile robot navigation in cluttered environment using neural network architecture

Purpose This study concerns an on-line path planning technique for a behaviour-based wheeled mobile robot local navigation in an unknown environment with hurdles, using the feedforward back-propagation neural network sensor-actuator control technique. The purpose of this study is to find the non-collision path for the mobile robot moving towards the goal in a cluttered environment. Design/methodology/approach Neural network architecture input layers are the different hurdle distance information, which are acquired by an array of equipped sensors, and the output layer is the turning angle (motor control). In this way, the mobile robot is effectively being trained to move autonomously in the environment. Findings Computer simulation and real-time experimental results show that the proposed neural network controller can improve navigation performance in cluttered and unknown environments. Originality/value The proposed neural network controller gives better results (in terms of path length) as compared to previously developed models, which verifies the effectiveness of the proposed architecture.

Hebbian Plasticity Realigns Grid Cell Activity with External Sensory Cues in Continuous Attractor Models.

After the discovery of grid cells, which are an essential component to understand how the mammalian brain encodes spatial information, three main classes of computational models were proposed in order to explain their working principles. Amongst them, the one based on continuous attractor networks (CAN), is promising in terms of biological plausibility and suitable for robotic applications. However, in its current formulation, it is unable to reproduce important electrophysiological findings and cannot be used to perform path integration for long periods of time. In fact, in absence of an appropriate resetting mechanism, the accumulation of errors over time due to the noise intrinsic in velocity estimation and neural computation prevents CAN models to reproduce stable spatial grid patterns. In this paper, we propose an extension of the CAN model using Hebbian plasticity to anchor grid cell activity to environmental landmarks. To validate our approach we used as input to the neural simulations both artificial data and real data recorded from a robotic setup. The additional neural mechanism can not only anchor grid patterns to external sensory cues but also recall grid patterns generated in previously explored environments. These results might be instrumental for next generation bio-inspired robotic navigation algorithms that take advantage of neural computation in order to cope with complex and dynamic environments.

An Evolutionary Algorithm for Autonomous Robot Navigation

This paper presents an implementation of an evolutionary algorithm to control a robot with autonomous navigation in avoiding obstacles. The paper describes how the evolutionary system controls the sensors and motors in order to complete this task. A simulator was developed to test the algorithm and its configurations. The tests were performed in a simulated environment containing a set of barriers that were observed by means of a set of sensors. The solution obtained in the simulator was embedded in a real robot, which was tested in an arena containing obstacles. The robot was able to navigate and avoid the obstacles in this environment.

Harmonic Potential Function Based Algorithm for Autonomous Mobile Robot Navigation

Harmonic Potential Function Based Algorithm for Autonomous Mobile Robot Navigation

Bio-inspired homogeneous multi-scale place recognition

Robotic mapping and localization systems typically operate at either one fixed spatial scale, or over two, combining a local metric map and a global topological map. In contrast, recent high profile discoveries in neuroscience have indicated that animals such as rodents navigate the world using multiple parallel maps, with each map encoding the world at a specific spatial scale. While a number of theoretical-only investigations have hypothesized several possible benefits of such a multi-scale mapping system, no one has comprehensively investigated the potential mapping and place recognition performance benefits for navigating robots in large real world environments, especially using more than two homogeneous map scales. In this paper we present a biologically-inspired multi-scale mapping system mimicking the rodent multi-scale map. Unlike hybrid metric-topological multi-scale robot mapping systems, this new system is homogeneous, distinguishable only by scale, like rodent neural maps. We present methods for training each network to learn and recognize places at a specific spatial scale, and techniques for combining the output from each of these parallel networks. This approach differs from traditional probabilistic robotic methods, where place recognition spatial specificity is passively driven by models of sensor uncertainty. Instead we intentionally create parallel learning systems that learn associations between sensory input and the environment at different spatial scales. We also conduct a systematic series of experiments and parameter studies that determine the effect on performance of using different neural map scaling ratios and different numbers of discrete map scales. The results demonstrate that a multi-scale approach universally improves place recognition performance and is capable of producing better than state of the art performance compared to existing robotic navigation algorithms. We analyze the results and discuss the implications with respect to several recent discoveries and theories regarding how multi-scale neural maps are learnt and used in the mammalian brain.

