Showing papers on "Mobile robot navigation published in 2021"

OpenStreetMap-based autonomous navigation for the four wheel-legged robot via 3D-Lidar and CCD camera

Abstract: OpenStreetMap (OSM) is widely used in outdoor navigation research recently, which is publicly available and can provide a wide range of road information for outdoor robot navigation. In this paper, aiming at the problem that the map error of OSM will cause the global path to be inconsistent with the real environment, we propose an OSM-based robot navigation method that combines road network information and local perception information. As a global map, OSM provides road network information to obtain the global path by the Dijkstra algorithm. Multi-sensor (including 3D-LiDAR and CCD camera) information fusion offers local information to detect local road information and obstacles for local path planning. We filter local road information and then extract useful road features to optimize the local path. Finally, this local path is used for robot path tracking to complete navigation tasks. The experimental results show that the average error between the trajectory of the robot and the road center is 0.18 meters. This reveals that our method has high navigation accuracy and strong robustness in the real complex environment.

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Abstract: Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can be insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience. Our reinforcement learning approach, which we call BADGR, is an end-to-end learning-based mobile robot navigation system that can be trained with autonomously-labeled off-policy data gathered in real-world environments, without any simulation or human supervision. BADGR can navigate in real-world urban and off-road environments with geometrically distracting obstacles. It can also incorporate terrain preferences, generalize to novel environments, and continue to improve autonomously by gathering more data. Videos, code, and other supplemental material are available on our website https://sites.google.com/view/badgr

A Lifelong Learning Approach to Mobile Robot Navigation

Abstract: This letter presents a self-improving lifelong learning framework for a mobile robot navigating in different environments Classical static navigation methods require environment-specific in-situ system adjustment, eg, from human experts, or may repeat their mistakes regardless of how many times they have navigated in the same environment Having the potential to improve with experience, learning-based navigation is highly dependent on access to training resources, eg, sufficient memory and fast computation, and is prone to forgetting previously learned capability, especially when facing different environments In this work, we propose Lifelong Learning for Navigation (LLfN) which (1) improves a mobile robot's navigation behavior purely based on its own experience, and (2) retains the robot's capability to navigate in previous environments after learning in new ones LLfN is implemented and tested entirely onboard a physical robot with a limited memory and computation budget

Finite Distribution Estimation-Based Dynamic Window Approach to Reliable Obstacle Avoidance of Mobile Robot

Abstract: This article proposes, a novel obstacle avoidance algorithm for a mobile robot based on finite memory filtering (FMF) in unknown dynamic environments. To overcome the limitations of the existing dynamic window approach (DWA), we propose a new version of the DWA, called the finite distribution estimation-based dynamic window approach (FDEDWA), which is an algorithm that avoids dynamic obstacles through estimating the overall distribution of obstacles. FDEDWA estimates the distribution of obstacles through the FMF, and predicts the future distribution of obstacles. The FMF is derived to minimize the effect of the measurement noise through the Frobenius norm, and covariance matrix adaptation evolution strategy. The estimated information is used to derive the control input for the robust mobile robot navigation effectively. FDEDWA allows for the fast perception of the dynamic environment, and superior estimation performance, and the mobile robot can be controlled by a more optimal path while maintaining real-time performance. To demonstrate the performance of the proposed algorithm, simulations, and experiments were carried out under dynamic environments by comparing the latest dynamic window for dynamic obstacle, and the existing DWA.

Scene perception based visual navigation of mobile robot in indoor environment

Abstract: Only vision-based navigation is the key of cost reduction and widespread application of indoor mobile robot. Consider the unpredictable nature of artificial environments, deep learning techniques can be used to perform navigation with its strong ability to abstract image features. In this paper, we proposed a low-cost way of only vision-based perception to realize indoor mobile robot navigation, converting the problem of visual navigation to scene classification. Existing related research based on deep scene classification network has lower accuracy and brings more computational burden. Additionally, the navigation system has not yet been fully assessed in the previous work. Therefore, we designed a shallow convolutional neural network (CNN) with higher scene classification accuracy and efficiency to process images captured by a monocular camera. Besides, we proposed an adaptive weighted control (AWC) algorithm and combined with regular control (RC) to improve the robot's motion performance. We demonstrated the capability and robustness of the proposed navigation method by performing extensive experiments in both static and dynamic unknown environments. The qualitative and quantitative results showed that the system performs better compared to previous related work in unknown environments.

