Success Rate Of Navigation Research Articles

Vision-and-language navigation based on history-aware cross-modal feature fusion in indoor environment

Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate an indoor environment using natural language instructions. Traditional VLN employs cross-modal feature fusion, where visual and textual information are combined to guide the agent’s navigation. However, incomplete use of perceptual information, scarcity of domain-specific training data, and diverse image and language inputs result in suboptimal performance. Herein, we propose a cross-modal feature fusion VLN history-aware information, that leverages an agent’s past experiences to make more informed navigation decisions. The regretful model and self-monitoring models are added, and the advantage actor critic(A2C) reinforcement learning algorithm is employed to improve the navigation success rate, reduce action redundancy, and shorten navigation paths. Subsequently, a data augmentation method based on speaker data is introduced to improve the model generalizability. We evaluate the proposed algorithm on the room-to-room (R2R) and room-for-room (R4R) benchmarks, and the experimental results demonstrate that, by comparison, the proposed algorithm outperforms state-of-the-art methods.

Research on deep reinforcement learning-based complex crowd navigation algorithm using risk perception and path selection

Abstract Aiming at the Frozen Robot Problem and the poor effect of dynamic obstacle avoidance in traditional navigation methods when encountering dynamic obstacles, a deep reinforcement learning navigation method based on risk perception and path selection is proposed. The core of this method lies in CP (Collision Probability) module and IOU (Intersection over Union) module. The CP module calculates the CP between the robot and the nearby dynamic obstacles in real time, so that the robot can avoid the dangerous obstacles first. At the same time, the intersection-merging ratio module calculates the “pass ability” of the area near the robot in real time, and guides the robot to choose a safer area to pass through. Compared with the DRL method without these two modules, the proposed method achieves the highest navigation success rate in all simulation test environments, and the maximum improvement rate is 11%. At the same time, it still has advantages in navigation time and other indicators.

Preoperative localization of pulmonary nodules by electromagnetic navigation bronchoscopy combined with methylene blue injection.

Electromagnetic navigation bronchoscopy (ENB) can help to accurately locate pulmonary nodules using a minimally invasive approach. This study sought to evaluate the clinical efficacy and safety of dye marking localization under the guidance of ENB followed by surgery. A retrospective analysis was performed of 61 patients who underwent ENB localization using methylene blue dye marking before surgery at Shanghai General Hospital from October 2021 to February 2022. The clinical efficacy and safety of ENB localization and the related factors affecting the navigation time of ENB location were analyzed. ENB was performed on 170 pulmonary nodules in 61 patients with a median age of 60 [interquartile range (IQR), 18] years. The majority of patients (70.69%) had more than two pulmonary nodules. The median maximum nodule diameter was 10 (IQR, 8) mm, and 48.21% of the nodules were mixed ground-glass nodules. Median time for ENB navigation was 10.5 (IQR, 6) min. The navigation success rate was 92.96%, and the ENB location success rate was 95.89%. The rate of complications related to ENB localization was 1.64% (there was only one case of pulmonary hemorrhage). The multivariate analysis showed that the factors related to the navigation time included the node location (P=0.001) and location mode (P=0.04). ENB-guided methylene blue injection is an effective and safe tool for localizing and marking pulmonary nodules, and can be used to assist the diagnosis and treatment of early lung cancer. The node location and location mode had significant effects on navigation time.

Mapless Path Planning for Mobile Robot Based on Improved Deep Deterministic Policy Gradient Algorithm.

In the traditional Deep Deterministic Policy Gradient (DDPG) algorithm, path planning for mobile robots in mapless environments still encounters challenges regarding learning efficiency and navigation performance, particularly adaptability and robustness to static and dynamic obstacles. To address these issues, in this study, an improved algorithm frame was proposed that designs the state and action spaces, and introduces a multi-step update strategy and a dual-noise mechanism to improve the reward function. These improvements significantly enhance the algorithm's learning efficiency and navigation performance, rendering it more adaptable and robust in complex mapless environments. Compared to the traditional DDPG algorithm, the improved algorithm shows a 20% increase in the stability of the navigation success rate with static obstacles along with a 25% reduction in pathfinding steps for smoother paths. In environments with dynamic obstacles, there is a remarkable 45% improvement in success rate. Real-world mobile robot tests further validated the feasibility and effectiveness of the algorithm in true mapless environments.

