Dynamic Outdoor Environments Research Articles

Evaluation of pedestrian thermal comfort from a whole-trip perspective: An outdoor empirical study

Pedestrian thermal comfort is a critical factor influencing urban livability and sustainability. However, existing models often overlook its cumulative impact from dynamic thermal experiences throughout the whole-trip. This study builds on previous findings, conducting outdoor mobile observations in Guangzhou's urban blocks on clear summer days. Methods for assessing thermal comfort during pedestrian travel were tested and refined, taking into account participants' skin temperatures and accumulated heat storage. The research found that the dynamic changes and non-uniform distribution of radiant temperature are the main characteristics of pedestrians' thermal experiences during summer clear weather and are critical factors affecting their thermal comfort. Non-uniform exposure to direct solar radiation can cause variations in pedestrians' instantaneous thermal sensations, and dynamic thermal experiences can lead to the formation of memorized thermal sensations, causing a deviation between instantaneous and whole-trip thermal sensations. There is a significant correlation between pedestrians' mean skin temperature and heat storage and their thermal experiences over the past 10–25 min. Regression analysis provided different weights that could represent the memory component in whole-trip thermal sensations. The findings provide a theoretical basis for understanding pedestrian thermal comfort in dynamic outdoor environments and will help improve the thermal quality of outdoor travel spaces.

An algorithm for large-span flexible bridge pose estimation and multi-keypoint vibration displacement measurement

Traditional visual vibration measurement methods face limitations in dynamic outdoor environments, making accurate multi-point vibration measurements challenging for the targeted objects. In this paper, a visual vibration measurement algorithm for large-span bridges is proposed by anthropomorphizing the bridge target and introducing key point detection at the same time. Firstly, the algorithm utilizes a convolutional neural network to extract multi-scale feature information from the image sequence of the bridge model. Secondly, to enhance target detection accuracy, a coordinate attention (CA) mechanism is incorporated, and the shape intersection over union (SIoU) loss function replaces the original loss function. Finally, the algorithm integrates the density-based spatial clustering of applications with noise (DBSCAN) and tracking algorithms to achieve precise localization of bridge targets. Vibration displacement data were extracted from a large-span suspension bridge structure in an outdoor environment and analyzed quantitatively and qualitatively. The vibration displacement curves obtained in this study show the highest level of agreement with the standard displacement signals, with a mean absolute percentage error of 0.5170% for the cable-stayed bridge model, 1.3822% for the Humen Bridge, and 3.2263% and 1.6982% for the Longjiang Bridge.

A dynamic object removing 3D reconstruction system based on multi-sensor fusion

Abstract Currently, one of the key technologies for autonomous navigation of unmanned mobile robots is SLAM, which faces many challenges in practical applications. These challenges include a lack of texture, deterioration in sensor performance, and interference from moving objects in dynamic outdoor environments, all of which have an impact on the mapping system. To address these issues, this paper proposes a framework for lidar, vision camera, and inertial navigation data, resulting in fusion and dynamic object removing. The system consists of three sub-modules: the Lidar-Inertial Module (LIM), the Visual-Inertial Module (VIM), and the Dynamic-Object-Removing Module (DORM). LIM and VIM assist each other, with lidar point clouds providing three-dimensional information for the global voxel map and the camera providing pixel-level color information. At the same time, the DORM performs synchronous dynamic object detection to remove dynamic objects from the global map. The system constructs a multi-sensor factor graph using the state and observation models, and the optimal solution is obtained using least squares. Furthermore, this paper employs triangle descriptors and bundle adjustment methods for loop closure detection in order to reduce accumulated errors and maintain consistency. Experimental results demonstrate that the system can perform clean state estimation, dynamic removing and scene reconstruction in a variety of complex scenarios.

AI-Enabled Vibrotactile Feedback-Based Condition Monitoring Framework for Outdoor Mobile Robots