OFM-SLAM: A Visual Semantic SLAM for Dynamic Indoor Environments

Abstract: Most of the current visual Simultaneous Localization and Mapping (SLAM) algorithms are designed based on the assumption of a static environment, and their robustness and accuracy in the dynamic environment do not behave well. The reason is that moving objects in the scene will cause the mismatch of features in the pose estimation process, which further affects its positioning and mapping accuracy. In the meantime, the three-dimensional semantic map plays a key role in mobile robot navigation, path planning, and other tasks. In this paper, we present OFM-SLAM: Optical Flow combining MASK-RCNN SLAM, a novel visual SLAM for semantic mapping in dynamic indoor environments. Firstly, we use the Mask-RCNN network to detect potential moving objects which can generate masks of dynamic objects. Secondly, an optical flow method is adopted to detect dynamic feature points. Then, we combine the optical flow method and the MASK-RCNN for full dynamic points’ culling, and the SLAM system is able to track without these dynamic points. Finally, the semantic labels obtained from MASK-RCNN are mapped to the point cloud for generating a three-dimensional semantic map that only contains the static parts of the scenes and their semantic information. We evaluate our system in public TUM datasets. The results of our experiments demonstrate that our system is more effective in dynamic scenarios, and the OFM-SLAM can estimate the camera pose more accurately and acquire a more precise localization in the high dynamic environment.

Collaborative Complete Coverage and Path Planning for Multi-Robot Exploration

Abstract: In mobile robotics research, the exploration of unknown environments has always been an important topic due to its practical uses in consumer and military applications One specific interest of recent investigation is the field of complete coverage and path planning (CCPP) techniques for mobile robot navigation In this paper, we present a collaborative CCPP algorithms for single robot and multi-robot systems The incremental coverage from the robot movement is maximized by evaluating a new cost function A goal selection function is then designed to facilitate the collaborative exploration for a multi-robot system By considering the local gains from the individual robots as well as the global gain by the goal selection, the proposed method is able to optimize the overall coverage efficiency In the experiments, our CCPP algorithms are carried out on various unknown and complex environment maps The simulation results and performance evaluation demonstrate the effectiveness of the proposed collaborative CCPP technique

A Behavior-Based Mobile Robot Navigation Method with Deep Reinforcement Learning

Abstract: Deep reinforcement learning-based mobile robot navigation has attracted some recent interest. In the single-agent case, a robot can learn to navigate autonomously without a map of the environment. ...

A Standalone RFID-Based Mobile Robot Navigation Method Using Single Passive Tag

Abstract: This article proposes a standalone radio frequency identification (RFID)-based mobile robot navigation method, in which a mobile robot equipped with reader antennas can be continuously guided to a static object marked with a single passive UHF RFID tag. An observation model based on the RFID phase difference is built and integrated into a particle filter, by which the instantaneous relative position between the mobile robot and the tagged object can be detected in real time. Based on the position information extracted from the RFID system, the mobile robot adjusts its pose to move toward the RFID-tagged object. Compared with the existing RFID-based mobile robot navigation methods, the proposed method requires no external sensors other than the RFID and requires only a single passive tag. Experiments using commercial off-the-shelf (COTS) RFID devices are performed, and the results indicate that the mobile robot can satisfactorily realize navigation task with a distance accuracy of 4.04 cm and a bearing accuracy of 2.23°. The proposed method is well applicable for the navigation scenes in which the absolute position of the tagged target object is not known beforehand. Note to Practitioners —UHF radio frequency identification (RFID) has been widely applied as an asset management ID sensor in many fields. RFID-based mobile robot navigation technology can further increase its application value as a location sensor. This article proposes a standalone RFID-based mobile robot navigation method, in which the reference tag and the external sensors other than RFID are both not required. In the proposed method, only a single passive tag is attached to the static target object. Experimental results indicate that the proposed method can enable navigation task with good performance in situations in which the absolute navigation goal position is not known in advance.

