Showing papers on "Obstacle published in 2023"

Deep Learning-Based Cost-Effective and Responsive Robot for Autism Treatment

Abstract: Recent studies state that, for a person with autism spectrum disorder, learning and improvement is often seen in environments where technological tools are involved. A robot is an excellent tool to be used in therapy and teaching. It can transform teaching methods, not just in the classrooms but also in the in-house clinical practices. With the rapid advancement in deep learning techniques, robots became more capable of handling human behaviour. In this paper, we present a cost-efficient, socially designed robot called `Tinku’, developed to assist in teaching special needs children. `Tinku’ is low cost but is full of features and has the ability to produce human-like expressions. Its design is inspired by the widely accepted animated character `WALL-E’. Its capabilities include offline speech processing and computer vision—we used light object detection models, such as Yolo v3-tiny and single shot detector (SSD)—for obstacle avoidance, non-verbal communication, expressing emotions in an anthropomorphic way, etc. It uses an onboard deep learning technique to localize the objects in the scene and uses the information for semantic perception. We have developed several lessons for training using these features. A sample lesson about brushing is discussed to show the robot’s capabilities. Tinku is cute, and loaded with lots of features, and the management of all the processes is mind-blowing. It is developed in the supervision of clinical experts and its condition for application is taken care of. A small survey on the appearance is also discussed. More importantly, it is tested on small children for the acceptance of the technology and compatibility in terms of voice interaction. It helps autistic kids using state-of-the-art deep learning models. Autism Spectral disorders are being increasingly identified today’s world. The studies show that children are prone to interact with technology more comfortably than a with human instructor. To fulfil this demand, we presented a cost-effective solution in the form of a robot with some common lessons for the training of an autism-affected child.

Autonomous Unmanned Aerial Vehicles in Bushfire Management: Challenges and Opportunities

Abstract: The intensity and frequency of bushfires have increased significantly, destroying property and living species in recent years. Presently, unmanned aerial vehicle (UAV) technology advancements are becoming increasingly popular in bushfire management systems because of their fundamental characteristics, such as manoeuvrability, autonomy, ease of deployment, and low cost. UAVs with remote-sensing capabilities are used with artificial intelligence, machine learning, and deep-learning algorithms to detect fire regions, make predictions, make decisions, and optimize fire-monitoring tasks. Moreover, UAVs equipped with various advanced sensors, including LIDAR, visual, infrared (IR), and monocular cameras, have been used to monitor bushfires due to their potential to provide new approaches and research opportunities. This review focuses on the use of UAVs in bushfire management for fire detection, fire prediction, autonomous navigation, obstacle avoidance, and search and rescue to improve the accuracy of fire prediction and minimize their impacts on people and nature. The objective of this paper is to provide valuable information on various UAV-based bushfire management systems and machine-learning approaches to predict and effectively respond to bushfires in inaccessible areas using intelligent autonomous UAVs. This paper aims to assemble information about the use of UAVs in bushfire management and to examine the benefits and limitations of existing techniques of UAVs related to bushfire handling. However, we conclude that, despite the potential benefits of UAVs for bushfire management, there are shortcomings in accuracy, and solutions need to be optimized for effective bushfire management.

A Non-Laboratory Gait Dataset of Full Body Kinematics and Egocentric Vision

Abstract: Abstract In this manuscript, we describe a unique dataset of human locomotion captured in a variety of out-of-the-laboratory environments captured using Inertial Measurement Unit (IMU) based wearable motion capture. The data contain full-body kinematics for walking, with and without stops, stair ambulation, obstacle course navigation, dynamic movements intended to test agility, and negotiating common obstacles in public spaces such as chairs. The dataset contains 24.2 total hours of movement data from a college student population with an approximately equal split of males to females. In addition, for one of the activities, we captured the egocentric field of view and gaze of the subjects using an eye tracker. Finally, we provide some examples of applications using the dataset and discuss how it might open possibilities for new studies in human gait analysis.

