Autonomous Robot Navigation Research Articles

A Novel Goal oriented Sampling Method for Improving the Convergence Rate of Sampling based Path Planning for Autonomous Mobile Robot Navigation

Autonomous Mobile Robots' performance relies on intelligent motion planning algorithms. In autonomous mobile robots, sampling-based path-planning algorithms are widely used. One of the efficient sampling-based path planning algorithms is the Rapidly Exploring Random Tree (RRT). However, the solution provided by RRT is suboptimal. An RRT extension known as RRT* is optimal, but it takes time to converge. To improve the RRT* slow convergence problem, a goal-oriented sampling-based RRT* algorithm known as GS-RRT* is proposed in this paper. The focus of the proposed research work is to reduce unwanted sample exploration and solve the slow convergence problem of RRT* by taking more samples in the vicinity of the goal region. The proposed research work is validated in three different environments with a map size of 384*384 and compared to the existing algorithms: RRT, Goal-directed RRT(G-RRT), RRT*, and Informed-RRT*. The proposed research work is compared with existing algorithms using four metrics: path length, time to find the solution, the number of nodes visited, and the convergence rate. The validation is done in the Gazebo Simulation and on a TurtleBot3 mobile robot using the Robotics Operating System (ROS). The numerical findings show that the proposed research work improves the convergence rate by an average of 33% over RRT* and 27% over Informed RRT*, and the node exploration is 26% better than RRT* and 20% better than Informed RRT*.

ROMR: A ROS-based open-source mobile robot

Currently, commercially available intelligent transport robots that are capable of carrying up to 90 kg of load can cost $5,000 or even more. This makes real-world experimentation prohibitively expensive and limits the applicability of such systems to everyday home or industrial tasks. Aside from their high cost, the majority of commercially available platforms are either closed-source, platform-specific or use difficult-to-customize hardware and firmware. In this work, we present a low-cost, open-source and modular alternative, referred to herein as “ROS-based Open-source Mobile Robot (ROMR)”. ROMR utilizes off-the-shelf (OTS) components, additive manufacturing technologies, aluminium profiles, and a consumer hoverboard with high-torque brushless direct current (BLDC) motors. ROMR is fully compatible with the robot operating system (ROS), has a maximum payload of 90 kg, and costs less than $1500. Furthermore, ROMR offers a simple yet robust framework for contextualizing simultaneous localization and mapping (SLAM) algorithms, an essential prerequisite for autonomous robot navigation. The robustness and performance of the ROMR were validated through real-world and simulation experiments. All the design, construction and software files are freely available online under the GNU GPL v3 license at https://doi.org/10.17605/OSF.IO/K83X7. A descriptive video of ROMR can be found athttps://osf.io/ku8ag.

Improved reinforcement learning path planning algorithm integrating prior knowledge.

In order to realize the optimization of autonomous navigation of mobile robot under the condition of partial environmental knowledge known. An improved Q-learning reinforcement learning algorithm based on prior knowledge is proposed to solve the problem of slow convergence and low learning efficiency in mobile robot path planning. Prior knowledge is used to initialize the Q-value, so as to guide the agent to move toward the target direction with a greater probability from the early stage of the algorithm, eliminating a large number of invalid iterations. The greedy factor ε is dynamically adjusted based on the number of times the agent successfully reaches the target position, so as to better balance exploration and exploitation and accelerate convergence. Simulation results show that the improved Q-learning algorithm has a faster convergence rate and higher learning efficiency than the traditional algorithm. The improved algorithm has practical significance for improving the efficiency of autonomous navigation of mobile robots.

Novel Development of Fuzzy Controller Based Multi-Agent System for Efficient Navigation of Autonomous Robots

This study investigates a fuzzy controller technique for autonomous robot navigation in both the static and dynamic environmental conditions and an excessive number of pathways to the destination. The design and implementation of a novel obstacle avoidance technique for autonomous robots are developed using the fuzzy controller-based multi-agent system. This method allows the Robot to identify dynamic or static unidentified objects while directing the Robot to prevent collisions and advance toward the objective. The Robot is capable of moving in a variety of environments. The Robot may communicate and travel in dynamic space by perceiving its surroundings and pursuing a free-collision route. This study covers creating a multi-agent system that includes fuzzy logic to regulate the robotic movements along a path reactive for effective Navigation. This project aims to develop an algorithm that allows the Robot to do distinct tasks to accomplish a unified objective, autonomous Navigation in a slightly unfamiliar environment. Under such a situation, the usage of a multi-agent system is advantageous. As a result, we created a framework made up of four agents responsible for sensing, Navigation, dynamic, and static obstacle avoidance. These agents communicate with one another via a coordinating mechanism.