A Reusable Generalized Voronoi Diagram Based Feature Tree for Fast Robot Motion Planning in Trapped Environments

Abstract: The sampling-based partial motion planning algorithm has been widely applied in real-time mobile robot navigation for its computational savings and its flexibility in avoiding obstacles. However, in some complex environments, partial planning algorithms are prone to fall into traps, resulting in the failure of motion planning. This paper proposes a feature tree algorithm based on Generalized Voronoi Diagram (GVD) to generate heuristic paths to guide partial motion planning. A GVD feature extraction algorithm is proposed to reduce the redundancy in the representation of obstacle-free regions and improve the searching efficiency in heuristic planning process. The feature node set guarantees that any node from obstacle-free regions can be connected to at least one feature node without any collision. For one map, the feature nodes only need to be extracted once and then can be reused in different scenarios on the same map. Thus, the feature extraction can be executed off-line. Based on GVD feature nodes, a feature tree is reported to generate a heuristic path and the nodes on the heuristic path are utilized sequentially as sub-goals to guide the partial motion planning. When the target changes, the feature tree can quickly replan a new heuristic path. The experimental studies reveal that our proposed method can significantly improve the robot motion planning efficiency and the navigation success rate in trapped environments.

Evaluation of mapping and path planning for non-holonomic mobile robot navigation in narrow pathway for agricultural application

Abstract: This paper evaluates mapping and path planning methods for mobile robot with non-holonomic constraint in the narrow pathways. Selection of sensors such as depth camera or LiDAR sensor is complex problem as it depends on applications, demand for cost, robustness and data processing. Along with sensor selection map generation is essential task for mobile robot navigation. This paper presents experimental evaluation of laser-based mapping algorithm i.e., Gmapping and vision based mapping i.e., RTAB-Map. The platform used for autonomous navigation is mobile robot with nonholonomic constraint. The path planning for mobile robot with non-holonomic constraint is more complex as not all arbitrary trajectories are kinematically feasible. The application of mobile robot navigation is to transfer agriculture products in greenhouse from one place to another. Generally, the pathways of greenhouse are narrow, which often results in the planner failing to generate a traversable trajectory if the mobile robot is restricted to forward movement, hence the switchback (forward and backward) path planning is essential to navigate in such environments. In the following discussion, we implement the Reeds-Shepp curve based path planning for mobile robot with a non-holonomic constraint to navigate in narrow pathways. Reeds-Shepp curve can generate various combinations of such switch-back trajectories and it remains unmatched in terms of computation efficiency and reliability compared to other curves. Effectiveness of the proposed path planning method is validated experimentally.

A CNN-Based System for Mobile Robot Navigation in Indoor Environments via Visual Localization with a Small Dataset

Abstract: Deep learning has made great advances in the field of image processing, which allows automotive devices to be more widely used in humans’ daily lives than ever before. Nowadays, the mobile robot navigation system is among the hottest topics that researchers are trying to develop by adopting deep learning methods. In this paper, we present a system that allows the mobile robot to localize and navigate autonomously in the accessible areas of an indoor environment. The proposed system exploits the Convolutional Neural Network (CNN) model’s advantage to extract data feature maps for image classification and visual localization, which attempts to precisely determine the location region of the mobile robot focusing on the topological maps of the real environment. The system attempts to precisely determine the location region of the mobile robot by integrating the CNN model and topological map of the robot workspace. A dataset with small numbers of images is acquired from the MYNT EYE camera. Furthermore, we introduce a new loss function to tackle the bounded generalization capability of the CNN model in small datasets. The proposed loss function not only considers the probability of the input data when it is allocated to its true class but also considers the probability of allocating the input data to other classes rather than its actual class. We investigate the capability of the proposed system by evaluating the empirical studies based on provided datasets. The results illustrate that the proposed system outperforms other state-of-the-art techniques in terms of accuracy and generalization capability.

An Efficient and Robust Improved A* Algorithm for Path Planning

Abstract: Path planning plays an essential role in mobile robot navigation, and the A* algorithm is one of the best-known path planning algorithms. However, the conventional A* algorithm and the subsequent improved algorithms still have some limitations in terms of robustness and efficiency. These limitations include slow algorithm efficiency, weak robustness, and collisions when robots are traversing. In this paper, we propose an improved A*-based algorithm called EBHSA* algorithm. The EBHSA* algorithm introduces the expansion distance, bidirectional search, heuristic function optimization and smoothing into path planning. The expansion distance extends a certain distance from obstacles to improve path robustness by avoiding collisions. Bidirectional search is a strategy that searches for a path from the start node and from the goal node at the same time. Heuristic function optimization designs a new heuristic function to replace the traditional heuristic function. Smoothing improves path robustness by reducing the number of right-angle turns. Moreover, we carry out simulation tests with the EBHSA* algorithm, and the test results show that the EBHSA* algorithm has excellent performance in terms of robustness and efficiency. In addition, we transplant the EBHSA* algorithm to a robot to verify its effectiveness in the real world.