Global epistasis and the emergence of ecological function

Abstract: The emergence of community functions is the result of a complex web of interactions between organisms and their environment. This complexity poses a significant obstacle in quantitatively predicting ecological function from the species-level composition of a community. In this study, we demonstrate that the collective impact of interspecies interactions leads to the emergence of simple linear models that predict ecological function. These predictive models mirror the patterns of global epistasis reported in genetics, and they can be quantitatively interpreted in terms of pairwise ecological interactions between species. Our results illuminate an unexplored path to quantitatively linking the composition and function of ecological communities, bringing the tasks of predicting biological function at the genetic, organismal, and ecological scales under the same quantitative formalism.

Collision avoidance for autonomous ship using deep reinforcement learning and prior-knowledge-based approximate representation

Abstract: Reinforcement learning (RL) has shown superior performance in solving sequential decision problems. In recent years, RL is gradually being used to solve unmanned driving collision avoidance decision-making problems in complex scenarios. However, ships encounter many scenarios, and the differences in scenarios will seriously hinder the application of RL in collision avoidance at sea. Moreover, the iterative speed of trial-and-error learning for RL in multi-ship encounter scenarios is slow. To solve this problem, this study develops a novel intelligent collision avoidance algorithm based on approximate representation reinforcement learning (AR-RL) to realize the collision avoidance of maritime autonomous surface ships (MASS) in a continuous state space environment involving interactive learning capability like a crew in navigation situation. The new algorithm uses an approximate representation model to deal with the optimization of collision avoidance strategies in a dynamic target encounter situation. The model is combined with prior knowledge and International Regulations for Preventing Collisions at Sea (COLREGs) for optimal performance. This is followed by a design of an online solution to a value function approximation model based on gradient descent. This approach can solve the problem of large-scale collision avoidance policy learning in static-dynamic obstacles mixed environment. Finally, algorithm tests were constructed though two scenarios (i.e., the coastal static obstacle environment and the static-dynamic obstacles mixed environment) using Tianjin Port as an example and compared with multiple groups of algorithms. The results show that the algorithm can improve the large-scale learning efficiency of continuous state space of dynamic obstacle environment by approximate representation. At the same time, the MASS can efficiently and safely avoid obstacles enroute to reaching its target destination. It therefore makes significant contributions to ensuring safety at sea in a mixed traffic involving both manned and MASS in near future.

Automatic Vehicle Following Under Safety, Comfort, and Road Geometry Constraints

Abstract: Automatic vehicle following and cruising under all road geometry characteristics (curvature, slope, and superelevation) and traffic conditions without putting the vehicle occupants or other vehicles in unsafe situations are fundamental for the success of autonomous vehicles. Despite the advances in sensor technologies, we do not have the accuracy needed to guarantee safety under all driving conditions. In fact, for certain road geometries such as going around sharp curves, forward-looking beams and vision cannot see what is around the curve no matter how accurate they are. To ensure safety and driving comfort, the following challenges need to be addressed under all road geometry characteristics and traffic conditions: Effective detection of in-path objects, collision avoidance with objects not visible with exteroceptive sensors, adopting a cautious approach in high noise environment and avoiding high longitudinal and lateral accelerations for driving comfort. This paper presents a methodology and control design that meets these challenges. It incorporates geo-referenced maps to identify road geometries and detect in-path objects. It analyses the impact of noise on sensor data and uses a probabilistic approach to determine the desired velocity. It then proposes a vehicle following controller that achieves robust vehicle following and cruising under all road geometries and in particular sharp curves. In the case of sharp curves, where a possible obstacle is not visible by the on-board sensors, slowing down to a certain speed preemptively to have time to stop is part of the proposed methodology. Simulations show that proposed system fulfills all safety and comfort constraints.