An automated Condition Monitoring (CM) and real-time controlling framework is essential for outdoor mobile robots to ensure the robot’s health and operational safety. This work presents a novel Artificial Intelligence (AI)-enabled CM and vibrotactile haptic-feedback-based real-time control framework suitable for deploying mobile robots in dynamic outdoor environments. It encompasses two sections: developing a 1D Convolutional Neural Network (1D CNN) model for predicting system degradation and terrain flaws threshold classes and a vibrotactile haptic feedback system design enabling a remote operator to control the robot as per predicted class feedback in real-time. As vibration is an indicator of failure, we identified and separated system- and terrain-induced vibration threshold levels suitable for CM of outdoor robots into nine classes, namely Safe, moderately safe system-generated, and moderately safe terrain-induced affected by left, right, and both wheels, as well as severe classes such as unsafe system-generated and unsafe terrain-induced affected by left, right, and both wheels. The vibration-indicated data for each class are modelled based on two sensor data: an Inertial Measurement Unit (IMU) sensor for the change in linear and angular motion and a current sensor for the change in current consumption at each wheel motor. A wearable novel vibrotactile haptic feedback device architecture is presented with left and right vibration modules configured with unique haptic feedback patterns corresponding to each abnormal vibration threshold class. The proposed haptic-feedback-based CM framework and real-time remote controlling are validated with three field case studies using an in-house-developed outdoor robot, resulting in a threshold class prediction accuracy of 91.1% and an effectiveness that, by minimising the traversal through undesired terrain features, is four times better than the usual practice.

A semantic SLAM-based dense mapping approach for large-scale dynamic outdoor environment

The visual SLAM in dynamic environment has been regarded as a fundamental task for robots. Currently, existing works achieve good performance in only indoor scenes due to the loss of depth information and scene complexity. In this paper, we present a semantic SLAM framework based on geometric constraint and deep learning models. Specifically, our method is built top on the ORB-SLAM2 system with stereo observation. First, the semantic feature and depth information are acquired respectively using different deep learning models. In this way, multiple views projection is generated to reduce the impact of moving objects for pose estimation. Under the hierarchical rule, the feature points are further refined for SLAM tracking via depth local contrast. Finally, multiple dense 3D maps are created for high-level robot navigation in an incremental updating manner. Our method on public KITTI dataset demonstrates that evaluation metrics of most of sequences improve and achieve state-of-the-art performance.

A reinforcement learning fuzzy system for continuous control in robotic odor plume tracking

AbstractIn dynamic outdoor environments characterized by turbulent airflow and intermittent odor plumes, robotic odor plume tracking remains challenging, because existing algorithms heavily rely on manually tuning or learning from expert experience, which are hard to implement in an unknown environment. In this paper, a multi-continuous-output Takagi–Sugeno–Kang fuzzy system was designed and tuned with reinforcement learning to solve the robotic odor source localization problem in dynamic odor plumes. Based on the Lévy Taxis plume tracking controller, the proposed fuzzy system determined the parameters of the controller based on the robot’s observation and guided the robot to turn and move towards the odor source at each searching step. The trained fuzzy system was tested in simulated filament-based odor plumes dispersed by a changing wind field. The results showed that the performance of the proposed fuzzy system-based controller trained with reinforcement learning can achieve a similar success rate and higher efficiency compared with a manually tuned and well-designed fuzzy system-based controller. The fuzzy system-based plume tracking controller was also validated through real robotic experiments.

An open platform for efficient drone-to-sensor wireless ranging and data harvesting

Drones deployed in combination with wireless sensors can unlock a host of prospective applications in environments that lack infrastructure communications networks and where access may be impossible for human operators. Community building efforts to engage with this opportunity are hampered by a lack of platform support and an evolving understanding of the performance of known wireless communications systems in dynamic outdoor environments, particularly under mobility. This paper proposes and evaluates a new combination of ultra-wide band and wake-up radio technologies. These enable high precision landing and support energy efficient operation. We describe in detail the design and implementation of an open platform making use of the combination of these radios to improve upon ranging, bandwidth and energy efficiency problems that affect drone–wireless sensor systems. Our evaluation shows how established ideas including low power listening and receiver-initiated data transfer compare with using a wake-up radio. We show that the energy efficiency of the localization–acquisition cycle can be improved by up to 62% with respect to a duty cycle approach. Our experimental evaluation also shows two orders of magnitude improvements in power consumption, from 190μW to 2μW, in non-ranging quiescent states on the sensor side.

ODS-Bot: Mobile Robot Navigation for Outdoor Delivery Services

Autonomous mobile robots have been used in outdoor delivery services. Delivery robots have to cope with dynamic obstacles and various environmental conditions. Although several successful technological solutions are available for indoor applications, there are still plenty of unsolved problems in outdoor environments. In this study, we concentrate on three technological challenges hindering the development of campus delivery robots. The first challenge is robust localization in various dynamic outdoor environments. Localization results obtained using lidars and Global Navigation Satellite System (GNSS) sensors show complementary advantages and disadvantages. The proposed localization strategy efficiently combines information from multiple sensors. The second challenge is safe navigation based on the detection of the traversable region. The presented terrain traversability analysis provides clear, real-time positive and negative obstacle information. The third challenge is the requirement of an effective path planning strategy to reduce the risk of collisions or deadlocks. We collected the appearance history of regional dynamic obstacles in the map. The resultant path was carefully generated to avoid crowded areas. Experimental verifications have been successfully conducted on the Korea University campus. The presented results clearly indicate that the proposed methods are essential to achieve safe and reliable navigation in dynamic, real-world environments.