Online path planning of mobile robot using grasshopper algorithm in a dynamic and unknown environment

Abstract: The navigation of mobile robots using heuristic algorithms is one of the important issues in computer and control sciences. Path planning and obstacle avoidance are current topics of navigational c...

Using Ultrasonic Sensors and a Knowledge-Based Neural Fuzzy Controller for Mobile Robot Navigation Control

Abstract: This study proposes a knowledge-based neural fuzzy controller (KNFC) for mobile robot navigation control. An effective knowledge-based cultural multi-strategy differential evolution (KCMDE) is used for adjusting the parameters of KNFC. The KNFC is applied in PIONEER 3-DX mobile robots to achieve automatic navigation and obstacle avoidance capabilities. A novel escape approach is proposed to enable robots to autonomously avoid special environments. The angle between the obstacle and robot is used and two thresholds are set to determine whether the robot entries into the special landmarks and to modify the robot behavior for avoiding dead ends. The experimental results show that the proposed KNFC based on the KCMDE algorithm has improved the learning ability and system performance by 15.59% and 79.01%, respectively, compared with the various differential evolution (DE) methods. Finally, the automatic navigation and obstacle avoidance capabilities of robots in unknown environments were verified for achieving the objective of mobile robot control.

Path Planning Approaches for Mobile Robot Navigation in Various Environments: A Review

Abstract: This paper presents an extensive study of different methods/approaches applied for mobile robot navigation in static as well as in dynamic environments. Mobile robot navigation mainly comprises of four basic steps, i.e. sensing, locomotion/positioning, motion control, and route planning. The shortest/optimal on-time collision-free path is the major issues for robot navigation. Numerous techniques/methods are adopted to tackle the path planning problems in the presence of obstacles prone scenarios to get an optimal/near optimal path, which is the major challenges in robotics research. Path planning techniques can be categorized into two main groups (i.e. classical and heuristic techniques) and further, subcategorized as online and offline navigation methods. The strengths and drawbacks of various techniques are reviewed thoroughly and highlighted in this paper. The literature survey reveals that the hybridization of heuristic approaches are more popular and widely used for path planning of mobile robots as compared to classical methods. This paper describes a comparative study and utilizing frequencies of different techniques used for mobile robot path planning and gives an clear idea/guides for improvement in path planning strategy particularly for smoothening of path navigation.

Autonomous Mobile Robot Navigation in Sparse LiDAR Feature Environments

Abstract: In the industrial environment, Autonomous Guided Vehicles (AGVs) generally run on a planned route. Among trajectory-tracking algorithms for unmanned vehicles, the Pure Pursuit (PP) algorithm is prevalent in many real-world applications because of its simple and easy implementation. However, it is challenging to decelerate the AGV’s moving speed when turning on a large curve path. Moreover, this paper addresses the kidnapped-robot problem occurring in spare LiDAR environments. This paper proposes an improved Pure Pursuit algorithm so that the AGV can predict the trajectory and decelerate for turning, thus increasing the accuracy of the path tracking. To solve the kidnapped-robot problem, we use a learning-based classifier to detect the repetitive pattern scenario (e.g., long corridor) regarding 2D LiDAR features for switching the localization system between Simultaneous Localization And Mapping (SLAM) method and Odometer method. As experimental results in practice, the improved Pure Pursuit algorithm can reduce the tracking error while performing more efficiently. Moreover, the learning-based localization selection strategy helps the robot navigation task achieve stable performance, with 36.25% in completion rate more than only using SLAM. The results demonstrate that the proposed method is feasible and reliable in actual conditions.