RSSI Map-Based Trajectory Design for UGV Against Malicious Radio Source: A Reinforcement Learning Approach

Abstract: Trajectory design is of great significance for the intelligent Unmanned Ground Vehicle (UGV) when performing various ground tasks. Though obstacle avoidance, speed control and other movement issues in the UGV navigation have been considered by the current research, the UGV path planning against malicious radio source is off the beaten path. To address such a research gap, we propose a reinforcement learning-based scheme to design UGV trajectory against malicious radio source as well as minimize the movement cost. Firstly, the malicious radio source detection and localization models are introduced after the Received Signal Strength Indicator (RSSI) map establishment. Then, the RSSI Map-based UGV trajectory design problem is formulated, where the movement cost and security risk are both concerned. To solve the formed problem, we propose a reinforcement learning-based trajectory design scheme, whose complexities are analyzed in detail. Finally, experiments are conducted under various parameter settings, where the simulation results evaluate the correctness and effectiveness of the proposed algorithm.

A simple catch: Fluctuations enable hydrodynamic trapping of microrollers by obstacles

Abstract: It is known that obstacles can hydrodynamically trap bacteria and synthetic microswimmers in orbits, where the trapping time heavily depends on the swimmer flow field and noise is needed to escape the trap. Here, we use experiments and simulations to investigate the trapping of microrollers by obstacles. Microrollers are rotating particles close to a bottom surface, which have a prescribed propulsion direction imposed by an external rotating magnetic field. The flow field that drives their motion is quite different from previously studied swimmers. We found that the trapping time can be controlled by modifying the obstacle size or the colloid-obstacle repulsive potential. We detail the mechanisms of the trapping and find two remarkable features: The microroller is confined in the wake of the obstacle, and it can only enter the trap with Brownian motion. While noise is usually needed to escape traps in dynamical systems, here, we show that it is the only means to reach the hydrodynamic attractor.

Flying Through a Narrow Gap Using End-to-End Deep Reinforcement Learning Augmented With Curriculum Learning and Sim2Real

Abstract: Traversing through a tilted narrow gap is previously an intractable task for reinforcement learning mainly due to two challenges. First, searching feasible trajectories is not trivial because the goal behind the gap is difficult to reach. Second, the error tolerance after Sim2Real is low due to the relatively high speed in comparison to the gap’s narrow dimensions. This problem is aggravated by the intractability of collecting real-world data due to the risk of collision damage. In this brief, we propose an end-to-end reinforcement learning framework that solves this task successfully by addressing both problems. To search for dynamically feasible flight trajectories, we use a curriculum learning to guide the agent toward the sparse reward behind the obstacle. To tackle the Sim2Real problem, we propose a Sim2Real framework that can transfer control commands to a real quadrotor without using real flight data. To the best of our knowledge, our brief is the first work that accomplishes successful gap traversing task purely using deep reinforcement learning.

An Investigation of Exhaust Gas Temperature of Aircraft Engine Using LSTM

Abstract: A significant obstacle to creating efficient machine health monitoring systems is estimating performance degradation in dynamic systems, like aero plane engines. In exceedingly complex systems with many components, states, and parameters, conventional model-based and data-driven methods fall short of producing satisfactory results. While traditional methods had several drawbacks, deep learning has emerged as a viable computational tool for dynamic system prediction. In order to track system deterioration and estimate the EGT, a novel technique based on the Long Short-Term Memory (LSTM) network, (an architecture created to find the hidden patterns hidden in time series data) is provided in this research. The health monitoring information of aircraft turbofan engines is used to assess the effectiveness of the proposed strategy. As a result of this network’s ability to recognize the input data as a real-time series, the output in the following step can be predicted. Results of the suggested study show a significant ability to anticipate the output in the following time step. Additionally, the proposed model has a shorter learning curve and is more accurate.

Path-Planning for Unmanned Aerial Vehicles with Environment Complexity Considerations: A Survey

Abstract: Unmanned aerial vehicles (UAVs) have the potential to make a significant impact in a range of scenarios where it is too risky or too costly to rely on human labour. Fleets of autonomous UAVs, which complete tasks collaboratively while managing their basic flight and related tasks independently, present further opportunities along with research and regulatory challenges. Improvements in UAV construction and components, along with developments in embedded computing hardware, communication mechanisms and sensors which may be mounted on-board a UAV, are nearing the point where commercial deployment of fleets of autonomous UAVs will be technically possible. To fulfil this potential, UAVs will need to operate safely and reliably in complex and potentially dynamically changing environments with path-planning, obstacle sensing and collision avoidance paramount. This survey presents an original environment complexity classification and critically analyses the current state of the art in relation to UAV path-planning approaches. Moreover, it highlights the existing challenges in environment complexity modelling and representation, as well as path-planning approaches, and outlines open research questions together with future directions.