The STDyn-SLAM: A Stereo Vision and Semantic Segmentation Approach for VSLAM in Dynamic Outdoor Environments

The Visual Simultaneous Localization and Mapping (VSLAM) is a system based on the scene’s features to estimate a map and the system pose. Commonly, VSLAM algorithms are focused on a static environment; however, some dynamic objects are present in the vast majority of real-world applications. This work presents a feature-based SLAM system focused on dynamic environments using convolutional neural networks, optical flow, and depth maps to detect objects in the scene. The proposed system employs a stereo camera as the primary sensor to capture the scene. The neural network is responsible for object detection and segmentation to avoid erroneous maps and wrong system locations. Moreover, the proposed system’s processing time is fast and can run in real-time, running in outdoor and indoor environments. The proposed approach has been compared with state-of-the-art; besides, we present several experimental results outdoors that corroborate the approach’s effectiveness. Our code is available online.

Deep Reinforcement Learning for Autonomous Map-Less Navigation of a Flying Robot

Flying robots are expected to be used in many tasks, such as aerial delivery, inspection inside dangerous areas, and rescue. However, their deployment in unstructured and highly dynamic environments has been limited. This paper proposes a novel approach for enabling a micro-aerial vehicle (MAV) system equipped with a laser rangefinder and depth sensor to autonomously navigate and explore an unknown indoor or outdoor environment. We built a modular deep-Q-network architecture to fuse information from multiple sensors mounted onboard a vehicle. The developed algorithm can perform collision-free flights in the real world, while being trained entirely on a 3D simulator. The proposed method does not require prior expert demonstrations, 3D mapping, or path planning. It transforms fused sensory data into a velocity control input for a robot through an end-to-end convolutional neural network (CNN). The obtained policy was compared to a simulation using the conventional potential-field method. Our approach achieves zero- shot transfer from simulation to real-world environments that were never experienced during training by simulating realistic sensor data. Several intensive experiments were conducted to demonstrate the effectiveness of our system for safely flying in dynamic outdoor and indoor environments. The supplementary videos for the actual flight tests can be accessed at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://bit.ly/2SEw8dQ</uri> .

A Semantic Slam-Based Dense Mapping Approach for Large-Scale Dynamic Outdoor Environment

A Semantic Slam-Based Dense Mapping Approach for Large-Scale Dynamic Outdoor Environment

Using perception cues for context-aware navigation in dynamic outdoor environments

Continued advancements in robot autonomy have allowed the research community to shift from using robots as tools in the field to deploying robot teammates capable of learning, reasoning, and executing tasks. Autonomous navigation is one necessary capability of a robot teammate that must operate in large field environments. In relatively static environments a simple navigation solution such as obstacle avoidance along the shortest path may suffice; however, as robot teammates are deployed to highly dynamic environments with changing mission requirements, additional environment context may be necessary to ensure safe and reliable navigation. Although recent works in urban autonomous driving have advanced the state-of-the-art in context-aware decision making, the spectrum of behaviors deployed for context-switching is more narrowly focused (by defining constraints specific to operation in structured environments) than what might be required for human-agent teaming field missions. As such, establishing a context-aware intelligent system for dynamic, unstructured environments is still an open problem. We discuss our approach to the integration of several context-aware navigation behaviors on a small unmanned ground vehicle (UGV) and a perception stack that provides cues used to transition between these different learned behaviors. Specifically, we integrate socially compliant, terrain-aware, and covert behaviors in an outdoor navigation scenario where the UGV encounters moving pedestrians, different terrains, and weapon threats. We provide a detailed account of the overall system integration, experiment design, component- and system-level analysis, and lessons learned.