A modified neuro-evolutionary algorithm for mobile robot navigation: Using fuzzy systems and combination of artificial neural networks

In this paper, an efficient, novel neuro-evolutionary algorithm to navigate a mobile robot in partially visible envi- ronments is introduced. The main disadvantage of Neuro-Evolutionary algorithm is the slow perception and low efficiency in complex environments which is required to be developed. This research is aimed to speed up the iteration and improve the per- formance in complicated ambient. In the typical neuro-evolutionary algorithm, random values are employed either in weights initialization of neural networks or during the training phase. To do so, this research employed a novel method in which robot navigation will be done by using selected values by 3 neural networks rather than one which improve the performance of learning procedure. Another novel method used in this article is replacing the neural networks which are responsible for obstacle avoid- ance by fuzzy algorithm. It will be shown that fuzzy logic is an easy way to put some initial knowledge in the neuro-evolution algorithm to avoid learning from zero. The results clearly demonstrate that the training algorithm approaches the optimum values with the least iterations which not only reduce the required time for reaching the target but also materialize the obstacle avoidance aim.

An Artificial Potential Field Based Mobile Robot Navigation Method To Prevent From Deadlock

Abstract Artificial Potential Filed (APF) is the most well-known method that is used in mobile robot path planning, however, the shortcoming is that the local minima. To overcome this issue, we present a deadlock free APF based path planning algorithm for mobile robot navigation. The Proposed-APF (P-APF) algorithm searches the goal point in unknown 2D environments. This method is capable of escaping from deadlock and non-reachability problems of mobile robot navigation. In this method, the effective front-face obstacle information associated with the velocity direction is used to modify the Traditional APF (T-APF) algorithm. This modification solves the deadlock problem that the T-APF algorithm often converges to local minima. The proposed algorithm is explained in details and to show the effectiveness of the proposed approach, the simulation experiments were carried out in the MATLAB environment. Furthermore, the numerical analysis of the proposed approach is given to prove a deadlock free motion of the mobile robot.

Autonomous Mobile Robot Navigation Using Harmonic Potential Field

Mobile robot navigation has been an area of robotics which has gained massive attention among the researchers of robotics community. Path planning and obstacle avoidance are the key aspects of mobile robot navigation. This paper presents harmonic potential field based navigation algorithm for mobile robots. Harmonic potential field method overcomes the issue of local minima which was a major bottleneck in the case of artificial potential field method. The harmonic potential field is calculated using harmonic functions and Dirichlet boundary conditions are used for the obstacles, goal and initial position. The simulation results shows that the proposed method is able to overcome the local minima issue and navigate successfully from initial position to the goal without colliding into obstacles in static environment.

A globally converging algorithm for reactive robot navigation among moving and deforming obstacles

We present a reactive strategy for the navigation of a mobile robot in dynamic a priori unknown environments densely cluttered with moving and deforming obstacles. Mathematically rigorous analysis of this law with the proof of its global convergence is provided; its performance is confirmed by computer simulations.

Comments on Automatic Visual Bag-of-Words for Online Robot Navigation and Mapping

The paper Automatic visual bag-of-words for online robot navigation and mapping by T. Nicosevici and R. Garcia ( IEEE Trans. Robot. , vol. 28, no. 4, pp. 886898, Aug. 2012) proposed an algorithm for robot navigation and mapping. In this paper, we correct some errors in their analysis.

Simple Image Processing Algorithms for Robot Navigation in Unknown Environment

This article deals with simple image processing algorithms which are used for navigation of the robot in unknown environment. In the beginning of the article image processing procedures used in these algorithms are defined. The transformation of coordinate system of camera to robot’s coordinate system is introduced. The main body of the article consists of the definition of L-K optical flow method used in proposed visual odometry system. Article also contains the parameter settings of the used methods. Emphasis in these algorithms has been placed on simplicity and speed, so that they can be carried out in real-time. Algorithms have been verified on several scenarios.

