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.

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.

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.

Recent years, there has been many attempts with different approaches to the human-robot interaction (HRI) problems. In this paper, the multi-agent interaction is formulated as a differential game with incomplete information. To tackle this problem, the parameter estimation method is utilized to obtain the approximated solution in a real time basis. Previous studies in the parameter estimation made the assumption that the human parameters are known by the robot; but such may not be the case and there exists uncertainty in the modeling of the human rewards as well as human's modeling of the robot's rewards. The proposed method, empathetic estimation, is tested and compared with the ``non-empathetic'' estimation from the existing works. The case studies are conducted in an uncontrolled intersection with two agents attempting to pass efficiently. Results have shown that in the case of both agents having inconsistent belief of the other agent's parameters, the empathetic agent performs better at estimating the parameters and has higher reward values, which indicates the scenarios when empathy is essential: when agent's initial belief is mismatched from the true parameters/intent of the agents.

Robotic assisted devices in gait rehabilitation have not seen penetration into clinical settings proportionate to the developments in this field. A possible reason for this is due to the development and evaluation of these devices from a predominantly engineering perspective. One way to mitigate this effect is to further include the principles of neurophysiology into the development of these systems. To further include these principles, this research proposes a method for grounded evaluation of three machine learning algorithms to gain insight on what modeling approaches are able to both replicate therapist assistance and emulate therapist strategies. The algorithms evaluated in this paper include ordinary least squares regression (OLS), gaussian process regression (GPR) and inverse reinforcement learning (IRL). The results show that grounded evaluation is able to provide evidence to support the algorithms at a higher resolution. Also, it was observed that GPR is likely the most accurate algorithm to replicate therapist assistance and to emulate therapist adaptation strategies.

This dissertation studies the methods to enhance the performance of foldable robots manufactured by laminated techniques. This class of robots are unique in their manufacturing process, which involves cutting and staking up thin layers of different materials with various stiffness. While inheriting the advantages of soft robots -- low weight, affordable manufacturing cost and a fast prototyping process -- a wider range of actuators is available to these mechanisms, while modeling their behavior requires less computational cost.The fundamental question this dissertation strives to answer is how to decode and leverage the effect of material stiffness in these robots. These robots' stiffness is relatively limited due to their slender design, specifically at larger scales. While compliant robots may have inherent advantages such as being safer to work around, this low rigidity makes modeling more complex. This complexity is mostly contained in material deformation since the conventional actuators such as servo motors can be easily leveraged in these robots. As a result, when introduced to real-world environments, efficient modeling and control of these robots are more achievable than conventional soft robots. Various approaches have been taken to design, model, and control a variety of laminate robot platforms by investigating the effect of material deformation in prototypes while they interact with their working environments. The results obtained show that data-driven approaches such as experimental identification and machine learning techniques are more reliable in modeling and control of these mechanisms. Also, machine learning techniques for training robots in non-ideal experimental setups that encounter the uncertainties of real-world environments can be leveraged to find effective gaits with high performance. Our studies on the effect of stiffness of thin, curved sheets of materials has evolved into introducing a new class of soft elements which we call Soft, Curved, Reconfigurable, Anisotropic Mechanisms (SCRAMs). Like bio-mechanical systems, SCRAMs are capable of re-configuring the stiffness of curved surfaces to enhance their performance and adaptability. Finally, the findings of this thesis show promising opportunities for foldable robots to become an alternative for conventional soft robots since they still offer similar advantages in a fraction of computational expense.

In the development of autonomous ground vehicles (AGVs), how to guarantee vehicle lateral stability is one of the most critical aspects. Based on nonlinear vehicle lateral and tire dynamics, new driving requirements of AGVs demand further studies and analyses of vehicle lateral stability control strategies. To achieve comprehensive analyses and stability-guaranteed vehicle lateral driving control, this dissertation presents three main contributions.First, a new method is proposed to estimate and analyze vehicle lateral driving stability regions, which provide a direct and intuitive demonstration for stability control of AGVs. Based on a four-wheel vehicle model and a nonlinear 2D analytical LuGre tire model, a local linearization method is applied to estimate vehicle lateral driving stability regions by analyzing vehicle local stability at each operation point on a phase plane. The obtained stability regions are conservative because both vehicle and tire stability are simultaneously considered. Such a conservative feature is specifically important for characterizing the stability properties of AGVs. Second, to analyze vehicle stability, two novel features of the estimated vehicle lateral driving stability regions are studied. First, a shifting vector is formulated to explicitly describe the shifting feature of the lateral stability regions with respect to the vehicle steering angles. Second, dynamic margins of the stability regions are formulated and applied to avoid the penetration of vehicle state trajectory with respect to the region boundaries. With these two features, the shiftable stability regions are feasible for real-time stability analysis. Third, to keep the vehicle states (lateral velocity and yaw rate) always stay in the shiftable stability regions, different control methods are developed and evaluated. Based on different vehicle control configurations, two dynamic sliding mode controllers (SMC) are designed. To better control vehicle stability without suffering chattering issues in SMC, a non-overshooting model predictive control is proposed and applied. To further save computational burden for real-time implementation, time-varying control-dependent invariant sets and time-varying control-dependent barrier functions are proposed and adopted in a stability-guaranteed vehicle control problem. Finally, to validate the correctness and effectiveness of the proposed theories, definitions, and control methods, illustrative simulations and experimental results are presented and discussed.