Automatic Obstacle Detection Method for the Train Based on Deep Learning

Abstract: Automatic obstacle detection is of great significance for improving the safety of train operation. However, the existing autonomous operation of trains mainly depends on the signaling control system and lacks the extra equipment to perceive the environment. To further enhance the efficiency and safety of the widely deployed fully automatic operation (FAO) systems of the train, this study proposes an intelligent obstacle detection system based on deep learning. It collects perceptual information from industrial cameras and light detection and ranging (LiDAR), and mainly implements the functionality including rail region detection, obstacle detection, and visual–LiDAR fusion. Specifically, the first two parts adopt deep convolutional neural network (CNN) algorithms for semantic segmentation and object detection to pixel-wisely identify the rail track area ahead and detect the potential obstacles on the rail track, respectively. The visual–LiDAR fusion part integrates the visual data with the LiDAR data to achieve environmental perception for all weather conditions. It can also determine the geometric relationship between the rail track and obstacles to decide whether to trigger a warning alarm. Experimental results show that the system proposed in this study has strong performance and robustness. The system perception rate (precision) is 99.994% and the recall rate reaches 100%. The system, applied to the metro Hong Kong Tsuen Wan line, effectively improves the safety of urban rail train operation.

Hydrodynamic performance in wave condition of autonomous amphibious robots

Abstract: Autonomous amphibious robot has a wide application able to move on land and sailing in water condition. In this paper, we design a new structure for autonomous amphibious robots, which can convert to water mode when coming through a water obstacle. Research on the hydrodynamic performance of amphibious robots in static water is carried out. To evaluate the impact of wave conditions on sailing characteristics, wave numerical simulation is studied. Results show that wave conditions will increase the resistance at low and medium velocities, with a maximum of 40% resistance increase at a speed of 1.5 m/s. The wave simulation model can capture wave dynamic flow well, including wave dissipation and turbulent energy loss.

Vision-Based Navigation Techniques for Unmanned Aerial Vehicles: Review and Challenges

Abstract: In recent years, unmanned aerial vehicles (UAVs), commonly known as drones, have gained increasing interest in both academia and industries. The evolution of UAV technologies, such as artificial intelligence, component miniaturization, and computer vision, has decreased their cost and increased availability for diverse applications and services. Remarkably, the integration of computer vision with UAVs provides cutting-edge technology for visual navigation, localization, and obstacle avoidance, making them capable of autonomous operations. However, their limited capacity for autonomous navigation makes them unsuitable for global positioning system (GPS)-blind environments. Recently, vision-based approaches that use cheaper and more flexible visual sensors have shown considerable advantages in UAV navigation owing to the rapid development of computer vision. Visual localization and mapping, obstacle avoidance, and path planning are essential components of visual navigation. The goal of this study was to provide a comprehensive review of vision-based UAV navigation techniques. Existing techniques have been categorized and extensively reviewed with regard to their capabilities and characteristics. Then, they are qualitatively compared in terms of various aspects. We have also discussed open issues and research challenges in the design and implementation of vision-based navigation techniques for UAVs.

Collision-Avoiding Flocking With Multiple Fixed-Wing UAVs in Obstacle-Cluttered Environments: A Task-Specific Curriculum-Based MADRL Approach.