Localization System for Vehicle Navigation Based on GNSS/IMU Using Time-Series Optimization with Road Gradient Constrain

In this paper, we propose a GNSS/IMU localization system for mobile robots when wheel speed sensors cannot be attached. Highly accurate location information is required for autonomous navigation of mobile robots. A typical method of acquiring location information is to use a Kalman filter for position estimation. The Kalman filter is a maximum-likelihood estimation method that assumes normally distributed noise. However, non-normally distributed GNSS multipath noise that frequently occurs in urban environments causes the Kalman filter to break down, and degrades the estimation performance. Other GNSS/IMU localization methods capable of lane-level estimation in urban environments use wheel speed sensors, which are unsuitable for the present situation. In this study, we aim to improve the performance of lane-level localization by adding a vehicle speed estimation function to adapt the method to those requiring wheel speed sensors. The proposed method optimizes time-series data to accurately compensate for accelerometer bias errors and reduce GNSS multipath noise. The evaluation confirmed the effectiveness of the proposed method, with improved velocity and position estimation performance compared with the Kalman filter method.

An Inter-Ridge Navigation Path Extraction Method Based on Res2net50 Segmentation Model

The extraction of navigation lines plays a crucial role in the autonomous navigation of agricultural robots. This work offers a method of ridge navigation route extraction, based on deep learning, to address the issues of poor real-time performance and light interference in navigation path recognition in a field environment. This technique is based on the Res2net50 model and incorporates the Squeeze-and-Excitation Networks (SE) attention mechanism to focus on the key aspects of the image. The empty space pyramid pooling module is presented to further extract high-level semantic data and enhance the network’s capacity for fine-grained representation. A skip connection is used to combine the high-level semantic characteristics and low-level textural features that are extracted. The results of the ridge prediction are then obtained, followed by the realization of the final image segmentation, through sampling. Lastly, the navigation line is fitted once the navigation feature points have been retrieved using the resulting ridge segmentation mask. The outcomes of the experiment reveal that: the Mean Intersection over Union (MIOU) and F-measure values of the inter-ridge navigation path extraction approach suggested in this paper are increased by 0.157 and 0.061, respectively, compared with the Res2net50 network. Under various illumination situations, the average pixel error is 8.27 pixels and the average angle error is 1.395°. This technique is appropriate for ridge operations and can successfully increase network prediction model accuracy.

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose From Monocular Video

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. In this paper, a novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. The source codes will be released soon at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/IRMVLab/HRANet</uri> .

ROS-Based Autonomous Navigation Robot Platform with Stepping Motor

Indoor navigation robots, which have been developed using a robot operating system, typically use a direct current motor as a motion actuator. Their control algorithm is generally complex and requires the cooperation of sensors such as wheel encoders to correct errors. For this study, an autonomous navigation robot platform named Owlbot was designed, which is equipped with a stepping motor as a mobile actuator. In addition, a stepping motor control algorithm was developed using polynomial equations, which can effectively convert speed instructions to generate control signals for accurately operating the motor. Using 2D LiDAR and an inertial measurement unit as the primary sensors, simultaneous localization, mapping, and autonomous navigation are realised based on the particle filtering mapping algorithm. The experimental results show that Owlbot can effectively map the unknown environment and realise autonomous navigation through the proposed control algorithm, with a maximum movement error being smaller than 0.015 m.

Development of an Omnidirectional AGV by Applying ORB-SLAM for Navigation Under ROS Framework

The development of an automated guided vehicle with omni-wheels for autonomous navigation under a robot operating system framework is presented in this paper. Specifically, a laser rangefinder-constructed two-dimensional environment map is integrated with a three-dimensional point cloud map to achieve real-time robot positioning using the oriented features from accelerated segment test and rotated binary robust independent elementary feature detector-simultaneous localisation and mapping algorithm. In the path planning for autonomous navigation of the omnidirectional mobile robot, we applied the A* global path search algorithm, which uses a heuristic function to estimate the robot position difference and searches for the best direction. Moreover, we employed the time-elastic-band method for local path planning, which merges the time interval of two locations to realise time optimisation for dynamic obstacle avoidance. The experimental results verified the effectiveness of the applied algorithms for the omni-wheeled mobile robot. Further, the results showed a superior performance over the adaptive Monte Carlo localisation for robot localisation and dynamic window approach for local path planning.

