Constrained Environments Research Articles

Co-Design Methods for Non-Standard Multi-Storey Timber Buildings

To meet climate change goals and respond to increased global urbanisation, the building industry needs to improve both its building technology and its design methods. Constrained urban environments and building stock extensions are challenges for standard timber construction. Co-design promises to better integrate disciplines and processes, promising smaller feedback loops for design iteration and building verification. This article describes the integrated design, fabrication, and construction processes of a timber building prototype as a case study for the application of co-design methods. Emphasis is placed on the development of design and engineering methods, fabrication and construction processes, and materials and building systems. The development of the building prototype builds on previous research in robotic fabrication (including prefabrication, task distribution, and augmented reality integration), agent-based modelling (ABM) for the design and optimisation of structural components, and the systematisation of timber buildings and their components. The results presented in this article include a functional example of co-design from which best practises may be extrapolated as part of an inductive approach to design research. The prototype, with its co-designed process and resultant flat ceilings, integrated services, wide spans, and design adaptability for irregular column locations, has the potential to expand the design potential of multi-storey timber buildings.

Atmospheric Buddhism: How Buddhism is Distributed, Felt, and Moralized in a Repressive Society

ABSTRACTA growing number of lay Buddhist practitioners have sought out alternative ways to incorporate Buddhist teachings in their daily practices and make positive changes in society by “doing good” for others. Sometimes recognized as part of “humanistic Buddhism,” this approach emphasizes general morality and focuses on people who need help as a way to fulfill Buddhist teachings in this world. Some Chinese Buddhist practitioners who follow the Tibetan Buddhist tradition also carry out similar humanistic engagements but use more subtle space‐making processes and often “brand” these as Buddhist practices. Drawing on the ethnographic observations of lay Buddhist practitioners in urban China, this article examines how urban practitioners promote (middle‐class) morality and well‐being lifestyles through what I call “atmospheric Buddhism.” Ultimately, the article argues that an alternative mode of Buddhist practice is emerging in Chinese urban environments in order to cope with politically constrained environments.

Causality-Driven Efficient Feature Selection for Deep-Learning-Based Surface Roughness Prediction in Milling Machines

This paper studies the application of artificial intelligence to milling machines, focusing specifically on identifying the inputs (features) required for predicting surface roughness. Previous studies have extensively reviewed and presented useful features for surface roughness prediction. However, applying research findings to actual operational factories can be challenging due to the additional costs of sensor installations and the diverse environments present in each factory setting. To address these issues, in this paper, we introduced effective features for predicting surface roughness in situations where additional sensors are not installed in the existing environment. These features include feed per tooth, Fz; material removal rate, Q; and the load information. These features are suitable for use in highly constrained environments where separate sensor installation is not required, making it possible to apply the research findings in various factory environments. Additionally, to efficiently select the optimal subset for surface roughness prediction among subsets formed by available features, we apply causality to the feature selection method, proposing an approach called causality-driven efficient feature selection. The experimental results demonstrate that the features introduced in this paper are quite suitable for predicting surface roughness and that the proposed feature selection approach is more effective and efficient compared to existing selection methods.

On multiple imputation-based reconstruction of degraded faces and recognition in multiple constrained environments

Recognition of degraded frontal face images acquired under occlusion constraints remain challenging despite the plethora of reconstruction mechanisms. Though recent works have leveraged on some imputation mechanisms in this regard, their robustness in multiple constrained environments may not be guaranteed and may be affected by the choice of pre-processing mechanism. This paper proposes enhancement mechanisms that augment or complement the use of three (3) multiple imputation mechanisms for facial reconstruction in the presence of multiple constraints (10% and 20% occlusions and varying facial expressions). Specifically, we propose the use of a Discrete Cosine Transform-based (DCT) denoising or a Discrete Wavelet-based denoising following Histogram Equalization (HE-DWT) of the reconstructed face images prior to recognition. Experimental results showed that the proposed augmented enhancements improved significantly the recognition rates (90.63% & 91.15% and 86.98% & 85.94% for DCT and HE-DWT at 10% and 20% occlusion levels respectively for Missforest de-occluded face images) as compared with DWT in recognizing degraded frontal face images under moderately low levels of occlusions and varying expressions.

