Approach For Robot Navigation Research Articles

Bridging Requirements, Planning, and Evaluation: A Review of Social Robot Navigation.

Navigation lies at the core of social robotics, enabling robots to navigate and interact seamlessly in human environments. The primary focus of human-aware robot navigation is minimizing discomfort among surrounding humans. Our review explores user studies, examining factors that cause human discomfort, to perform the grounding of social robot navigation requirements and to form a taxonomy of elementary necessities that should be implemented by comprehensive algorithms. This survey also discusses human-aware navigation from an algorithmic perspective, reviewing the perception and motion planning methods integral to social navigation. Additionally, the review investigates different types of studies and tools facilitating the evaluation of social robot navigation approaches, namely datasets, simulators, and benchmarks. Our survey also identifies the main challenges of human-aware navigation, highlighting the essential future work perspectives. This work stands out from other review papers, as it not only investigates the variety of methods for implementing human awareness in robot control systems but also classifies the approaches according to the grounded requirements regarded in their objectives.

An Improved Sampling Dijkstra Approach for Robot Navigation and Path Planning

The task of path planning is extremely investigated in mobile robotics to determine a suitable path for the robot from the source point to the target point. The intended path should satisfy purposes such as collision-free, shortest-path, or power-saving. In the case of a mobile robot, many constraints should be considered during the selection of path planning algorithms such as static or dynamic environment and holonomic or non-holonomic robot. There is a pool of path-planning algorithms in the literature. However, Dijkstra is still one of the effective algorithms due to its simplicity and capabilities to compute single-source shortest-path to every position in the workspace. Researchers propose several versions of the Dijkstra algorithm, especially in mobile robotics. In this paper, we propose an improved approach based on the Dijkstra algorithm with a simple sampling method to sample the workspace to avoid an exhaustive search of the Dijkstra algorithm which consumes time and resources. The goal is to identify the same optimal shortest path resulting from the Dijkstra algorithm with minimum time and number of turns i.e., a smoothed path. The simulation results show that the proposed method improves the Dijkstra algorithm with respect to the running time and the number of turns of the mobile robot and outperforms the RRT algorithm concerning the path length.

Deep Reinforcement Learning for Robotic Approaching Behavior Influenced by User Activity and Disengagement

AbstractA robot intended to monitor human behavior must account for the user’s reactions to minimize his/her perceived discomfort. The possibility of learning user interaction preferences and changing the robot’s behavior accordingly may positively impact the perceived quality of the interaction with the robot. The robot should approach the user without causing any discomfort or interference. In this work, we contribute and implement a novel Reinforcement Learning (RL) approach for robot navigation toward a human user. Our implementation is a proof-of-concept that uses data gathered from real-world experiments to show that our algorithm works on the kind of data that it would run on in a realistic scenario. To the best of our knowledge, our work is one of the first attempts to provide an adaptive navigation algorithm that uses RL to account for non-deterministic phenomena.

Predictive hierarchical reinforcement learning for path-efficient mapless navigation with moving target

Deep reinforcement learning (DRL) has been proven as a powerful approach for robot navigation over the past few years. DRL-based navigation does not require the pre-construction of a map, instead, high-performance navigation skills can be learned from trial-and-error experiences. However, recent DRL-based approaches mostly focus on a fixed navigation target. It is noted that when navigating to a moving target without maps, the performance of the standard RL structure drops dramatically on both the success rate and path efficiency. To address the mapless navigation problem with moving target, the predictive hierarchical DRL (pH-DRL) framework is proposed by integrating the long-term trajectory prediction to provide a cost-effective solution. In the proposed framework, the lower-level policy of the RL agent learns robot control actions to a specified goal, and the higher-level policy learns to make long-range planning of shorter navigation routes by sufficiently exploiting the predicted trajectories. By means of making decisions over two level of policies, the pH-DRL framework is robust to the unavoidable errors in long-term predictions. With the application of deep deterministic policy gradient (DDPG) for policy optimization, the pH-DDPG algorithm is developed based on the pH-DRL structure. Finally, through comparative experiments on the Gazebo simulator with several variants of the DDPG algorithm, the results demonstrate that the pH-DDPG outperforms other algorithms and achieves a high success rate and efficiency even though the target moves fast and randomly.