Mars Exploration: Research on Goal-Driven Hierarchical DQN Autonomous Scene Exploration Algorithm

In the non-deterministic, large-scale navigation environment under the Mars exploration mission, there is a large space for action and many environmental states. Traditional reinforcement learning algorithms that can only obtain rewards at target points and obstacles will encounter the problems of reward sparsity and dimension explosion, making the training speed too slow or even impossible. This work proposes a deep layered learning algorithm based on the goal-driven layered deep Q-network (GDH-DQN), which is more suitable for mobile robots to explore, navigate, and avoid obstacles without a map. The algorithm model is designed in two layers. The lower layer provides behavioral strategies to achieve short-term goals, and the upper layer provides selection strategies for multiple short-term goals. Use known position nodes as short-term goals to guide the mobile robot forward and achieve long-term obstacle avoidance goals. Hierarchical execution not only simplifies tasks but also effectively solves the problems of reward sparsity and dimensionality explosion. In addition, each layer of the algorithm integrates a Hindsight Experience Replay mechanism to improve performance, make full use of the goal-driven function of the node, and effectively avoid the possibility of misleading the agent by complex processes and reward function design blind spots. The agent adjusts the number of model layers according to the number of short-term goals, further improving the efficiency and adaptability of the algorithm. Experimental results show that, compared with the hierarchical DQN method, the navigation success rate of the GDH-DQN algorithm is significantly improved, and it is more suitable for unknown scenarios such as Mars exploration.

A Soft Actor-Critic Deep Reinforcement-Learning-Based Robot Navigation Method Using LiDAR

When there are dynamic obstacles in the environment, it is difficult for traditional path-generation algorithms to achieve desired obstacle-avoidance results. To solve this problem, we propose a robot navigation control method based on SAC (Soft Actor-Critic) Deep Reinforcement Learning. Firstly, we use a fast path-generation algorithm to control the robot to generate expert trajectories when the robot encounters danger as well as when it approaches a target, and we combine SAC reinforcement learning with imitation learning based on expert trajectories to improve the safety of training. Then, for the hybrid data consisting of agent data and expert data, we use an improved prioritized experience replay method to improve the learning efficiency of the policies. Finally, we introduce RNN (Recurrent Neural Network) units into the network structure of the SAC Deep Reinforcement-Learning navigation policy to improve the agent’s transfer inference ability in a new environment and obstacle-avoidance ability in dynamic environments. Through simulation and practical experiments, it is fully verified that our method has a higher training efficiency and navigation success rate compared to state-of-the-art reinforcement-learning algorithms, which further enhances the obstacle-avoidance capability of the robot system.

Collaborative approach for swarm robot systems based on distributed DRL

Navigation and task allocation for swarm robot systems are more difficult than for a single robot. In swarm robot systems, navigation and task allocation difficulties are compounded by challenges such as a dynamic environment, exponentially increasing complexity, and collaboration. In this study, a deep reinforcement learning (DRL) based collaborative approach for navigation and task allocation is proposed, which can be trained at the same time as the training time of a single robot and achieve a high success rate. The proposed approach implements DRL as a distributed architecture. Furthermore, the proposed approach uses adaptive reward mechanisms, a leaderless control approach for environment control, and a simultaneous learning approach for learning. The proposed approach is evaluated by the success rate of reaching the target, the success rate of reaching the target by the shortest path, the success rate of selecting a task, and the success rate of selecting the nearest task. In addition, the costs of the non-collaborative approach are compared with the costs of the collaborative approach. The evaluations show that the success rate of navigation and collaboration of the robots increased and the cost decreased. Thus, the performance of the proposed approach is verified.