An hybridization of global-local methods for autonomous mobile robot navigation in partially-known environments

Abstract: This paper deals with the navigation problem of an autonomous non-holonomic mobile robot in partially-known environment. In this proposed method, the entire process of navigation is divided into two phases: an off-line phase on which a distance-optimal reference trajectory enables the mobile robot to move from an initial position to a desired target which is planned using the B-spline method and the Dijkstra algorithm. In the online phase of the navigation process, the mobile robot follows the planned trajectory using a sliding mode controller with the ability of avoiding unexpected obstacles by the use of fuzzy logic controller. Also, the fuzzy logic and fuzzy wall-following controllers are used to accomplish the reactive navigation mission (path tracking and obstacle avoidance) for a comparative purpose. Simulation results prove that the proposed path planning method (B-spline) is simple and effective. Also, they attest that the sliding mode controller track more precisely the reference trajectory than the fuzzy logic controller (in terms of time elapsed to reach the target and stability of two wheels velocity) and this last gives best results than the wall-following controller in the avoidance of unexpected obstacles. Thus, the effectiveness of our proposed approach (B-spline method combined with sliding mode and fuzzy logic controllers) is proved compared to other techniques.

Mapless LiDAR Navigation Control of Wheeled Mobile Robots Based on Deep Imitation Learning

Abstract: This paper addresses the problems related to the mapless navigation control of wheeled mobile robots based on deep learning technology. The traditional navigation control framework is based on a global map of the environment, and its navigation performance depends on the quality of the global map. In this paper, we proposes a mapless Light Detection and Ranging (LiDAR) navigation control method for wheeled mobile robots based on deep imitation learning. The proposed method is a data-driven control method that directly uses LiDAR sensors and relative target position for mobile robot navigation control. A deep convolutional neural network (CNN) model is proposed to predict motion control commands of the mobile robot without the requirement of the global map to achieve navigation control of the mobile robot in unknown environments. While collecting the training dataset, we manipulated the mobile robot to avoid obstacles through manual control and recorded the raw data of the LiDAR sensor, the relative target position, and the corresponding motion control commands. Next, we applied a data augmentation method on the recorded samples to increase the number of training samples in the dataset. In the network model design, the proposed CNN model consists of a LiDAR CNN module to extract LiDAR features and a motion prediction module to predict the motion behavior of the robot. In the model training phase, the proposed CNN model learns the mapping between the input sensor data and the desired motion behavior through end-to-end imitation learning. Experimental results show that the proposed mapless LiDAR navigation control method can safely navigate the mobile robot in four unseen environments with an average success rate of 75%. Therefore, the proposed mapless LiDAR navigation control system is effective for robot navigation control in an unknown environment without the global map.

Occupancy Map Inpainting for Online Robot Navigation

Abstract: In this work, we focus on mobile robot navigation in indoor environments where occlusions and field-of-view limitations hinder onboard sensing capabilities. We show that the footprint of a camera mounted on a robot can be drastically improved using learning-based approaches. Specifically, we consider the task of building an occupancy map for autonomous navigation of a robot equipped with a depth camera. In our approach, a local occupancy map is first computed using measurements from the camera directly. Afterwards, an inpainting network adds further information, the occupancy probabilities of unseen grid cells, to the map. A novel aspect of our approach is that rather than direct supervision from ground truth, we combine the information from a second camera with a better field-of-view for supervision. The training focuses on predicting extensions of the sensed data. To test the effectiveness of our approach, we use a robot setup with a single camera placed at 0.5m above the ground. We compare the navigation performance using raw maps from only this camera’s input (baseline) versus using inpainted maps augmented with our network. Our method outperforms the baseline approach even in completely new environments not included in the training set and can yield 21% shorter paths than the baseline approach. A real-time implementation of our method on a mobile robot is also tested in home and office environments.

Goal-Driven Autonomous Exploration Through Deep Reinforcement Learning

Abstract: In this paper, we present an autonomous navigation system for goal-driven exploration of unknown environments through deep reinforcement learning (DRL). Points of interest (POI) for possible navigation directions are obtained from the environment and an optimal waypoint is selected, based on the available data. Following the waypoints, the robot is guided towards the global goal and the local optimum problem of reactive navigation is mitigated. Then, a motion policy for local navigation is learned through a DRL framework in a simulation. We develop a navigation system where this learned policy is integrated into a motion planning stack as the local navigation layer to move the robot between waypoints towards a global goal. The fully autonomous navigation is performed without any prior knowledge while a map is recorded as the robot moves through the environment. Experiments show that the proposed method has an advantage over similar exploration methods, without reliance on a map or prior information in complex static as well as dynamic environments.