A bio-inspired robot navigation model based on the environmental cognitive mechanism of the rat brain hippocampus

Self-positioning and goal-oriented navigation behaviors in complex and variable environments are important capabilities that mammals rely on for survival in the natural world. To this end, this article proposes a robot navigation model with bio-inspired environmental cognition and autonomous localization capabilities based on the spatial cognitive mechanism of the hippocampus in the rat brain. The model constructs a cognitive map by integrating its own motion cues and visual observation features, and uses the dynamic predictive relationship between each location cognitive node to achieve a goal-oriented navigation process. The research approach in this article will provide inspirational implications for a robot navigation approach with brain-like cognitive mechanisms.

A Review on Path Planning and Obstacle Avoidance Algorithms for Autonomous Mobile Robots

Mobile robots have been widely used in various sectors in the last decade. A mobile robot could autonomously navigate in any environment, both static and dynamic. As a result, researchers in the robotics field have offered a variety of techniques. This paper reviews the mobile robot navigation approaches and obstacle avoidance used so far in various environmental conditions to recognize the improvement of path planning strategists. Taking into consideration commonly used classical approaches such as Dijkstra algorithm (DA), artificial potential field (APF), probabilistic road map (PRM), cell decomposition (CD), and meta-heuristic techniques such as fuzzy logic (FL), neutral network (NN), particle swarm optimization (PSO), genetic algorithm (GA), cuckoo search algorithm (CSO), and artificial bee colony (ABC). Classical approaches have limitations of trapping in local minima, failure to handle uncertainty, and many more. On the other hand, it is observed that heuristic approaches can solve most real-world problems and perform well after some modification and hybridization with classical techniques. As a result, many methods have been established worldwide for the path planning strategy for mobile robots. The most often utilized approaches, on the other hand, are offered below for further study.

깊이 이미지를 이용한 딥러닝 기반 충돌 확률 예측 및 장애물 회피 알고리즘

This paper proposes a vision-based navigation algorithm in cluttered environments by using a convolutional neural network (CNN)-based deep learning and depth images. Existing approaches for robot navigation are developed based on obstacle detection or an accurate map to generate a path, which requires complex computation. To solve this issue, we propose a deep-learning-based navigation algorithm that does not require a preobtained map or a recognition of obstacles. In addition, by exploiting a collision probability prediction using a depth image, our method automatically adjusts the velocity command while passing the complex area, so we can improve the safety of a mobile robot. To validate the performance of our proposed method, we conduct a simulation with a mobile robot in a Gazebo environment. The simulation results show that our method outperforms the conventional avoidance algorithm.

Agricultural rout planning with variable rate pesticide application in a greenhouse environment

The use of robotics in executing agricultural tasks has significantly improved productivity over the years as a result of automation in performing such activities as spray, harvesting, planting etc. In order to optimize both crop yield and quality while minimizing costs, there will be need for the application of navigation strategies. These will provide optimal as well as autonomous navigation capability which is built entirely upon field coverage plan thereby making robot navigation approach a paramount scheme. In this paper, the autonomy of an agricultural mobile robot is enhanced in a structured environment (greenhouse farm) to locate an optimum route such that the robot performs a selective and variable spray of pesticides to the plants. To realize this, a robust vehicle routing problem (VRP) scheme is designed to navigate the robot autonomously while making intelligent decisions to fulfil the pesticide demands at each node (infected plants). The improved non-dominated sorting genetic algorithm (INSGA-III) is adopted to solve this fully integer problem based on three (3) test cases carried out with 8, 32 and 56 infected plants respectively for validation. The results obtained show a trade-off solution as the Optimal INSGA-III is significantly lower than NSGA-III in terms of solution quality. On the other hand, a significant reduction in run times of between 66% and 76% and 76–93% was obtained for all test case scenarios for population sizes of 100 and 1500 respectively.

Navigation in Large Groups of Robots

As robots become more ubiquitous, research in large-scale robot navigation has gained more focus given their potential real-world applications. This review intends to provide a summary of recent advances on the field of multi-robot navigation, focusing on cases where scale is an important attribute of the system. Experimental evaluation of a large number of robots is complex due to size and cost constraints. Successful applications of large-scale robot navigation approaches are in structured and known environments where robots are centrally controlled. Advances in the standardization of robot hardware and software are increasing interest for research in navigation for large groups of robots. We present a review on navigation approaches for multi-robot systems. Then, we focus on recent articles that deal with the problem of moving a large number of robots in virtual or physical space. Finally, we summarize our main findings and emphasize the challenges.