Abstract: Multiple unmanned aerial vehicles (UAVs) are able to efficiently accomplish a variety of tasks in complex scenarios. However, developing a collision-avoiding flocking policy for multiple fixed-wing UAVs is still challenging, especially in obstacle-cluttered environments. In this article, we propose a novel curriculum-based multiagent deep reinforcement learning (MADRL) approach called task-specific curriculum-based MADRL (TSCAL) to learn the decentralized flocking with obstacle avoidance policy for multiple fixed-wing UAVs. The core idea is to decompose the collision-avoiding flocking task into multiple subtasks and progressively increase the number of subtasks to be solved in a staged manner. Meanwhile, TSCAL iteratively alternates between the procedures of online learning and offline transfer. For online learning, we propose a hierarchical recurrent attention multiagent actor-critic (HRAMA) algorithm to learn the policies for the corresponding subtask(s) in each learning stage. For offline transfer, we develop two transfer mechanisms, i.e., model reload and buffer reuse, to transfer knowledge between two neighboring stages. A series of numerical simulations demonstrate the significant advantages of TSCAL in terms of policy optimality, sample efficiency, and learning stability. Finally, the high-fidelity hardware-in-the-loop (HITL) simulation is conducted to verify the adaptability of TSCAL. A video about the numerical and HITL simulations is available at https://youtu.be/R9yLJNYRIqY.

A Time-Saving Path Planning Scheme for Autonomous Underwater Vehicles With Complex Underwater Conditions

Abstract: Autonomous underwater vehicle (AUV) shows great potential in the Internet of Underwater Things (IoUT) system, in which the path planning algorithm plays a fundamental role. However, the complex underwater environment brings greater challenges to AUV path planning, especially the ocean current, which has a profound impact on time and energy consumption. This article focuses on the complex ocean current condition and proposes an underwater path planning method based on proximal policy optimization (UP4O). In this novel method, a deep reinforcement network is constructed to serve as a decision control to plan the moving direction of AUV. An information encoding module is developed to extract the features of the local obstacles. Furthermore, UP4O integrates the obstacle features with the current state information, including relative position, ocean current, and velocity, enabling the AUV to focus on the global direction and local obstacles at the same time. Additionally, to further adapt to the ocean current and shorten the time cost, UP4O expands the action space of AUV, realizing a fine and flexible action adjustment. The wide applicability of UP4O has been proved by numerous experiments. The proposed algorithm can always plan the time-saving and collision-free paths in complex underwater environments with various terrains and ocean current.

CISA: Context Substitution for Image Semantics Augmentation

Abstract: Large datasets catalyze the rapid expansion of deep learning and computer vision. At the same time, in many domains, there is a lack of training data, which may become an obstacle for the practical application of deep computer vision models. To overcome this problem, it is popular to apply image augmentation. When a dataset contains instance segmentation masks, it is possible to apply instance-level augmentation. It operates by cutting an instance from the original image and pasting to new backgrounds. This article challenges a dataset with the same objects present in various domains. We introduce the Context Substitution for Image Semantics Augmentation framework (CISA), which is focused on choosing good background images. We compare several ways to find backgrounds that match the context of the test set, including Contrastive Language–Image Pre-Training (CLIP) image retrieval and diffusion image generation. We prove that our augmentation method is effective for classification, segmentation, and object detection with different dataset complexity and different model types. The average percentage increase in accuracy across all the tasks on a fruits and vegetables recognition dataset is 4.95%. Moreover, we show that the Fréchet Inception Distance (FID) metrics has a strong correlation with model accuracy, and it can help to choose better backgrounds without model training. The average negative correlation between model accuracy and the FID between the augmented and test datasets is 0.55 in our experiments.

Megastudies: A New Approach to Reducing Vaccine Hesitation Worldwide

Abstract: Vaccine hesitancy is a considerable obstacle to achieving vaccine protection worldwide. There needs to be more evidence-based research for interventions for vaccine hesitancy. Existing effectiveness evaluations are limited to one particular hypothesis, and no studies have compared the effectiveness of different interventions. A megastudy takes a large-scale, multi-intervention, uniform participant and the same evaluation criteria approach to evaluate many interventions simultaneously and find the most effective ones. Therefore, megastudies can help us find the most effective interventions for vaccine hesitancy. Additionally, considering the complex causes of vaccine hesitancy, we design interventions that involve social factors in megastudies. Lastly, quality control and justice are critical issues for megastudies in the future.