A Comparative Study: Modified Particle Swarm Optimization and Modified Genetic Algorithm for Global Mobile Robot Navigation

In this paper, Modified Genetic Algorithm (MGA*) and Modified Particle Swarm Optimization (MPSO* ) are developed to increase the capability of the optimization algorithms for a global path planning which means that environment models have been known already. The proposed algorithms read the map of the environment which expressed by grid model and then creates an optimal or near optimal collision free path. The effectiveness of these optimization algorithms for mobile robot path planning is demonstrated by simulation studies. This paper investigates the application of efficient optimization algorithms, MGA* and MPSO* to the problem of mobile robot navigation. Despite the fact that Genetic Algorithm (GA) has rapid search and high search quality, infeasible paths and high computational cost problems are exist associated with this algorithm. To address these problems, the MGA* is presented. Adaptive population size without selection and mutation operators are used in the proposed algorithm. In this thesis, Distinguish Algorithm (DA) is used to check the paths, whether the path is feasible or not, in order to come out with all feasible paths in the population. Improvements presented in MPSO* are mainly trying to address the problem of premature convergence associated with the original PSO. In the MPSO* an error factor is modelled to ensure that the PSO converges. MPSO* try to address another problem which is the population may contain many infeasible paths. A modified procedure is carrying out in the MPSO* to solve the infeasible path problem. According to the simulation done using MATLAB version R2012 (m-file), both algorithms (MGA* and MPSO*) are tested in different environments and the results are compared. The results demonstrate that these two algorithms have a great potential to solve mobile robot path planning with satisfactory results in terms of minimizing distance and execution time. The simulation results illustrate that the path obtained by MGA* is the shortest path, however the execution time based on MPSO* is significantly smaller than the execution time of MGA*. Thus, the proposed MPSO* is computationally faster than the MGA* in finding optimal path. 1 The (*) used to distinguish the proposed modified algorithms (MGA and MPSO) from the previous modified algorithms.

Reactive Robot Navigation Utilizing Nonlinear Control

In this paper, we propose a computationally efficient heuristic solution to choosing a path around obstacles in the face of limited sensor information. Specifically, we propose a navigation algorithm for a mobile robot that reaches a measured target position while avoiding obstacles, making decisions in real-time (without stopping) and relying strictly on information obtained from limited and noisy robot-mounted sensors to determine the location and severity of obstacles. The solution utilizes fuzzy processing to encode the environment – the fuzzy encoding is used both in deciding on an intermediate target direction and in a collision-avoidance strategy. A closed-loop nonlinear feedback control provides a smooth motion with stability guarantees. Simulation results in a corridor environment demonstrate expected collision-free trajectories.

Trend and Bounds for Error Growth in Controlled Lagrangian Particle Tracking

This paper establishes the method of controlled Lagrangian particle tracking (CLPT) to analyze the offsets between physical positions of marine robots in the ocean and simulated positions of controlled particles in an ocean model. The offset, which we term the CLPT error, demonstrates distinguished characteristics not previously seen in drifters and floats that cannot be actively controlled. The CLPT error growth over time is exponential until it reaches a turning point that only depends on the resolution of the ocean model. After this turning point, the error growth slows down significantly to polynomial functions of time. In the ideal case, a theoretical upper threshold on exponential growth of CLPT error can be derived. These characteristics are proved theoretically, verified via simulation, and justified with ocean experimental data. The method of CLPT may be applied to improve the accuracy of ocean circulation models and the performance of navigation algorithms for marine robots.

Cognitive response navigation algorithm for mobile robots using biological antennas

SUMMARYWe present BioBug, a bionic cognitive response navigation algorithm for mobile robots based on neuroethology principles. It includes a biological antenna model for environment perception and an improved Bug algorithm for motion planning and control. The biological antenna model delineates the interested sensing areas, and thus decreases the computational burden. Then, this obtained environment stimulation is responded to generate the corresponding walking behavior according to BioBug. Simulations and experiments have been carried out in different conditions of obstacle density and boundary shape through algorithm comparisons. Compared with the competitors, BioBug is characterized by not only a smaller path length, but also shorter time for obstacle escape. The results demonstrate the practicality, environment robustness, and obstacle avoidance efficiency of the algorithm.