Nature inspired evolutionary approaches for robot navigation: Survey

Autonomous robot navigation (ARN) requires intelligent systems equipped with human capabilities to achieve controlled motion among flats, ridgesor obstacles while avoiding collision in known or partially unknown environment with safety of equipment and manpower involved. Its objective is to generate optimal collision free path from initial to target location within minimal time and energy requirement. There are various navigational approaches (classical, heuristics, hybrid or nature inspired) and its choice depends on type of environment (static or dynamic) and application area. Nature inspired evolutionary (NIE) approaches is an emerging paradigm to develop robust and dynamic problems to address non-linear or multi-objective problemsin dynamic environment. This work is an attempt to review recently developed NIE approaches based on different biological groups for application in field of robot path planning (RPP).

Improved grid mapping technology based on Rao-Blackwellized particle filters and the gradient descent algorithm

ABSTRACTRecently, the Rao-Blackwellized particle filter (RBPF) has been used to solve the problem of simultaneous localization and mapping (SLAM). Using the odometer information of robot to calculate the proposed distribution requires a number of sampled particles, which increases the calculation complexity in the RBPF operation. In this paper, we integrate the odometer measurement and sensor observation into the proposed distribution, effectively reducing the particle sample scale. To reduce the inconsistency in the map model caused by the cumulative error of the odometer information of robot, we applied a gradient descent algorithm to fuse the sensor data to obtain the real-time attitude angle. This combination method, based on the robot operation system (ROS), runs on a platform of self-built mobile robot equipped with a laser rangefinder. The experimental results show that this method can realize the online real-time high-precision grid map which provides a new approach for robot navigation and SLAM.

Anticipative kinodynamic planning: multi-objective robot navigation in urban and dynamic environments

This paper presents the anticipative kinodynamic planning (AKP) approach for robot navigation in urban environments, while satisfying both dynamic and nonholonomic constraints. Our main motivation is to minimize the impact that the robot is doing to the environment, i.e. other pedestrians, while successfully achieving a navigation goal. To this end, we require a better understanding of the environment, and thus, we propose to integrate seamlessly a human motion prediction algorithm into the planning algorithm. In addition, we are able to anticipate for each of the robot’s calculated paths or actions the corresponding people’s future trajectories, which is essential to reduce the impact to nearby pedestrians. Multi-objective cost functions are proposed and we describe a well-posed procedure to build joint cost functions. Plenty of simulations and real experiments have been carried out to demonstrate the success of the AKP, compared to other navigation approaches.

Road area detection method based on DBNN for robot navigation using single camera in outdoor environments

PurposeThe purpose of this study is to develop a cost-effective autonomous wheelchair robot navigation method that assists the aging population.Design/methodology/approachNavigation in outdoor environments is still a challenging task for an autonomous mobile robot because of the highly unstructured and different characteristics of outdoor environments. This study examines a complete vision guided real-time approach for robot navigation in urban roads based on drivable road area detection by using deep learning. During navigation, the camera takes a snapshot of the road, and the captured image is then converted into an illuminant invariant image. Subsequently, a deep belief neural network considers this image as an input. It extracts additional discriminative abstract features by using general purpose learning procedure for detection. During obstacle avoidance, the robot measures the distance from the obstacle position by using estimated parameters of the calibrated camera, and it performs navigation by avoiding obstacles.FindingsThe developed method is implemented on a wheelchair robot, and it is verified by navigating the wheelchair robot on different types of urban curve roads. Navigation in real environments indicates that the wheelchair robot can move safely from one place to another. The navigation performance of the developed method and a comparison with laser range finder (LRF)-based methods were demonstrated through experiments.Originality/valueThis study develops a cost-effective navigation method by using a single camera. Additionally, it utilizes the advantages of deep learning techniques for robust classification of the drivable road area. It performs better in terms of navigation when compared to LRF-based methods in LRF-denied environments.