Diagnostic yield of cone beam CT based navigation bronchoscopy in patients with metastatic lesions: A propensity score matched case-control study

BackgroundCone beam CT based Navigation Bronchoscopy (CBCT-NB) has predominantly been investigated as a diagnostic tool in (suspected) primary lung cancers. Small metastatic lesions are clinically considered more challenging to diagnose, but no study has explored the yield of navigation bronchoscopy in patients with pulmonary metastatic lesions (ML) compared to primary lung cancers (PL), correcting for known lesion characteristics affecting diagnostic yield. Materials and methodsThis is a single-center, retrospective, propensity score-matched case-control study. We matched a subset of patients who underwent CBCT-NB and received a final diagnosis of pulmonary metastases of solid tumors between December 2017 and 2021 against confirmed primary lung cancer lesions subjected to CBCT-NB in the same time period. The lesions were propensity score matched based on known characteristics affecting yield, including location (upper lobe, lower lobe), size, bronchus sign, and lesion solidity. ResultsFifty-six metastatic pulmonary lesions (mean size 14.7 mm) were individually case-matched to a selection of 297 available primary lung cancer lesions. Case-matching revealed non-significant differences in navigation success rate (PL: 89.3 % vs. ML: 82.1 %, 95%CI on differences: −21.8 to +7.5) and yield (PL: 60.7 % vs. ML: 55.4 %, 95%CI on differences: −25.4 to +14.7). The overall complication rate was comparable (5.4 % in PL vs. 5,4 % in ML). ConclusionAfter matching primary and metastatic lesions based on CT assessable lesions characteristics, CBCT-NB showed no clinically relevant or significantly different navigation success or yield in either group. We recommend a careful assessment of CT characteristics to determine procedural difficulty rather than selecting based on the suspicion of lesion origin.

A Review of Brain-Inspired Cognition and Navigation Technology for Mobile Robots

Brain-inspired navigation technologies combine environmental perception, spatial cognition, and target navigation to create a comprehensive navigation research system. Researchers have used various sensors to gather environmental data and enhance environmental perception using multimodal information fusion. In spatial cognition, a neural network model is used to simulate the navigation mechanism of the animal brain and to construct an environmental cognition map. However, existing models face challenges in achieving high navigation success rate and efficiency. In addition, the limited incorporation of navigation mechanisms borrowed from animal brains necessitates further exploration. On the basis of the brain-inspired navigation process, this paper launched a systematic study on brain-inspired environment perception, brain-inspired spatial cognition, and goal-based navigation in brain-inspired navigation, which provides a new classification of brain-inspired cognition and navigation techniques and a theoretical basis for subsequent experimental studies. In the future, brain-inspired navigation technology should learn from more perfect brain-inspired mechanisms to improve its generalization ability and be simultaneously applied to large-scale distributed intelligent body cluster navigation. The multidisciplinary nature of brain-inspired navigation technology presents challenges, and multidisciplinary scholars must cooperate to promote the development of this technology.

Deep Learning-Based Visual Navigation Algorithms for Mobile Robots: A Comprehensive Study

This research addresses the challenges faced by mobile robots in efficiently navigating complex environments. A novel approach is proposed, leveraging deep learning techniques, and introducing the Neo model. The method combines Split Attention with the Res-NeSt50 network to enhance the recognition accuracy of key features in the observed images. Furthermore, improvements have been made in the loss calculation method to improve navigation accuracy across different scenarios. Evaluations conducted on AI2-THOR and active vision datasets demonstrate that the improved model achieves higher average navigation accuracy (92.3%) in scene 4 compared to other methods. The success rate of navigation reached 36.8%, accompanied by a 50% reduction in ballistic length. Additionally, compared to HAUSR and LSTM-Nav, this technology significantly reduced collision rates to 0.01 and reduced time consumption by over 8 seconds. The research methodology addresses navigation model accuracy, speed, and generalization issues, thus making significant advancements for intelligent autonomous robots.