Interval Type-2 Fuzzy Dynamic Parameter Adaptation in Bee Colony Optimization for Autonomous Mobile Robot Navigation

Abstract: This paper describes a comparative study of Interval Type-2 Membership Functions applied for dynamic parameter adaptation in Bee Colony Optimization Algorithm for the controlling of the trajectory in an autonomous mobile robot. The main goal of the work is comparing the impact of the results when different Interval Type-2 Membership Functions are used in this study case to adapt some parameters of bee colony optimization (BCO) algorithm. Two trajectories are optimized to test the methods. Perturbation is added in the model, and a comparative study is performed.

Mobile Robot Navigation Based on Deep Reinforcement Learning with 2D-LiDAR Sensor using Stochastic Approach

Abstract: In recent years, there has been a significant progress in mobile robotics and their applications in different fields. Currently, mobile robots are employed for applications such as service robots for delivery, exploration, mapping, search and rescue, and warehouses. Recent advances in computing efficiency and machine learning algorithms have increased the variations of intelligent robots that can navigate autonomously using sensor data. Particularly, reinforcement learning has recently enjoyed a wide variety of success in controlling the robot motion in an unknown environment. However, most of the reinforcement learning-based navigation gets the path plan with a deterministic method, which results in some errors. Therefore, we present a navigation policy for a mobile robot equipped with a 2D range sensor based on the Proximal Policy Optimization of a stochastic approach. The tested algorithm also includes a stochastic operation, which simplifies the policy network model. We trained a differential drive robot in multiple training environments, and based on such stochastic learning, the training data accumulates faster than before. We tested our algorithm in a virtual environment and present the results of successful planning and navigation for mobile robots.

Hexagonal Grid-Based Framework for Mobile Robot Navigation

Abstract: The paper addresses the problem of mobile robots’ navigation using a hexagonal lattice. We carried out experiments in which we used a vehicle equipped with a set of sensors. Based on the data, a traversable map was created. The experimental results proved that hexagonal maps of an environment can be easily built based on sensor readings. The path planning method has many advantages: the situation in which obstacles surround the position of the robot or the target is easily detected, and we can influence the properties of the path, e.g., the distance from obstacles or the type of surface can be taken into account. A path can be smoothed more easily than with a rectangular grid.

An Investigation of Bug Algorithms for Mobile Robot Navigation and Obstacle Avoidance in Two-Dimensional Unknown Static Environments

Abstract: A significant problem in mobile robot navigation is obstacle avoidance in an unknown environment. Though there are efficient global path planning algorithms for known environments, they are not feasible in layouts where the robot does not have a comprehensive knowledge about the obstacle locations. Bug Algorithms are navigation and obstacle avoidance algorithms that can be implemented in a 2D environment with previously unknown static obstacles. The Bug family of algorithms includes some of the most fundamental navigation and obstacle avoidance algorithms which are still used at a higher level in any mobile robot navigation problem. In this paper, three algorithms belonging to the Bug algorithm family have been implemented with Python3 software and the results have been compared against each other with cost of the path and the computational time as criteria. Finally, the probability density functions were plotted and the relative performances of three Bug algorithms which are Bug0, Bug1 and Bug2, were compared using simulations with varying parameters and layouts.

A Knowledge-Based Fast Motion Planning Method Through Online Environmental Feature Learning

Abstract: The sampling-based partial motion planning algorithm has come into widespread application in dynamic mobile robot navigation due to its low calculation costs and excellent performance in avoiding obstacles. However, when confronted with complicated scenarios, the motion planning algorithms are easily caught in traps. In order to solve this problem, this paper proposes a knowledge-based fast motion planning algorithm based on Risk-RRT, which guides motion planning by constructing a topological feature tree and generating a heuristic path from the tree. Firstly, an online topological feature learning method is proposed to simultaneously extract the features during the motion of the robot by means of the dual-channel scale filter and the secondary distance fusion. The learning process is completed until the feature points can represent arbitrary obstacle-free grid points of the whole map. Secondly, the topological feature tree is constructed with environmental feature points and the heuristic motion planning can be carried out on the feature tree. For one map, once the construction of the feature tree finishes, it can be reused as a prior knowledge in the following heuristic motion planning process, which will further improve the efficiency of searching feasible paths. The experimental results demonstrate that our proposed method can remarkably reduce the time taken to find a heuristic path and enhance the success rate of navigation in trapped environments.