The Proposed Fuzzy_IAMR Approach

In this paper we present a fuzzy_IAMR Intelligent Autonomous Mobile Robot navigation approach of Autonomous Mobile Robot. The robot has to find a collision-free trajectory between the starting configuration and the goal configuration in a static unknown environment containing some obstacles. To deal with autonomy requirements and to present a real intelligent task, the use of the Fuzzy Logic FL has an advantage of adaptivity such that this approach works perfectly even if an environment is unknown. In this context, we present a software implementation Fuzzy Logic FL path planning in a terrain. Fuzzy logic allows a continuum of control variables such as heading angles and speeds to be considered, as opposed to the discrete numbers used in crisp behaviors. Artificial intelligence, including Fuzzy logic has been actively studied and applied to domains such as automatically control of complex systems like robot. In f act, recognition, learning, decision-making, and action constitute the principal obstacle avoidance problems, so it is interesting to replace the classical approaches by technical approaches based on intelligent computing technologies. This technology FL is becoming useful as alternate approach to the classical techniques one. Also, fuzzy logic can be viewed as an attempt to bring together conventional precise mathematics and humanlike decision-making concepts. Fuzzy logic can be a valid approach solving control problem in a wide range of applications. To deal with the principle, the robot moves within the unknown environment by sensing and avoiding the obstacles coming across its way towards the unknown target. This algorithm provides the robot the possibility to move from the initial position to the final position (target) without collisions where the main factors of moving are included such as learning, deciding, acting, cognition, perception, and thinking. The robot succeeds to reach the target without collisions. The results gotten of the FL on randomly generated terrains are very satisfactory and promising. The extension of the FL for solving both paths planning and trajectory planning.

Self-Organizing Incremental Associative Memory-Based Robot Navigation

SUMMARY This paper presents a new incremental approach for robot navigation using associative memory. We defined the association as node→action→node where node is the robot position and action is the action of a robot (i.e., orientation, direction). These associations are used for path planning by retrieving a sequence of path fragments (in form of (node→action→node) → (node→action→node) →· ·· ) starting from the start point to the goal. To learn such associations, we applied the associative memory using Self-Organizing Incremental Associative Memory (SOIAM). Our proposed method comprises three layers: input layer, memory layer and associative layer. The input layer is used for collecting input observations. The memory layer clusters the obtained observations into a set of topological nodes incrementally. In the associative layer, the associative memory is used as the topological map where nodes are associated with actions. The advantages of our method are that 1) it does not need prior knowledge, 2) it can process data in continuous space which is very important for real-world robot navigation and 3) it can learn in an incremental unsupervised manner. Experiments are done with a realistic robot simulator: Webots. We divided the experiments into 4 parts to show the ability of creating a map, incremental learning and symbol-based recognition. Results show that our method offers a 90% success rate for reaching

A Model Predictive Navigation Approach Considering Mobile Robot Shape and Dynamics

Most mobile robot navigation approaches assume the robot being point-like or consider only its bounding circle while looking for a collision-free path to a given goal position. A well-known method called the Dynamic Window Approach (DWA) introduced an interesting idea for solving the navigation problem by local optimization in the control space of the robot. Some extensions of the original DWA method can also be found in the literature, which enable its applicability to holonomic and non-holonomic robots and ensure a global and safe solution to the navigation problem. The method described in this paper has also been motivated by the basic idea of dynamic window and contributes to the previous variants by taking the robot shape into consideration as well. A navigation function based model predictive control scheme is utilized to choose the appropriate control for a safe and successful navigation.

Pose estimation and map building with a Time-Of-Flight-camera for robot navigation

In this paper, we describe a joint approach for robot navigation with collision avoidance, pose estimation and map building with a 2.5D Photonic Mixer Device (PMD)-camera combined with a high-resolution spherical camera. The cameras are mounted at the front of the robot with a certain inclination angle. The navigation and map building consists of two steps: when entering new terrain the robot first scans the surrounding. Simultaneously a 3D-panorama is generated from the PMD-images. In the second step, the robot moves along the pre-defined path, using the PMD-camera for collision avoidance and a combined Structure-from-Motion (SfM) and model-tracking approach for self-localisation. The computed poses of the robot are simultaneously used for map building with new measurements from the PMD-camera.

Model extension and refinement using pose recovery techniques

Visual measurements of modeled 3-D landmarks provide strong constraints on the location and orientation of a mobile robot. To make the landmark-based robot navigation approach widely applicable, it is necessary to automatically build the landmark models. A substantial amount of effort has been invested by computer vision researchers over the past 10 years on developing robust methods for computing 3-D structure from a sequence of 2-D images. However, robust computation of 3-D structure, with respect to even small amounts of input image noise, has remained elusive. The approach adopted in this article is one of model extension and refinement. A partial model of the environment is assumed to exist and this model is extended over a sequence of frames. As will be shown in the experiments, prior knowledge of the small partial model greatly enhances the robustness of the 3-D structure computations. The initial 3-D model may have errors and these are also refined over the sequence of frames. © 1992 John Wiley & Sons, Inc.