Risk-Aware Deep Reinforcement Learning for Robot Crowd Navigation

Ensuring safe and efficient navigation in crowded environments is a critical goal for assistive robots. Recent studies have emphasized the potential of deep reinforcement learning techniques to enhance robots’ navigation capabilities in the presence of crowds. However, current deep reinforcement learning methods often face the challenge of robots freezing as crowd density increases. To address this issue, a novel risk-aware deep reinforcement learning approach is proposed in this paper. The proposed method integrates a risk function to assess the probability of collision between the robot and pedestrians, enabling the robot to proactively prioritize pedestrians with a higher risk of collision. Furthermore, the model dynamically adjusts the fusion strategy of learning-based and risk-aware-based features, thereby improving the robustness of robot navigation. Evaluations were conducted to determine the effectiveness of the proposed method in both low- and high-crowd density settings. The results exhibited remarkable navigation success rates of 98.0% and 93.2% in environments with 10 and 20 pedestrians, respectively. These findings emphasize the robust performance of the proposed method in successfully navigating through crowded spaces. Additionally, the approach achieves navigation times comparable to those of state-of-the-art methods, confirming its efficiency in accomplishing navigation tasks. The generalization capability of the method was also rigorously assessed by subjecting it to testing in crowd environments exceeding the training density. Notably, the proposed method attains an impressive navigation success rate of 90.0% in 25-person environments, surpassing the performance of existing approaches and establishing itself as a state-of-the-art solution. This result highlights the versatility and effectiveness of the proposed method in adapting to various crowd densities and further reinforces its applicability in real-world scenarios.

Optimization-based local planner for a nonholonomic autonomous mobile robot in semi-structured environments

This paper proposes an optimization-based adaptive local planner to address the aggressive motion planning problem of an autonomous mobile robot in realistic semi-structured scenarios. The goal is to enable the robot to perform autonomous navigation tasks at the limit of its speed capability to maximize the efficiency, while ensuring safety and feasibility. The proposed approach constitutes an integrated scheme that leverages real-time hierarchical collision avoidance constraints reformulation and handles the heterogeneous constraints using a unified nonlinear optimization. An aggressiveness adaption method is employed to cope with disturbances instead of relying on excessive obstacle inflation, resulting in reduced conservatism while enhancing safety. The efficacy of the proposed method is demonstrated through simulation and experimental results. Compared with previous work, the proposed approach provides significant improvements in navigation success rate without sacrificing the task efficiency.

Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment

PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with near-perfect success rate in photo-realistically simulated environments, under the assumptions with noiseless actuation and most importantly, perfect localization with GPS and compass sensors. However, accurate GPS signalis difficult to be obtained in real indoor environment. To improve the PointGoal navigation accuracy without GPS signal, we use visual odometry (VO) and propose a novel action integration module (AIM) trained in unsupervised manner. Sepecifically, unsupervised VO computes the relative pose of the agent from the re-projection error of two adjacent frames, and then replaces the accurate GPS signal with the path integration. The pseudo position estimated by VO is used to train action integration which assists agent to update their internal perception of location and helps improve the success rate of navigation. The training and inference process only use RGB, depth, collision as well as self-action information. The experiments show that the proposed system achieves satisfactory results and outperforms the partially supervised learning algorithms on the popular Gibson dataset.

Mapless Navigation With Safety-Enhanced Imitation Learning

Mapless navigation is a popular approach for guiding a robot in an unknown environment. However, current learning based methods for mapless navigation cannot guarantee safe exploration during training. In this article, we aim to safely train a mapless navigation policy with 2D lidar inputs using Imitation Learning (IL). We propose a novel IL training scheme based on the dataset aggregation (DAgger) with extra safety enhancement. In order to avoid collisions during training, we design a controlled exploration strategy for demonstration data collection. In this strategy, the output of the novice and expert policy are fused adaptively to control the robot. In order to improve the obstacle avoidance capability of the trained policy, we design a safety-enhanced loss function for network training. This proposed loss function focuses on the obstacle avoidance by prioritizing the training samples collected in different states. In addition, inspired by the symmetrical pattern of the navigation task, we propose a new data augmentation technique which increases the training speed significantly. In both simulation and real-world experiments, our method demonstrates remarkable performance in terms of training safety and navigation success rate compared with other IL-based approaches. Videos of our experiments are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://www.youtube.com/watch?v=s6leZ2RR3Os</uri> .

