Matching Items (63)
Filtering by
- Member of: ASU Electronic Theses and Dissertations
Description
The ubiquity of single camera systems in society has made improving monocular depth estimation a topic of increasing interest in the broader computer vision community. Inspired by recent work in sparse-to-dense depth estimation, this thesis focuses on sparse patterns generated from feature detection based algorithms as opposed to regular grid sparse patterns used by previous work. This work focuses on using these feature-based sparse patterns to generate additional depth information by interpolating regions between clusters of samples that are in close proximity to each other. These interpolated sparse depths are used to enforce additional constraints on the network’s predictions. In addition to the improved depth prediction performance observed from incorporating the sparse sample information in the network compared to pure RGB-based methods, the experiments show that actively retraining a network on a small number of samples that deviate most from the interpolated sparse depths leads to better depth prediction overall.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
ContributorsRai, Anshul (Author) / Yang, Yezhou (Thesis advisor) / Zhang, Wenlong (Committee member) / Liang, Jianming (Committee member) / Arizona State University (Publisher)
Created2019
Description
Wearable assistive devices have been greatly improved thanks to advancements made in soft robotics, even creation soft extra arms for paralyzed patients. Grasping remains an active area of research of soft extra limbs. Soft robotics allow the creation of grippers that due to their inherit compliance making them lightweight, safer for human interactions, more robust in unknown environments and simpler to control than their rigid counterparts. A current problem in soft robotics is the lack of seamless integration of soft grippers into wearable devices, which is in part due to the use of elastomeric materials used for the creation of most of these grippers. This work introduces fabric-reinforced textile actuators (FRTA). The selection of materials, design logic of the fabric reinforcement layer and fabrication method are discussed. The relationship between the fabric reinforcement characteristics and the actuator deformation is studied and experimentally verified. The FRTA are made of a combination of a hyper-elastic fabric material with a stiffer fabric reinforcement on top. In this thesis, the design, fabrication, and evaluation of FRTAs are explored. It is shown that by varying the geometry of the reinforcement layer, a variety of motion can be achieve such as axial extension, radial expansion, bending, and twisting along its central axis. Multi-segmented actuators can be created by tailoring different sections of fabric-reinforcements together in order to generate a combination of motions to perform specific tasks. The applicability of this actuators for soft grippers is demonstrated by designing and providing preliminary evaluation of an anthropomorphic soft robotic hand capable of grasping daily living objects of various size and shapes.
ContributorsLopez Arellano, Francisco Javier (Author) / Santello, Marco (Thesis advisor) / Zhang, Wenlong (Thesis advisor) / Buneo, Christopher (Committee member) / Arizona State University (Publisher)
Created2019
Description
Stiffness and flexibility are essential in many fields, including robotics, aerospace, bioengineering, etc. In recent years, origami-based mechanical metamaterials were designed for better mechanical properties including tunable stiffness and tunable collapsibility. However, in existing studies, the tunable stiffness is only with limited range and limited controllability. To overcome these challenges, two objectives were proposed and achieved in this dissertation: first, to design mechanical metamaterials with metamaterials with selective stiffness and collapsibility; second, to design mechanical metamaterials with in-situ tunable stiffness among positive, zero, and negative.In the first part, triangulated cylinder origami was employed to build deployable mechanical metamaterials through folding and unfolding along the crease lines. These deployable structures are flexible in the deploy direction so that it can be easily collapsed along the same way as it was deployed. An origami-inspired mechanical metamaterial was designed for on-demand deployability and selective collapsibility: autonomous deployability from the collapsed state and selective collapsibility along two different paths, with low stiffness for one path and substantially high stiffness for another path. The created mechanical metamaterial yields unprecedented load bearing capability in the deploy direction while possessing great deployability and collapsibility. The principle in this prospectus can be utilized to design and create versatile origami-inspired mechanical metamaterials that can find many applications.
In the second part, curved origami patterns were designed to accomplish in situ stiffness manipulation covering positive, zero, and negative stiffness by activating predefined creases on one curved origami pattern. This elegant design enables in situ stiffness switching in lightweight and space-saving applications, as demonstrated through three robotic-related components. Under a uniform load, the curved origami can provide universal gripping, controlled force transmissibility, and multistage stiffness response. This work illustrates an unexplored and unprecedented capability of curved origami, which opens new applications in robotics for this particular family of origami patterns.