The use of machine learning in optimizing the height of triangular obstacles in the mixed convection flow of two-phase MHD nanofluids inside a rectangular cavity

Abstract: In this article, a numerical study was conducted on the mixed convection (CNV) of nanofluid (NFD) in a two-dimensional rectangular cavity using the control volume method. The upper and lower walls of the cavity were cold and hot, respectively, and its two vertical walls were insulated. The Upper wall has constant velocity and order to create a forced CNV in the cavity. They positioned three triangle-shaped obstacles on the heated wall that were likewise hot. The velocity and temperature graph values in the cavity, the velocity and streamline contours, and the Nusselt number value were examined independently by varying the height (HIT) of each barrier. Using artificial intelligence, the best values of the parameters to have the strongest flow and the most heat transfer (HTF) were checked. Two-phase method was used to simulate NFD flow. The results of this study showed that the middle obstacle with the highest HIT had more HTF. Increasing the length of the obstacle on the right has reduced the amount of HTF and the highest HTF occurred at the lowest HIT of this obstacle. When the obstacle on the left side has the HIT, the amount of HTF is the highest, while its average value has minimized the HTF. An increase in the HIT of the right fin at different HITs of the other two fins reduces the average Nu value

Hybrid Autonomous Vehicle (Aerial and Grounded)

Abstract: This work discusses hybrid autonomous vehicles that are grounded and aerial vehicles that are utilized to select their course based on their environmental characteristics. It includes algorithms for path planning, obstacle avoidance, and trajectory planning. It also has a microcontroller, known as the PIXHAWK Flight Controller, for various transmissions and configurations. Calibration and testing are performed using Mission Planner software. This article shows the different problematic features of an autonomous vehicle with several functionalities.

Vision-based Perception with Safety Awareness for UAS Autonomous Landing

Abstract: ,

Modelling Driver’s Behaviour While Avoiding Obstacles

Abstract: This article presents a short description of mathematical driver models. In the literature, there are no models that are generally considered fully satisfactory for use in analysing drivers’ behaviour in emergencies. This paper presents a concept of model, which includes two sub-models related to the driver’s defensive manoeuvres—avoiding the obstacle and braking. This article describes a model used for a simple road situation—a single obstacle (pedestrian) appearing on the road in front of the vehicle. In the model, the method of artificial potential fields was used, but it was enriched with the concept of safety zones around the vehicle and obstacles for three variants of the proposed shape, namely a rectangle, a circle, and an ellipse. In the simulations, parameters important for the model’s operation were used. The proposed model can be used for the simulation of human behaviour in specialised programs for accident reconstruction and in the future in assistant systems.

Obstacle Avoidance Control of Unmanned Aerial Vehicle with Motor Loss-of-Effectiveness Fault Based on Improved Artificial Potential Field

Abstract: This paper presents an obstacle avoidance control strategy for an underactuated quadrotor unmanned aerial vehicle with motor loss-of-effectiveness fault and disturbance. The control system is divided into two parts: the obstacle avoidance loop and the tracking loop. By introducing the height factor in the artificial potential field function, an improved obstacle avoidance strategy is designed in the obstacle avoidance loop. Compared with the existing literature, the proposed obstacle avoidance strategy can avoid falling into the trap of the local optimum when a UAV encounters obstacles. At the same time, considering the sudden motor loss-of-effectiveness fault of UAV, adaptive technology is used to estimate the fault parameters online to restrain the effects of motor loss-of-effectiveness fault in the tracking loop. The stability of the closed-loop UAV system is guaranteed by stabilizing each of the subsystems through backstepping technology. Simulations are conducted to demonstrate the effectiveness of the designed obstacle avoidance control strategy.

On the dynamics of grounded shallow ice sheets: Modeling and analysis

Abstract: Abstract In this article, we formulate a model describing the evolution of thickness of a grounded shallow ice sheet. The thickness of the ice sheet is constrained to be nonnegative. This renders the problem under consideration an obstacle problem. A rigorous analysis shows that the model is thus governed by a set of variational inequalities that involve nonlinearities in the time derivative and in the elliptic term, and that it admits solutions, whose existence is established by means of a semi-discrete scheme and the penalty method.