Layout-Aware Dreamer for Embodied Visual Referring Expression Grounding

In this work, we study the problem of Embodied Referring Expression Grounding, where an agent needs to navigate in a previously unseen environment and localize a remote object described by a concise high-level natural language instruction. When facing such a situation, a human tends to imagine what the destination may look like and to explore the environment based on prior knowledge of the environmental layout, such as the fact that a bathroom is more likely to be found near a bedroom than a kitchen. We have designed an autonomous agent called Layout-aware Dreamer (LAD), including two novel modules, that is, the Layout Learner and the Goal Dreamer to mimic this cognitive decision process. The Layout Learner learns to infer the room category distribution of neighboring unexplored areas along the path for coarse layout estimation, which effectively introduces layout common sense of room-to-room transitions to our agent. To learn an effective exploration of the environment, the Goal Dreamer imagines the destination beforehand. Our agent achieves new state-of-the-art performance on the public leaderboard of REVERIE dataset in challenging unseen test environments with improvement on navigation success rate (SR) by 4.02% and remote grounding success (RGS) by 3.43% comparing to previous previous state of the art. The code is released at https://github.com/zehao-wang/LAD.

INSUS: Indoor Navigation System Using Unity and Smartphone for User Ambulation Assistance

Currently, outdoor navigation systems have widely been used around the world on smartphones. They rely on GPS (Global Positioning System). However, indoor navigation systems are still under development due to the complex structure of indoor environments, including multiple floors, many rooms, steps, and elevators. In this paper, we present the design and implementation of the Indoor Navigation System using Unity and Smartphone (INSUS). INSUS shows the arrow of the moving direction on the camera view based on a smartphone’s augmented reality (AR) technology. To trace the user location, it utilizes the Simultaneous Localization and Mapping (SLAM) technique with a gyroscope and a camera in a smartphone to track users’ movements inside a building after initializing the current location by the QR code. Unity is introduced to obtain the 3D information of the target indoor environment for Visual SLAM. The data are stored in the IoT application server called SEMAR for visualizations. We implement a prototype system of INSUS inside buildings in two universities. We found that scanning QR codes with the smartphone perpendicular in angle between 60∘ and 100∘ achieves the highest QR code detection accuracy. We also found that the phone’s tilt angles influence the navigation success rate, with 90∘ to 100∘ tilt angles giving better navigation success compared to lower tilt angles. INSUS also proved to be a robust navigation system, evidenced by near identical navigation success rate results in navigation scenarios with or without disturbance. Furthermore, based on the questionnaire responses from the respondents, it was generally found that INSUS received positive feedback and there is support to improve the system.

Recurrent neural networks for generalization towards the vessel geometry in autonomous endovascular guidewire navigation in the aortic arch

PurposeEndovascular intervention is the state-of-the-art treatment for common cardiovascular diseases, such as heart attack and stroke. Automation of the procedure may improve the working conditions of physicians and provide high-quality care to patients in remote areas, posing a major impact on overall treatment quality. However, this requires the adaption to individual patient anatomies, which currently poses an unsolved challenge.MethodsThis work investigates an endovascular guidewire controller architecture based on recurrent neural networks. The controller is evaluated in-silico on its ability to adapt to new vessel geometries when navigating through the aortic arch. The controller’s generalization capabilities are examined by reducing the number of variations seen during training. For this purpose, an endovascular simulation environment is introduced, which allows guidewire navigation in a parametrizable aortic arch.ResultsThe recurrent controller achieves a higher navigation success rate of 75.0% after 29,200 interventions compared to 71.6% after 156,800 interventions for a feedforward controller. Furthermore, the recurrent controller generalizes to previously unseen aortic arches and is robust towards size changes of the aortic arch. Being trained on 2048 aortic arch geometries gives the same results as being trained with full variation when evaluated on 1000 different geometries. For interpolation a gap of 30% of the scaling range and for extrapolation additional 10% of the scaling range can be navigated successfully.ConclusionAdaption to new vessel geometries is essential in the navigation of endovascular instruments. Therefore, the intrinsic generalization to new vessel geometries poses an essential step towards autonomous endovascular robotics.