HCTNav: A Path Planning Algorithm for Low-Cost Autonomous Robot Navigation in Indoor Environments

Low-cost robots are characterized by low computational resources and limited energy supply. Path planning algorithms aim to find the optimal path between two points so the robot consumes as little energy as possible. However, these algorithms were not developed considering computational limitations (i.e., processing and memory capacity). This paper presents the HCTNav path-planning algorithm (HCTLab research group’s navigation algorithm). This algorithm was designed to be run in low-cost robots for indoor navigation. The results of the comparison between HCTNav and the Dijkstra’s algorithms show that HCTNav’s memory peak is nine times lower than Dijkstra’s in maps with more than 150,000 cells.

Command Fusion for Navigation of Mobile Robots in Dynamic Environments with Objects

In this paper, we propose a fuzzy inference model for a navigation algorithm for a mobile robot that intelligently searches goal location in unknown dynamic environments. Our model uses sensor fusion based on situational commands using an ultrasonic sensor. Instead of using the “physical sensor fusion” method, which generates the trajectory of a robot based upon the environment model and sensory data, a “command fusion” method is used to govern the robot motions. The navigation strategy is based on a combination of fuzzy rules tuned for both goal-approach and obstacle-avoidance based on a hierarchical behavior-based control architecture. To identify the environments, a command fusion technique is introduced where the sensory data of the ultrasonic sensors and a vision sensor are fused into the identification process. The result of experiment has shown that highlights interesting aspects of the goal seeking, obstacle avoiding, decision making process that arise from navigation interaction.

A new effective algorithm for on-line robot motion planning

Article history: Received May 12, 2013 Accepted July 15, 2013 Available online July 17 2013 A very challenging issue in robot navigation or path planning in an unknown environment is to find a globally optimal path from the start to the target point at the same time avoid collisions. This paper presents a new sensor-based online method for generating collision-free optimal path for mobile robots to take a target amidst static obstacles. It is assumed that, target is static and the location of obstacles is completely unknown for robot and all of these materials will be calculated online. Although the area that is under vision of robot’s sensor is confined, we have to consider an inevitable assumption that target is detectable by robot in everywhere. Proposed algorithm to avoid colliding the obstacles in its way toward target, detects a short and feasible paths by utilizing an innovative and effective method. Following that, shortest of them to will be chosen for navigation. There are different important factors which are considered in robot motion planning problems. First, required time for robot’s action in unpredicted circumstances that the running time of the used algorithm plays a major role in this term. Second, the length of traveled path from start point to target point that represents the efficiency of exploited algorithm for leading the robot. The presented algorithm of this paper has proved its efficiency in both of mentioned issues. Simulation results show that traveled path has the least length and the running time is remarkably less than other presented algorithms until now. In addition, the effectiveness of presented algorithm in complex situation is discernible. These results prove that the presented novel and effective robot navigation algorithm is very suitable for real-time navigation in complex environments. © 2014 Growing Science Ltd. All rights reserved.

Mobile Robot Collision Avoidance in Human Environments

Collision avoidance is a fundamental requirement for mobile robots. Avoiding moving obstacles (also termed dynamic obstacles) with unpredictable direction changes, such as humans, is more challenging than avoiding moving obstacles whose motion can be predicted. Precise information on the future moving directions of humans is unobtainable for use in navigation algorithms. Furthermore, humans should be able to pursue their activities unhindered and without worrying about the robots around them. In this paper, both active and critical regions are used to deal with the uncertainty of human motion. A procedure is introduced to calculate the region sizes based on worst-case avoidance conditions. Next, a novel virtual force field-based mobile robot navigation algorithm (termed QVFF) is presented. This algorithm may be used with both holonomic and nonholonomic robots. It incorporates improved virtual force functions for avoiding moving obstacles and its stability is proven using a piecewise continuous Lyapunov function. Simulation and experimental results are provided for a human walking towards the robot and blocking the path to a goal location. Next, the proposed algorithm is compared with five state-of-the-art navigation algorithms for an environment with one human walking with an unpredictable change in direction. Finally, avoidance results are presented for an environment containing three walking humans. The QVFF algorithm consistently generated collision-free paths to the goal.