ContributorsZhai, Zirui (Author) / Nian, Qiong (Thesis advisor) / Zhuang, Houlong (Committee member) / Huang, Huei-Ping (Committee member) / Zhang, Wenlong (Committee member) / Liu, Yongming (Committee member) / Arizona State University (Publisher)
Created2021
Description
Floating trash objects are very commonly seen on water bodies such as lakes, canals and rivers. With the increase of plastic goods and human activities near the water bodies, these trash objects can pile up and cause great harm to the surrounding environment. Using human workers to clear out these trash is a hazardous and time-consuming task. Employing autonomous robots for these tasks is a better approach since it is more efficient and faster than humans. However, for a robot to clean the trash objects, a good detection algorithm is required. Real-time object detection on water surfaces is a challenging issue due to nature of the environment and the volatility of the water surface. In addition to this, running an object detection algorithm on an on-board processor of a robot limits the amount of CPU consumption that the algorithm can utilize. In this thesis, a computationally low cost object detection approach for robust detection of trash objects that was run on an on-board processor of a multirotor is presented. To account for specular reflections on the water surface, we use a polarization filter and integrate a specularity removal algorithm on our approach as well. The challenges faced during testing and the means taken to eliminate those challenges are also discussed. The algorithm was compared with two other object detectors using 4 different metrics. The testing was carried out using videos of 5 different objects collected at different illumination conditions over a lake using a multirotor. The results indicate that our algorithm is much suitable to be employed in real-time since it had the highest processing speed of 21 FPS, the lowest CPU consumption of 37.5\% and considerably high precision and recall values in detecting the object.
ContributorsSyed, Danish Faraaz (Author) / Zhang, Wenlong (Thesis advisor) / Yang, Yezhou (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2021
Description
Unmanned aerial vehicles (UAVs) have reshaped the world of aviation. With the emergence of different types of UAVs, a multitude of mission critical applications, e.g., aerial photography, package delivery, grasping and manipulation, aerial reconnaissance and surveillance have been accomplished successfully. All of the aforementioned applications require the UAVs to be robust to external disturbances and safe while flying in cluttered environments and these factors are of paramount importance for task completion. In the first phase, this dissertation starts by presenting the synthesis and experimental validation of real-time low-level estimation and robust attitude and position controllers for multirotors. For the task of reliable position estimation, a hybrid low-pass de-trending filter is proposed for attenuating noise and drift in the velocity and position estimates respectively. Subsequently, a disturbance observer (DOB) approach with online Q-filter tuning is proposed for disturbance rejection and precise position control. Finally, a non-linear disturbance observer (NDOB) approach, along with a parameter optimization framework, is proposed for robust attitude control of multirotors. Multiple simulation and experimental flight tests are performed to demonstrate the efficacy of the proposed algorithms. Aerial grasping and collection is a type of mission-critical task which requires vision based sensing and robust control algorithms for successful task completion. In the second phase, this dissertation initially explores different object grasping approaches utilizing soft and rigid graspers. Additionally, vision based control paradigms are developed for object grasping and collection applications, specifically from water surfaces. Autonomous object collection from water surfaces presents a multitude of challenges: i) object drift due to propeller outwash, ii) reflection and glare from water surfaces makes object detection extremely challenging and iii) lack of reliable height sensors above water surface (for autonomous landing on water). Finally, a first of its kind aerial manipulation system, with an integrated net system and a robust vision based control structure, is proposed for floating object collection from water surfaces. Objects of different shapes and sizes are collected, through multiple experimental flight tests, with a success rate of 91.6%. To the best of the author's knowledge, this is the first work demonstrating autonomous object collection from water surfaces.