A deep reinforcement learning strategy for autonomous robot flocking

<p>Social behaviors in animals such as bees, ants, and birds have shown high levels of intelligence from a multi-agent system perspective. They present viable solutions to real-world problems, particularly in navigating constrained environments with simple robotic platforms. Among these behaviors is swarm flocking, which has been extensively studied for this purpose. Flocking algorithms have been developed from basic behavioral rules, which often require parameter tuning for specific applications. However, the lack of a general formulation for tuning has made these strategies difficult to implement in various real conditions, and even to replicate laboratory behaviors. In this paper, we propose a flocking scheme for small autonomous robots that can self-learn in dynamic environments, derived from a deep reinforcement learning process. Our approach achieves flocking independently of population size and environmental characteristics, with minimal external intervention. Our multi-agent system model considers each agent’s action as a linear function dynamically adjusting the motion according to interactions with other agents and the environment. Our strategy is an important contribution toward real-world flocking implementation. We demonstrate that our approach allows for autonomous flocking in the system without requiring specific parameter tuning, making it ideal for applications where there is a need for simple robotic platforms to navigate in dynamic environments.</p>

Stateless Q-learning algorithm for service caching in resource constrained edge environment

In resource constrained edge environment, multiple service providers can compete to rent the limited resources to cache their service instances on edge servers close to end users, thereby significantly reducing the service delay and improving quality of service (QoS). However, service providers renting the resources of different edge servers to deploy their service instances can incur different resource usage costs and service delay. To make full use of the limited resources of the edge servers to further reduce resource usage costs, multiple service providers on an edge server can form a coalition and share the limited resource of an edge server. In this paper, we investigate the service caching problem of multiple service providers in resource constrained edge environment, and propose an independent learners-based services caching scheme (ILSCS) which adopts a stateless Q-learning to learn an optimal service caching scheme. To verify the effectiveness of ILSCS scheme, we implement COALITION, RANDOM, MDU, and MCS four baseline algorithms, and compare the total collaboration cost and service latency of ILSCS scheme with these of these four baseline algorithms under different experimental parameter settings. The extensive experimental results show that the ILSCS scheme can achieve lower total collaboration cost and service latency.

SWOT: Analysis of Strategic Approaches in Total Force Fitness and Whole Health Summit.

Leaders and subject matter experts from the Department of Defense (DoD), Department of Veterans Affairs, and other organizations participated in the Total Force Fitness (TFF) and Whole Health Summit. TFF and Whole Health Summit are holistic programs designed to maximize performance and resilience through interventions across multiple domains of health, wellness, and preparedness. Findings generated from the Summit were collected and categorized using a tool known as a Strengths-Weaknesses-Opportunities-Threats (SWOT) analysis. The SWOT analysis highlighted key beneficial points regarding implementation of TFF-Whole Health principles including (1) a strong history of collaboration between the DoD and Department of Veterans Affairs, (2) a potential boost to recruitment and retention, and (3) better support for military-to-civilian transition. Risks identified ranged from policy limitations to program development within a fiscally constrained environment. The SWOT analysis can focus future efforts.

Exploring the Funding Challenges Faced by Small NGOs: Perspectives from an Organization with Practical Experience of Working in Rural Malawi.