Autonomous Navigation System of Indoor Mobile Robots Using 2D Lidar

Significant developments have been made in the navigation of autonomous mobile robots within indoor environments; however, there still remain challenges in the face of poor map construction accuracy and suboptimal path planning, which limit the practical applications of such robots. To solve these challenges, an enhanced Rao Blackwell Particle Filter (RBPF-SLAM) algorithm, called Lidar-based RBPF-SLAM (LRBPF-SLAM), is proposed. In LRBPF, the adjacent bit poses difference data from the 2D Lidar sensor which is used to replace the odometer data in the proposed distribution function, overcoming the vulnerability of the proposed distribution function to environmental disturbances, and thus enabling more accurate pose estimation of the robot. Additionally, a probabilistic guided search-based path planning algorithm, gravitation bidirectional rapidly exploring random tree (GBI-RRT), is also proposed, which incorporates a target bias sampling to efficiently guide nodes toward the goal and reduce ineffective searches. Finally, to further improve the efficiency of navigation, a path reorganization strategy aiming at eliminating low-quality nodes and improving the path curvature of the path is proposed. To validate the effectiveness of the proposed method, the improved algorithm is integrated into a mobile robot based on a ROS system and evaluated in simulations and field experiments. The results show that LRBPF-SLAM and GBI-RRT perform superior to the existing algorithms in various indoor environments.

An Obstacle-Finding Approach for Autonomous Mobile Robots Using 2D LiDAR Data

Obstacle detection is crucial for the navigation of autonomous mobile robots: it is necessary to ensure their presence as accurately as possible and find their position relative to the robot. Autonomous mobile robots for indoor navigation purposes use several special sensors for various tasks. One such study is localizing the robot in space. In most cases, the LiDAR sensor is employed to solve this problem. In addition, the data from this sensor are critical, as the sensor is directly related to the distance of objects and obstacles surrounding the robot, so LiDAR data can be used for detection. This article is devoted to developing an obstacle detection algorithm based on 2D LiDAR sensor data. We propose a parallelization method to speed up this algorithm while processing big data. The result is an algorithm that finds obstacles and objects with high accuracy and speed: it receives a set of points from the sensor and data about the robot’s movements. It outputs a set of line segments, where each group of such line segments describes an object. The two proposed metrics assessed accuracy, and both averages are high: 86% and 91% for the first and second metrics, respectively. The proposed method is flexible enough to optimize it for a specific configuration of the LiDAR sensor. Four hyperparameters are experimentally found for a given sensor configuration to maximize the correspondence between real and found objects. The work of the proposed algorithm has been carefully tested on simulated and actual data. The authors also investigated the relationship between the selected hyperparameters’ values and the algorithm’s efficiency. Potential applications, limitations, and opportunities for future research are discussed.

LIO-Fusion: Reinforced LiDAR Inertial Odometry by Effective Fusion With GNSS/Relocalization and Wheel Odometry

Reliable state estimation is a prerequisite for autonomous robot navigation in complex environments. In this work, we present LIO-Fusion, a reinforced LiDAR inertial odometry system that optimally fuses GNSS/relocalization and wheel odometry to provide accurate and robust 6-DoF movement estimation under challenging perceptual conditions. LIO-Fusion formulates multi-source sensors fusion based on factor graph, allowing a multitude of relative and absolute measurements which may be degraded, disturbed or even inaccessible. In the LIO-Fusion system, online initialization consists of point cloud feature extraction and matching, IMU preintegration, encoder integration, GNSS calibration and prior-map relocalization. Then, its global reinforcement module detects the reliability of GNSS/relocalization to obtain healthy GNSS/relocalization factors, whereas the local reinforcement module uses a sub-factor graph to fuse prior estimation results for the reinforced local odometry factor. Finally, the basic LiDAR/IMU factors, healthy GNSS/relocalization factors and reinforced local odometry factor are jointly used to constrain the system state in the main factor graph such that low-drift odometry under LiDAR degradation can be reliably obtained and corrected globally. We extensively evaluated the real-time LIO-Fusion system by real-world experiments, and compared its performance to other state-of-the-art methods on large-scale datasets collected in the urban and hazardous environments. Results have shown that LIO-Fusion yielded high precision localization and mapping accuracy as well as robustness to sensor failures.