Experimental characterisation of a smart glazing with tuneable transparency, light scattering ability and electricity generation function

Daylighting control technologies have become an essential part of sustainable building design to reduce overheating, glare and energy consumption in buildings. In this paper, a smart glazing system where a Building Integrated Photovoltaic (BIPV) glazing is coupled with an optically switchable thermotropic hydrogel layer is proposed to improve the daylighting control and electricity generation performance of traditional BIPV glazings. Thermotropic (TT) hydrogels made of various weight percentage combinations of hydroxypropyl cellulose (HPC) polymer, gellan gum and sodium chloride (NaCl) salt were synthesised and first evaluated by visible-near-infrared spectroscopy. Subsequently, small-scale prototypes of the proposed BIPV thermotropic (BIPV-TT) laminated glazing based on these TT hydrogels were fabricated and characterised experimentally under controlled laboratory conditions. The TT hydrogel, which was synthesised of 6 wt% HPC, 0.5 wt% gellan gum and 4.5 wt% NaCl, was selected for further experimental characterisations in a dynamic outdoor environment, due to its appropriate transition temperature of 30.7 °C for use in mild climates with a wide modulation range of solar transmittance from 85.8% (in the transparent state) to 9.6% (in the light-scattering state). The outdoor tests were conducted in Nottingham, the UK, on typical summer days with sunny and partial cloudy conditions. The results showed that using the prototype BIPV-TT laminated glazing can reduce up to 80% of the solar radiation transmitted into the outdoor test cell, while providing up to 12% higher electrical power outputs, compared to its counterpart system with no thermotropic hydrogel applied.

Evaluation of thermal sensation models for predicting thermal comfort in dynamic outdoor and indoor environments

Thermal sensation models are commonly used to assess thermal perception in various indoor environments. Our previous work developed a new model to predict thermal sensation in cars that uses gradual change in thermal load on the face, sudden change in solar radiation on the face, mean skin temperature and outdoor air temperature as predictors. The present investigation selected 11 outdoor scenarios and 20 indoor scenarios from the literature to further verify the accuracy of the thermal sensation model. Four other thermal models, the predicted mean vote (PMV) model, the dynamic thermal sensation (DTS) model, a model from the University of California, Berkeley (UCB), and a transient outdoor thermal comfort model (Lai's) were compared with the new model for the 32 scenarios. The results confirmed the validity of the new model in an outdoor environment with sudden change in solar radiation. The new model was able to predict the trend of thermal changes, but the accuracy was not as good as that of the PMV model in an environment with indoor temperature gradient/sudden changes.

Improved Target Signal Source Tracking and Extraction Method Based on Outdoor Visible Light Communication Using an Improved Particle Filter Algorithm Based on Cam-Shift Algorithm

An improved particle filter algorithm based on Cam-Shift algorithm applied to outdoor visible light communication (outdoor-VLC) is presented in this paper. In the outdoor-VLC system, accurately and completely tracking and extracting the target signal source Light Emitting Diode (LED) area is the premise for realizing communication. However, few existing studies pay attention to it. In the dynamic outdoor environment, there will be a lot of different environmental interferences (such as background interference, similar object interference, etc.), which greatly increases the difficulty of tracking and extracting the target signal source LED area. Therefore, in this paper, an improved tracking algorithm is proposed to solve the problem of how to track and extract the target signal source LED area accurately, stably and in real time in the outdoor-VLC system under various environmental interferences, so as to increase the feasibility of practical application of VLC system in outdoor scenes. This improved algorithm combines the particle filter algorithm and Cam-Shift algorithm originally. Experimental results show that the proposed algorithm has good accuracy, robustness and real-time performance under the environment of multiple interference factors. Accordingly, the proposed algorithm can be applied to the outdoor-VLC system with various environmental interferences, and can realize the actual first step of communication in VLC system based on image sensor well, laying a foundation for feature extraction, data transmission and other subsequent steps.

Fully-automatic natural plant recognition system using deep neural network for dynamic outdoor environments

The leaf, as the vital part of plants, can be affected by physical and physiological factors which might lead to changes in its shape, color and size. These unique parts play an essential role in the design and implementation of plant recognition systems, as the shapes of leaves vary among different plants. Weather type and related factors, such as light intensity, humidity, temperature and wind-speed, may have effects on the number of leaves that grow on a plant, the amount of fresh and dried leaves, the deformation of leaves, color of leaves, positions of leaves on branches, etc. In addition, photographing in outdoor environments with different weather conditions has undesired impacts on images. For instance, light scattering changes severely when there are water droplets during photographing which influences the images captured in rainy weather. Despite the importance of the proposed factors and the relevant effects on the plants, leaves and images taken from plants, a plant recognition system should be independent from all environmental and non-environmental factors to be practically useful and applicable for identifying plant species in uncontrolled outdoor environments. Moreover, changes in the time of day (morning, noon and evening), the distance between camera and plant species as well as the angle and illumination of the object and environment when the images are taken should be considered in the process of plant recognition. For instance, in a windy weather condition, for an observer even from a short distance, it is challenging to distinguish all single leaves and identify the plant type from the shape of its leaf. Furthermore, the unstructured background of the images is another challenge which affects the images captured in fields and outdoor environments. These are only some difficulties for identification of plants in natural environments such as farms, forests, etc. A consideration of mentioned factors contributes to developing a novel, efficient and accurate system for plant recognition that can be used in various uncontrolled outdoor environments. In the real-life, the images of the plants captured with the presence of these factors are very challenging for recognizing plant species and it is a desire to develop an efficient and accurate system that can be used in various natural conditions and uncontrolled situations. This paper presents the development and implementation of a convolutional neural network for automatic plant recognition in uncontrolled outdoor environments. The deep network has been used to recognize four different natural plant species. The proposed system brings the opportunity and transformative potential of deep neural networks to the plant recognition field. This fully-automatic system is efficient and generalized for recognition of plants in outdoor environments like forests and farms, and its the accuracy is 99.5%. Meanwhile, the final system has the functionality of being applied as a real-time one.