Malawi is a small landlocked country in Southern Africa, which faces a number of development challenges. It is one of the world's poorest nations and over 70% of the population live below the International Poverty Line of $2.15 per day. Health inequalities are a well-documented problem and those most affected are women and children. Non-governmental organizations (NGOs) play a vital role in supplementing government efforts to provide health services to vulnerable people in areas that are difficult to reach. The World Medical Fund (WMF) is a small medical charity that operates in the central, rural, Nkhotakota region of Malawi where many children lack access to even basic health services. To date, WMF has successfully provided free care and treatment for over 400,000 sick children, but its initiatives, such as mobile clinics, rely entirely on external donations. Since 2000, the funding resources available to small NGOs have declined and efforts to attract funding have become increasingly competitive. Frequently, the criteria used for funding decisions are too rigid, and do not reflect the difficult operating conditions on the ground in rural Africa. As one of the world's most highly resource constrained healthcare environments, Malawi illustrates the need for more flexible funding criteria from donors so that NGOs can carry out their work to save children's lives.

Touching the Sound: Audible Features Enable Haptics for Robot Control

Haptic control interfaces can significantly improve the quality of teleoperation in robotic and mechatronic systems. However, the required force feedback introduces new challenges when highly constrained environments and systems hinder the use of conventional force sensors. In this article, we propose a haptic control method that provides feedback to the operator when force data can be extracted from a sound signal. Since sound can be acquired by a microphone deployed outside the workspace, this method enables remote feedback in any process that can be characterized through acoustic emissions (e.g. machining), without the need for sensors embedded in the system and deployed in the work environment. The performance of the method is verified by an example application with a teleoperated robot that executes a machining process (milling and grinding), whose sound is acquired with a microphone and processed to successfully estimate the machining force for haptic feedback.

A Continuum Robot for Remote Applications: From Industrial to Medical Surgery With Slender Continuum Robots

The maintenance of critical industrial components is often hindered by limited access, tortuous passages, and complex geometries. In highly constrained environments, inspection tasks are currently performed with borescopes, but even skilled operators struggle with hard-to-reach targets, and the limited mobility prevents in situ repair when defects are identified. Thanks to an active shape control, snakelike and continuum robots can outperform borescopes for short-range inspection as well as enable intervention. However, their actuation technology limits their scalability in length, as longer bodies pose control challenges due to their intrinsically low stiffness and space constraints. To overcome the limitations of both borescopes and continuum robots, here, we propose a modular design at their intersection, with both active tendon-driven and passively flexible segments. The main elements of the novel design, including the actuation and control interface, are described, and the system is demonstrated in scenarios for aerospace assets, nuclear installations, and robotassisted surgery.

Blind Modalities for Human Activity Recognition.

Human Activity Recognition (HAR) has attracted considerable interest due to its ability to facilitate automation in various application areas, including but not limited to smart homes, active assisted living, and security. At present, optical modalities such as RGB, depth, and thermal imaging are prevalent in the field due to the effectiveness of deep learning algorithms like Convolutional Neural Networks (CNNs) and the abundance of publicly available image data. However, unconventional modalities such as radar, WiFi, seismic and environmental sensors are emerging as potential alternatives due to their capacity for contactless long-range sensing in spatially constrained environments and preservation of visual privacy. This work gives an overview of the HAR modalities landscape and discusses works that apply these emerging modalities in new and unconventional ways to inform researchers and practitioners about challenges and opportunities in the field of HAR.

Innovative security and compression for constrained IoT networks

Low-Power Wide-Area Networks (LPWAN) are a type of wireless communication technologies that enable efficient data transfer between low-power devices. This article explores the challenges of ensuring security in LPWANs and proposes a solution that combines two key mechanisms: Object Security for Constrained RESTful Environments (OSCORE) and Static Context Header Compression (SCHC). LPWANs are increasingly being used in Internet of Things (IoT) applications, but the features that endow these technologies with low power consumption and long range also make it necessary to adapt protocols and innovate in the approaches to achieve security while maintaining communications viable in technologies like these, in some cases with severe limitations. OSCORE provides end-to-end security for constrained devices, while SCHC enables efficient IP-based transmission over LPWANs. By combining these two protocols, the proposed solution aims to address the security and efficiency challenges of LPWANs, ensuring that IoT devices and data are protected from unauthorized access and manipulation. The article also presents experimental results demonstrating the feasibility and effectiveness of the proposed approach using a real-life scenario, with industrial-grade hardware. The study concludes that the use of OSCORE and SCHC in LPWAN networks can significantly enhance the security and privacy of IoT devices.

DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles

This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a subgoal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move toward the goal. Through a series of 3-D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learning-based policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized.

Integer Arithmetic Algorithm for Fundamental Frequency Identification of Oceanic Currents.

Underwater sensor networks play a crucial role in collecting valuable data to monitor offshore aquaculture infrastructures. The number of deployed devices not only impacts the bandwidth for a highly constrained communication environment, but also the cost of the sensor network. On the other hand, industrial and literature current meters work as raw data loggers, and most of the calculations to determine the fundamental frequencies are performed offline on a desktop computer or in the cloud. Belonging to the edge computing research area, this paper presents an algorithm to extract the fundamental frequencies of water currents in an underwater sensor network deployed in offshore aquaculture infrastructures. The target sensor node is based on a commercial ultra-low-power microcontroller. The proposed fundamental frequency identification algorithm only requires the use of an integer arithmetic unit. Our approach exploits the mathematical properties of the finite impulse response (FIR) filtering in the integer domain. The design and implementation of the presented algorithm are discussed in detail in terms of FIR tuning/coefficient selection, memory usage and variable domain for its mathematical formulation aimed at reducing the computational effort required. The approach is validated using a shallow water current model and real-world raw data from an offshore aquaculture infrastructure. The extracted frequencies have a maximum error below a 4%.

Hapstick: A Soft Flexible Joystick for Stiffness Rendering via Fiber Jamming

Continuum robots are well-suited for applications in delicate and constrained environments, such as minimally invasive surgery, due to their inherent compliance and ability to conform to highly curved paths. Yet the kinematic dissimilarity between continuum robots and conventional, off-the-shelf input devices, along with the general lack of haptic feedback available with such devices, can lead to non-intuitive control. In this work, we present Hapstick — a soft, flexible haptic joystick that uses fiber jamming to modulate its stiffness and provide feedback to users during teleoperation tasks. We characterize the performance of Hapstick, showing that the bending stiffness increases linearly with the increase in applied vacuum load. A psychophysical study is also conducted to obtain the just noticeable difference in stiffness that users can perceive using Hapstick. Lastly, we perform a study in which participants use Hapstick to teleoperate a physical tendon-driven continuum robot in a simulated colorectal cancer screening task. Users correctly identify the position and development stages of cancerous tissues in 25 out of 27 trials, illustrating the potential of jamming-based mechanisms as bidirectional interfaces capable of providing effective haptic feedback.

An ultra-lightweight block cipher with string transformations

Security efficiency and hardware efficiency are equally important when designing a block cipher. In this paper, we propose a new block cipher that uses string transformations and requires less memory and fewer computational resources, making it suitable for highly constrained environments. We compare the performance of our design with AES-128 and quasigroup-based block cipher INRU in the cipher block chaining (CBC) mode of operation using the National Institute of Standards and Technology (NIST) test suite. We then analyze our design against the standard linear, differential, and algebraic attacks. Choosing suitable S-boxes and a quasigroup of a smaller order does not compromise the security of the cipher, but the storage space is reduced compared with AES-128 and INRU.

Optimal sampling-based path planning for mobile cable-driven parallel robots in highly constrained environment