Multi-target trajectory planning and control technique for autonomous navigation of multiple robots

The autonomous robot has been the attraction point among robotic researchers since the last decade by virtue of increasing demand of automation in defence and intelligent industries. In the current research, a modified flow direction optimization algorithm (MFDA) and firefly algorithm (FA) are hybridized and implemented on wheeled robots to encounter multi-target trajectory optimization with smooth navigation by negotiating obstacles present within the workspace. Here, a hybrid algorithm is adopted for designing the controller with consideration of navigational parameters. A Petri-Net controller is also aided with the developed controller to resolve any conflict during navigation. The developed controller has been investigated on WEBOTS and MATLAB simulation environments coupled with real-time experiments by considering Khepera-II robot as wheeled robot. Single robot- multi-target, multiple robot single target and multiple robots-multiple target problems are tackled during the investigation. The outcomes of simulation are verified through real-time experimental outcomes by comparing results. Further, the proposed algorithm is tested for its suitability, precision, and stability. Finally, the developed controller is tested against existing techniques for authentication of proposed technique, and significant improvements of an average 34.2% is observed in trajectory optimization and 70.6% in time consumption.

An Autonomous Maze-Solving Robotic System Based on an Enhanced Wall-Follower Approach

Autonomous robots are designed to discover and interpret their surroundings and orient themselves around obstacles to reach the destination point from an initial point. Robot autonomous navigation is a requirement for maze-solving systems, where the solver robot is required to navigate the maze area to get its desire destination location using the fastest route possible. In this paper, a new, modified wall-follower system for a maze-solving robot was proposed that overcame the infinite loop-back issue in the traditional wall-follower approaches. We also investigated and analyzed the performance of three different maze-solving algorithms and compared them with the proposed, modified wall-follower robotic system by conducting several real experiments to validate the efficiency of the developed wall-follower robotic system.

Path Planning for Unmanned Delivery Robots Based on EWB-GWO Algorithm.

With the rise of robotics within various fields, there has been a significant development in the use of mobile robots. For mobile robots performing unmanned delivery tasks, autonomous robot navigation based on complex environments is particularly important. In this paper, an improved Gray Wolf Optimization (GWO)-based algorithm is proposed to realize the autonomous path planning of mobile robots in complex scenarios. First, the strategy for generating the initial wolf pack of the GWO algorithm is modified by introducing a two-dimensional Tent-Sine coupled chaotic mapping in this paper. This guarantees that the GWO algorithm generates the initial population diversity while improving the randomness between the two-dimensional state variables of the path nodes. Second, by introducing the opposition-based learning method based on the elite strategy, the adaptive nonlinear inertia weight strategy and random wandering law of the Butterfly Optimization Algorithm (BOA), this paper improves the defects of slow convergence speed, low accuracy, and imbalance between global exploration and local mining functions of the GWO algorithm in dealing with high-dimensional complex problems. In this paper, the improved algorithm is named as an EWB-GWO algorithm, where EWB is the abbreviation of three strategies. Finally, this paper enhances the rationalization of the initial population generation of the EWB-GWO algorithm based on the visual-field line detection technique of Bresenham's line algorithm, reduces the number of iterations of the EWB-GWO algorithm, and decreases the time complexity of the algorithm in dealing with the path planning problem. The simulation results show that the EWB-GWO algorithm is very competitive among metaheuristics of the same type. It also achieves optimal path length measures and smoothness metrics in the path planning experiments.

A review: On bio-inspired optimization methods for path planning of mobile robot

In recent years, researchers have paid attention to algorithms inspired by nature where these algorithms have proven their efficiency in solving many optimization problems, especially in complex situations, due to their high precision, speed of optimization, simplicity of the techniques, and efficiency in agent cooperation. The primary issue in the field of autonomous mobile robots is navigation. An autonomous robot's navigation ability is one of its most crucial and distinctive features. There are four components of the autonomous robot navigation issue: vision, localization, cognition, and path planning. Many academics have used bio-inspired methods to solve navigation difficulties in mobile robots in recent years, including path planning where they considered the path planning problem as an optimization problem. Many novel path-planning methods have been created, and those using bio-inspired algorithms have received much attention. These algorithms have been shown to be useful in solving complex problems where the solution space isn't always adequately characterized and the problem necessitates solving complex mathematical models of live processes. More intricate optimization methods that transcend the constraints of classical procedures must be applied as the complexities of the optimization problem increase. This work contributes to presenting a group of algorithms inspired by nature that has been used to solve the problem of planning the path of mobile robots, and then making a comparison between these algorithms based on three factors (cost, time, and path length). Choosing an appropriate path-planning method contributes to ensuring safe and efficacious navigation from one point to another.