A Gaussian Mixture Model Based Fast Motion Planning Method Through Online Environmental Feature Learning

Rapidly-exploring Random Tree (RRT) and its applications for mobile robot navigation have attracted extensive interest in human-robot interaction environments. However, most current sampling-based motion planning algorithms are easy to fall into the trap space in complex and dynamic environments. In this paper, a fast motion planning algorithm based on Gaussian Mixture Model is proposed to allow robotic systems to efficiently extract feature nodes and generate cheuristic paths considering the pedestrian density and the environmental structure. Firstly, the preliminary feature nodes are obtained by training GMM, in which the covariance matrix of each feature node contains the environmental structure information. Secondly, an online feature learning method is presented to extract features during the movement of the robot by the dual-channel scale filter and the secondary distance fusion. Once the free grids can be connected to the feature nodes without any collision, a heuristic path is generated directly to guide the robot to avoid the crowds according to the proposed pedestrian matrix. For the same environment, the learned information can be reused as prior knowledge in the next path planning to further improve the efficiency of re-planning. A series of experimental studies demonstrate that our proposed method can remarkably reduce the time and enhance the success rate of navigation in trapped and narrow environments.

Diagnostic Performance of Electromagnetic Navigation versus Virtual Navigation Bronchoscopy-Guided Biopsy for Pulmonary Lesions in a Single Institution: Potential Role of Artificial Intelligence for Navigation Planning.

Navigation bronchoscopy is an emerging technique used to evaluate pulmonary lesions. Using Veran's SPiN electromagnetic navigation bronchoscopy (ENB) and Archimedes virtual bronchoscopy navigation (VBN), this study aimed to compare the accuracy and safety of these procedures for lung lesions and to identify potentially relevant knowledge for the application of artificial intelligence in interventional pulmonology in a single institute. This single-center, retrospective study compared the ENB and VBN results in patients with pulmonary lesions unsuitable for biopsy via percutaneous transthoracic needle biopsy methods. A total of 35 patients who underwent navigation bronchoscopy for pulmonary lesion diagnosis were enrolled. Nineteen patients were stratified in the ENB group, and sixteen were in the VBN group. The mean age of this cohort was 67.6 ± 9.9 years. The mean distance of the lesion from the pleural surface was 16.1 ± 11.7 mm (range: 1.0-41.0 mm), and most lesions were a solid pattern (n = 33, 94.4%). There were 32 cases (91.4%) of pulmonary lesions with an air-bronchus sign. A statistically significant difference was found between pulmonary size and transparenchymal nodule access (p = 0.049 and 0.037, respectively). The navigation success rate was significantly higher in the VBN group (93.8% vs. 78.9%). Moreover, no procedure-related complications or mortality were noted. The radiographic characteristics, such as size or solid component, can affect the selection of the biopsy procedure, either ENB or VBN. Navigation bronchoscopy-guided biopsy demonstrated acceptable accuracy and a good safety profile in evaluating pulmonary lesions when the percutaneous approach was challenging or life threatening.

Locate, Tell, and Guide: Enabling Public Cameras to Navigate the Public

Indoor navigation is essential to a wide spectrum of applications in the era of mobile computing. Existing vision-based technologies suffer from both start-up costs and the absence of semantic information for navigation. We observe an opportunity to leverage pervasively deployed surveillance cameras to deal with the above drawbacks and revisit the problem of indoor navigation with a fresh perspective. In this paper, we propose <i>iSAT</i> , a system that enables public surveillance cameras, as indoor navigating satellites, to locate users on the floorplan, tell users with semantic information about the surrounding environment, and guide users with navigation instructions. However, enabling public cameras to navigate is non-trivial due to 3 factors: absence of real scale, disparity of camera perspective, and lack of semantic information. To overcome these challenges, <i>iSAT</i> leverages POI-assisted framework and adopts a novel coordinate transformation algorithm to associate public and mobile cameras, and further attaches semantic information to user location. Extensive experiments in 4 different scenarios show that <i>iSAT</i> achieves a localization accuracy of 0.48m and a navigation success rate of 90.5 percent, outperforming the state-of-th-art systems by <inline-formula><tex-math notation="LaTeX">$&gt; 30\%$</tex-math></inline-formula> . Benefiting from our solution, all areas with public cameras can upgrade to smart spaces with visual navigation services.