The role of planning in outdoor adventure decision-making

ABSTRACTThis article explores the influential role of planning on recognition-primed decision-making. Considerable prior thinking occurs and there is a need to trace and account for the cognitive processes that precede and guide decisions in dynamic outdoor environments. Seven expert leaders from four countries were interviewed about memorable decisions made on outdoor journeys with an educational focus on land, sea and ice. Four stages of planning were identified: (1) long-term preparation; (2) formal leadership meetings; (3) day-by-day planning on route and (4) thinking immediately prior to the event. The stages sequentially capture the planning progression, illuminating the cognitive processes at each stage to culminate in option selection. In each decision situation, planned goals and actions were implemented through the creation and re-creation of micro-plans. As windows of opportunity presented themselves, the flexible execution of plans was a key feature. Planning provided the solid bedrock upon which decisions were made.

Shadow verification–based waterline detection for unmanned surface vehicles deployed in complicated natural environment

Boundary separation of operational regions would be helpful for unmanned surface vehicles deployed in dynamic outdoor environments. However, the feasibility and accuracy of current obstacle avoidance methods based on conventional optical images are comparatively poor for unmanned surface vehicle applications, with complicated natural illumination as one of the main sources of error. In this article, a new optical waterline detection method is proposed by combining shadow verification and global optimization (energy minimization). The method is then validated using an actual unmanned surface vehicle operating in outdoor environments. First, the basic principles of intrinsic image are introduced and then employed to evaluate the threshold for background segmentation so that the influence of complicated intensity distribution on the original image is reduced. The properties of different types of shadows are compared, and the basic principles of shadow verification are used to classify the different object regions. Subsequently, the intensity contrast between the shadow and non-shadow regions is used to measure the waterline position based on the relationship between the illumination and the shadow formation. Furthermore, the waterline detection problem is transformed into a problem involving the optimization of energy (minimization) described using differential equations. Finally, experiments are conducted with a series of practical images captured by the unmanned surface vehicle. The experimental results demonstrate the feasibility and robustness of the proposed method.

Automatic segmentation of trees in dynamic outdoor environments

Segmentation in dynamic outdoor environments can be difficult when the illumination levels and other aspects of the scene cannot be controlled. Specifically in orchard and vineyard automation contexts, a background material is often used to shield a camera's field of view from other rows of crops. In this paper, we describe a method that uses superpixels to determine low texture regions of the image that correspond to the background material, and then show how this information can be integrated with the color distribution of the image to compute optimal segmentation parameters to segment objects of interest. Quantitative and qualitative experiments demonstrate the suitability of this approach for dynamic outdoor environments, specifically for tree reconstruction and apple flower detection applications.

Incorporating a wheeled vehicle model in a new monocular visual odometry algorithm for dynamic outdoor environments.

This paper presents a monocular visual odometry algorithm that incorporates a wheeled vehicle model for ground vehicles. The main innovation of this algorithm is to use the single-track bicycle model to interpret the relationship between the yaw rate and side slip angle, which are the two most important parameters that describe the motion of a wheeled vehicle. Additionally, the pitch angle is also considered since the planar-motion hypothesis often fails due to the dynamic characteristics of wheel suspensions and tires in real-world environments. Linearization is used to calculate a closed-form solution of the motion parameters that works as a hypothesis generator in a RAndom SAmple Consensus (RANSAC) scheme to reduce the complexity in solving equations involving trigonometric. All inliers found are used to refine the winner solution through minimizing the reprojection error. Finally, the algorithm is applied to real-time on-board visual localization applications. Its performance is evaluated by comparing against the state-of-the-art monocular visual odometry methods using both synthetic data and publicly available datasets over several kilometers in dynamic outdoor environments.