ContributorsMishra, Shatadal (Author) / Zhang, Wenlong (Thesis advisor) / Berman, Spring M (Committee member) / Sugar, Thomas G (Committee member) / Arizona State University (Publisher)
Created2021
Description
Soft robotics has garnered attention for its substantial prospective in various domains, such as manipulation and interactions with humans, by offering competitive advantages against rigid robotic systems, including inherent compliance and variable stiffness. Despite these benefits, their theoretically infinite degrees of freedom and prominent nonlinearities pose significant challenges in developing dynamic models and guiding the robots along desired paths. Additionally, soft robots may exhibit rigid behaviors and potentially collide with their surroundings during path tracking tasks, particularly when possible contact points are unknown. In this dissertation, reduced-order models are used to describe the behaviors of three different soft robot designs, including both linear parameter varying (LPV) and augmented rigid robot (ARR) models. While the reduced-order model captures the majority of the soft robot's dynamics, modeling uncertainties notably remain. Non-repeated modeling uncertainties are addressed by categorizing them as a lumped disturbance, employing two methodologies, $H_\infty$ method and nonlinear disturbance observer (NDOB) based sliding mode control, for its rejection. For repeated disturbances, an iterative learning control (ILC) with a P-type learning function is implemented to enhance trajectory tracking efficacy. Furthermore,for non-repeated disturbances, the NDOB facilitates the contact estimation, and its results are jointly used with a switching algorithm to modify the robot trajectories. The stability proof of all controllers and corresponding simulation and experimental results are provided. For a path tracking task of a soft robot with multi-segments, a robust control strategy that combines a LPV model with an innovative improved nonlinear disturbance observer-based adaptive sliding mode control (INASMC). The control framework employs a first-order LPV model for dynamic representation, leverages an improved disturbance observer for accurate disturbance forecasting, and utilizes adaptive sliding mode control to effectively counteract uncertainties. The tracking error under the proposed controller is proven to be asymptotically stable, and the controller's effectiveness is is validated with simulation and experimental results. Ultimately, this research mitigates the inherent uncertainty in soft robot modeling, thereby enhancing their functionality in contact-intensive tasks.
ContributorsQIAO, ZHI (Author) / Zhang, Wenlong (Thesis advisor) / Marvi, Hamidreza (Committee member) / Lee, Hyunglae (Committee member) / Berman, Spring (Committee member) / Sugar, Thomas (Committee member) / Arizona State University (Publisher)
Created2023
Description
Robots programmed to follow human commands have struggled to accurately interpret human intentions down to the motion level. There has been growing research in robotics to integrate descriptive natural language commands into robot actions. Existing correction methods often rely on less intuitive approaches like direct manipulation, requiring full user attention. To address this challenge, I present a framework that uses natural language adverbial corrections to bridge the gap between human intent and robotic execution. Integrating these natural language corrections with robot demonstrations allows for iterative policy adjustments without sacrificing performance. This leverages the flexibility of natural language to convey complex goals, potentially surpassing the limitations of reward functions and expert demonstrations. Formulating the problem with parameterized robot trajectories, the method tested two robotic domains: a 7-degree-of-freedom Franka robotic arm and a synthetic 1-degree-of-freedom arm performing reaching and waving tasks. The action generation model employs a regressive transformer and an action chunking approach. The experiments demonstrate that robots can modulate their trajectories according to adverbial instructions — such as "move faster" — 86% and "move slower" — 79% of the time. This enhances human-robot collaboration by enabling robots to understand and execute tasks with language-informed precision, potentially improving assistive robotics and making human-robot interactions safer.
ContributorsKondepudi, Naga Suresh Krishna (Author) / Gopalan, Nakul (Thesis advisor) / Zhang, Wenlong (Committee member) / Senanayake, Ransalu (Committee member) / Arizona State University (Publisher)
Created2024
Description
Collision-resilient quadrotors have gained significant attention for operating in cluttered environments and leveraging impacts to perform agile maneuvers. However, existing designs are typically single-mode: either safeguarded by propeller guards that prevent deformation or deformable but lacking rigidity, which is crucial for stable flight in open environments. This thesis introduces DART, a Dual-stiffness Aerial RoboT, that adapts its post-collision response by either engaging a locking mechanism for a rigid mode or disengaging it for a flexible mode, respectively. Comprehensive characterization tests highlight the significant difference in post-collision responses between its rigid and flexible modes, with the rigid mode offering seven times higher stiffness compared to the flexible mode. To understand and harness the collision dynamics, a novel collision response prediction model based on the linear complementarity system theory has been proposed. The accuracy of predicting collision forces for both the rigid and flexible modes of DART is analysed by performing flight tests. Experimental results confirm the accuracy of the model and underscore its potential to advance collision-inclusive trajectory planning in aerial robotics.