Multi-Scale Fully Convolutional Network-Based Semantic Segmentation for Mobile Robot Navigation

In computer vision and mobile robotics, autonomous navigation is crucial. It enables the robot to navigate its environment, which consists primarily of obstacles and moving objects. Robot navigation employing impediment detections, such as walls and pillars, is not only essential but also challenging due to real-world complications. This study provides a real-time solution to the problem of obtaining hallway scenes from an exclusive image. The authors predict a dense scene using a multi-scale fully convolutional network (FCN). The output is an image with pixel-by-pixel predictions that can be used for various navigation strategies. In addition, a method for comparing the computational cost and precision of various FCN architectures using VGG-16 is introduced. The binary semantic segmentation and optimal obstacle avoidance navigation of autonomous mobile robots are two areas in which our method outperforms the methods of competing works. The authors successfully apply perspective correction to the segmented image in order to construct the frontal view of the general area, which identifies the available moving area. The optimal obstacle avoidance strategy is comprised primarily of collision-free path planning, reasonable processing time, and smooth steering with low steering angle changes.

DCP-SLAM: Distributed Collaborative Partial Swarm SLAM for Efficient Navigation of Autonomous Robots

Collaborative robots represent an evolution in the field of swarm robotics that is pervasive in modern industrial undertakings from manufacturing to exploration. Though there has been much work on path planning for autonomous robots employing floor plans, energy-efficient navigation of autonomous robots in unknown environments is gaining traction. This work presents a novel methodology of low-overhead collaborative sensing, run-time mapping and localization, and navigation for robot swarms. The aim is to optimize energy consumption for the swarm as a whole rather than individual robots. An energy- and information-aware management algorithm is proposed to optimize the time and energy required for a swarm of autonomous robots to move from a launch area to the predefined destination. This is achieved by modifying the classical Partial Swarm SLAM technique, whereby sections of objects discovered by different members of the swarm are stitched together and broadcast to members of the swarm. Thus, a follower can find the shortest path to the destination while avoiding even far away obstacles in an efficient manner. The proposed algorithm reduces the energy consumption of the swarm as a whole due to the fact that the leading robots sense and discover respective optimal paths and share their discoveries with the followers. The simulation results show that the robots effectively re-optimized the previous solution while sharing necessary information within the swarm. Furthermore, the efficiency of the proposed scheme is shown via comparative results, i.e., reducing traveling distance by 13% for individual robots and up to 11% for the swarm as a whole in the performed experiments.

Exploring the Most Sectors at the DARPA Subterranean Challenge Finals

Autonomous robot navigation in austere environments is critical to missions like “search and rescue”, yet it remains difficult to achieve. The recent DARPA Subterranean Challenge (SubT) highlights prominent challenges including GPS-denied navigation through rough terrains, rapid exploration in large-scale three-dimensional (3D) space, and interrobot coordination over unreliable communication. Solving these challenges requires both mechanical resilience and algorithmic intelligence. Here, we present our approach that leverages a fleet of custom-built heterogeneous robots and an autonomy stack for robust navigation in challenging environments. Our approach has demonstrated superior navigation performance in the SubT Final Event, resulting in the fastest traversal and most thorough exploration of the environment, which won the “Most Sectors Explored Award.” This paper details our approach from two aspects: mechanical designs of a marsupial ground-and-aerial system to overcome mobility challenges and autonomy algorithms enabling collective rapid exploration. We also provide lessons learned in the design, development, and deployment of complex but resilient robotic systems to overcome real-world navigation challenges.

LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment

In this work, we propose the LiDAR Road-Atlas, a compact and efficient 3D map representation, for autonomous robot or vehicle navigation in a general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework which incrementally merges local 2D occupancy grid maps (2D-OGMs). Specifically, the contributions of our method are threefold. First, we solve the challenging problem of creating local 2D-OGMs in nonstructured urban scenes based on a real-time delimitation of traversable and curb regions in a LiDAR point cloud. Second, we achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we achieve a very efficient 3D map representation of a general environment thanks to the automatic local-OGM-induced traversable-region labeling and a sparse probabilistic local point-cloud encoding. Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning, and some other tasks. Our map representation is insensitive to dynamic objects which can be filtered out in the resulting map based on a probabilistic fusion. Empirically, we compare our map representation with a couple of popular map representations in robotics society, and our map representation is more favorable in terms of efficiency, scalability, and compactness. Additionally, we also evaluate localization performance given the LiDAR Road-Atlas representations on two public datasets. With a 16-channel LiDAR sensor, our method achieves an average global localization error of 0.26 m (translation) and 1.07 (rotation) on the Apollo dataset, and 0.89 m (translation) and 1.29 (rotation) on the MulRan dataset, respectively, at 10 Hz, which validates its promising performance. The code for this work is open-sourced at https://github.com/IMRL/Lidar-road-atlas.