Mobile cable-driven parallel robots (MCDPRs) is a novel concept of cable-driven parallel robots (CDPRs) developed by mounting several mobile bases to discrete the conventional fixed frame. However, the additional mobile bases introduce more degree-of-freedom (DoF), thereby causing the kinematic redundancy. Moreover, mobile bases are susceptible to disturbances causing inconsistent performance. Hence, path planning of MCDPRs becomes a challenging issue due to various internal and external constraints involved. In this article, an optimization-based path planning method is proposed for MCDPRs in highly constrained environments with considering kinematic stability. The proposed approach quickly generates feasible paths for coupled mobile bases by using the developed multi-agent rapidly exploring random tree (MA-RRT). In this process, the tree can share information through the heuristics method to optimize the path, and the adaptive sampling strategy is thus proposed to increase the tree growth efficiency by self-adjusting sampling space. Moreover, the developed dynamic control checking method (DCC) is integrated with MA-RRT to smooth the path and the kinodynamic constraints of mobile bases can be satisfied. To generate the path of the end-effector, two performance metrics are designed considering the kinematic and stability of the MCDPR. Based on the performance metrics, the grid-based search method is developed to generate the path for the end-effector. Finally, the convincing performance of the proposed method is revealed through the dynamic simulation software (CoppeliaSim) and real-world experiments based on a self-built MCDPR prototype.

Takeoff of a 2.1 g Fully Untethered Tailless Flapping-Wing Micro Aerial Vehicle With Integrated Battery

Insect-scale micro-aerial vehicles (MAV) are becoming increasingly important for sensing and mapping spatially constrained environments. However, achieving untethered flight powered by a small and lightweight on-board energy source remains a challenge. In this study, we successfully demonstrated the untethered takeoff of a flapping-wing MAV powered by a commercially available LiPo battery for a short duration without stability control. By incorporating a high-efficiency direct-drive piezoelectric actuator, and an optimized control circuit for high-impedance-width modulation and charge recovery, this electronics configuration realizes over 5 min of practical operation with a thrust of 1.5 times its own weight, while offering wireless communication capability and sensors for attitude estimation. Our MAV has a total mass of 2.1 g, which is an eight-fold reduction compared to the lightest battery-powered tailless flapping-wing MAV currently available, making this the first report of a battery-powered tailless flapping-wing MAV with insect-scale weight.

A Lightweight Exoskeleton Force Feedback Glove

The wearable force feedback glove provides a promising solution for enhancing immersion during teleoperation. In this study, a lightweight five-finger exoskeleton force feedback glove (EFFG) was designed, enabling driving force detection and flexible force feedback. This wireless prototype weighs only 278 g. The glove features a bionic structure and optimized linkage length to ensure operator safety while providing extensive coverage of the finger working space. Moreover, a detailed illustration of the kinematic and dynamic analyses, as well as the circuit structure, was presented. With this prototype as the basis, an isomorphic teleoperation system is designed to achieve force feedback during teleoperation. Concurrently, a driving force-based impedance controller was proposed to enable smooth and precise force feedback. Finally, the performance of the EFFG prototype was evaluated in both unconstrained and constrained environments, demonstrating that the proposed glove is lightweight, capable of detecting driving force, and provides flexible force feedback.

New blender-based augmentation method with quantitative evaluation of CNNs for hand gesture recognition

<p>In this study, we extensively analyze and evaluate the performance of recent deep neural networks (DNNs) for hand gesture recognition and static gestures in particular. To this end, we captured an unconstrained hand dataset with complex appearances, shapes, scales, backgrounds, and viewpoints. We then deployed some new trending convolution neuron networks (CNNs) for gesture classification. We arrived at three major conclusions: i) DenseNet121 architecture is the best recognition rate through almost evaluated red, green, blue (RGB) and augmentation datasets. Its performance is outstanding in most original works; ii) blender-based augmentation help to significantly increase 9% of accuracy, compared to the use of a RGB cues; iii) most CNNs can achieve impressive results at 97% accuracy when the training and testing datasets come from the same lab-based or constrained environment. Their performance is drastically reduced when dealing with gestures collected in unconstrained environments. In particular, we validated the best CNN on a new unconstrained dataset. We observed a significant reduction with an accuracy of only 74.55%. This performance can be improved up to 80.59% by strategies such as blender-based and/or GAN-based data augmentations to obtain an acceptable result of 83.17%. These findings contribute crucial factors and make fruitful recommendations for the development of a robust hand-based interface in practice</p>