ContributorsKumar, Yogesh (Author) / Zhang, Wenlong (Thesis advisor) / Jin, Wanxin (Committee member) / Aukes, Daniel (Committee member) / Arizona State University (Publisher)
Created2024
Description
What if there is a way to integrate prosthetics seamlessly with the human body and robots could help improve the lives of children with disabilities? With physical human-robot interaction being seen in multiple aspects of life, including industry, medical, and social, how these robots are interacting with human becomes even more important. Therefore, how smoothly the robot can interact with a person will determine how safe and efficient this relationship will be. This thesis investigates adaptive control method that allows a robot to adapt to the human's actions based on the interaction force. Allowing the relationship to become more effortless and less strained when the robot has a different goal than the human, as seen in Game Theory, using multiple techniques that adapts the system. Few applications this could be used for include robots in physical therapy, manufacturing robots that can adapt to a changing environment, and robots teaching people something new like dancing or learning how to walk after surgery.
The experience gained is the understanding of how a cost function of a system works, including the tracking error, speed of the system, the robot’s effort, and the human’s effort. Also, this two-agent system, results into a two-agent adaptive impedance model with an input for each agent of the system. This leads to a nontraditional linear quadratic regulator (LQR), that must be separated and then added together. Thus, creating a traditional LQR. This new experience can be used in the future to help build better safety protocols on manufacturing robots. In the future the knowledge learned from this research could be used to develop technologies for a robot to allow to adapt to help counteract human error.
The experience gained is the understanding of how a cost function of a system works, including the tracking error, speed of the system, the robot’s effort, and the human’s effort. Also, this two-agent system, results into a two-agent adaptive impedance model with an input for each agent of the system. This leads to a nontraditional linear quadratic regulator (LQR), that must be separated and then added together. Thus, creating a traditional LQR. This new experience can be used in the future to help build better safety protocols on manufacturing robots. In the future the knowledge learned from this research could be used to develop technologies for a robot to allow to adapt to help counteract human error.
ContributorsBell, Rebecca C (Author) / Zhang, Wenlong (Thesis advisor) / Chiou, Erin (Committee member) / Aukes, Daniel (Committee member) / Arizona State University (Publisher)
Created2019
Description
The knee joint has essential functions to support the body weight and maintain normal walking. Neurological diseases like stroke and musculoskeletal disorders like osteoarthritis can affect the function of the knee. Besides physical therapy, robot-assisted therapy using wearable exoskeletons and exosuits has shown the potential as an efficient therapy that helps patients restore their limbs’ functions. Exoskeletons and exosuits are being developed for either human performance augmentation or medical purposes like rehabilitation. Although, the research on exoskeletons started early before exosuits, the research and development on exosuits have recently grown rapidly as exosuits have advantages that exoskeletons lack. The objective of this research is to develop a soft exosuit for knee flexion assistance and validate its ability to reduce the EMG activity of the knee flexor muscles. The exosuit has been developed with a novel soft fabric actuator and novel 3D printed adjustable braces to attach the actuator aligned with the knee. A torque analytical model has been derived and validate experimentally to characterize and predict the torque output of the actuator. In addition to that, the actuator’s deflation and inflation time has been experimentally characterized and a controller has been implemented and the exosuit has been tested on a healthy human subject. It is found that the analytical torque model succeeded to predict the torque output in flexion angle range from 0° to 60° more precisely than analytical models in the literature. Deviations existed beyond 60° might have happened because some factors like fabric extensibility and actuator’s bending behavior. After human testing, results showed that, for the human subject tested, the exosuit gave the best performance when the controller was tuned to inflate at 31.9 % of the gait cycle. At this inflation timing, the biceps femoris, the semitendinosus and the vastus lateralis muscles showed average electromyography (EMG) reduction of - 32.02 %, - 23.05 % and - 2.85 % respectively. Finally, it is concluded that the developed exosuit may assist the knee flexion of more diverse healthy human subjects and it may potentially be used in the future in human performance augmentation and rehabilitation of people with disabilities.
ContributorsHasan, Ibrahim Mohammed Ibrahim (Author) / Zhang, Wenlong (Thesis advisor) / Aukes, Daniel (Committee member) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2021