This work presents the design, modeling, analysis, and experimental characterization and testing of soft wearable robotics for lower limb rehabilitation for the ankle and hip. The Soft Robotic Ankle-Foot Orthosis (SR-AFO) is a wearable soft robot designed using multiple pneumatically-powered soft actuators to assist the ankle in multiple degrees-of-freedom during standing and walking tasks. The flat fabric pneumatic artificial muscle (ff-PAM) contracts upon pressurization and assists ankle plantarflexion in the sagittal plane. The Multi-material Actuator for Variable Stiffness (MAVS) aids in supporting ankle inversion/eversion in the frontal plane. Analytical models of the ff-PAM and MAVS were created to understand how the changing of the design parameters affects tensile force generation and stiffness support, respectively. The models were validated by both finite element analysis and experimental characterization using a universal testing machine. A set of human experiments were performed with healthy participants: 1) to measure lateral ankle support during quiet standing, 2) to determine lateral ankle support during walking over compliant surfaces, and 3) to evaluate plantarflexion assistance at push-off during treadmill walking, and 4) determine if the SR-AFO could be used for gait entrainment. Group results revealed increased ankle stiffness during quiet standing with the MAVS active, reduced ankle deflection while walking over compliant surfaces with the MAVS active, and reduced muscle effort from the SOL and GAS during 40 - 60% of the gait cycle with the dual ff-PAM active. The SR-AFO shows promising results in providing lateral ankle support and plantarflexion assistance with healthy participants, and a drastically increased basin of entrainment, which suggests a capability to help restore the gait of impaired users in future trials. The ff-PAM actuators were used in an X-orientation to assist the hip in flexion and extension. The Soft Robotic Hip Exosuit (SR-HExo) was evaluated using the same set of actuators and trials with healthy participants showed reduction in muscle effort during hip flexion and extension to further enhance the study of soft fabric actuators on human gait assistance.

With the substantial development of intelligent robots, human-robot interaction (HRI) has become ubiquitous in applications such as collaborative manufacturing, surgical robotic operations, and autonomous driving. In all these applications, a human behavior model, which can provide predictions of human actions, is a helpful reference that helps robots to achieve intelligent interaction with humans. The requirement elicits an essential problem of how to properly model human behavior, especially when individuals are interacting or cooperating with each other. The major objective of this thesis is to utilize the human intention decoding method to help robots enhance their performance while interacting with humans. Preliminary work on integrating human intention estimation with an HRI scenario is shown to demonstrate the benefit. In order to achieve this goal, the research topic is divided into three phases. First, a novel method of an online measure of the human's reliance on the robot, which can be estimated through the intention decoding process from human actions，is described. An experiment that requires human participants to complete an object-moving task with a robot manipulator was conducted under different conditions of distractions. A relationship is discovered between human intention and trust while participants performed a familiar task with no distraction. This finding suggests a relationship between the psychological construct of trust and joint physical coordination, which bridges the human's action to its mental states. Then, a novel human collaborative dynamic model is introduced based on game theory and bounded rationality, which is a novel method to describe human dyadic behavior with the aforementioned theories. The mutual intention decoding process was also considered to inform this model. Through this model, the connection between the mental states of the individuals to their cooperative actions is indicated. A haptic interface is developed with a virtual environment and the experiments are conducted with 30 human subjects. The result suggests the existence of mutual intention decoding during the human dyadic cooperative behaviors. Last, the empirical results show that allowing agents to have empathy in inference, which lets the agents understand that others might have a false understanding of their intentions, can help to achieve correct intention inference. It has been verified that knowledge about vehicle dynamics was also important to correctly infer intentions. A new courteous policy is proposed that bounded the courteous motion using its inferred set of equilibrium motions. A simulation, which is set to reproduce an intersection passing case between an autonomous car and a human driving car, is conducted to demonstrate the benefit of the novel courteous control policy.

Self-Driving cars are a long-lasting ambition for many AI scientists and engineers. In the last decade alone, many self-driving cars like Google Waymo, Tesla Autopilot, Uber, etc. have been roaming the streets of many cities. As a rapidly expanding field, researchers all over the world are attempting to develop more safe and efficient AI agents that can navigate through our cities. However, driving is a very complex task to master even for a human, let alone the challenges in developing robots to do the same. It requires attention and inputs from the surroundings of the car, and it is nearly impossible for us to program all the possible factors affecting this complex task. As a solution, imitation learning was introduced, wherein the agents learn a policy, mapping the observations to the actions through demonstrations given by humans. Through imitation learning, one could easily teach self-driving cars the expected behavior in many scenarios. Despite their autonomous nature, it is undeniable that humans play a vital role in the development and execution of safe and trustworthy self-driving cars and hence form the strongest link in this application of Human-Robot Interaction. Several approaches were taken to incorporate this link between humans and self-driving cars, one of which involves the communication of human's navigational instruction to self-driving cars. The communicative channel provides humans with control over the agent’s decisions as well as the ability to guide them in real-time. In this work, the abilities of imitation learning in creating a self-driving agent that can follow natural language instructions given by humans based on environmental objects’ descriptions were explored. The proposed model architecture is capable of handling latent temporal context in these instructions thus making the agent capable of taking multiple decisions along its course. The work shows promising results that push the boundaries of natural language instructions and their complexities in navigating self-driving cars through towns.