Search

El bipedisme és un dels trets més característics dels humanoides, però aconseguir una locomoció robusta continua sent un dels problemes més difícils de la robòtica. Les dificultats sorgeixen de la complexitat de la dinàmica híbrida d'alta dimensió, combinada amb les limitacions computacionals. Normalment s'utilitzen models d'ordre reduït per abordar aquest problema, però aquests models no capturen la dinàmica completa del robot. En aquest treball, proposem un marc jeràrquic que combina una política de planificació d'espais de tasques d'alt nivell, composta per un controlador predictiu basat en models (MPC) i un terme residual après mitjançant l'aprenentatge per reforç, amb un whole-body controller a un nivell inferior, per fer seguir de les trajectòries de l'espai de tasques desitjades. L'MPC utilitza un model d'ordre reduït per generar una política de pas subòptima, que es millora posteriorment per la política residual, que té en compte la dinàmica del cos sencer del robot. L'MPC actuarà com a guia durant el procés d'entrenament, facilitant un aprenentatge eficient. El marc proposat es prova en simulació en tres escenaris diferents, com ara caminar cap endavant i enrere, girar, i caminar sota forces externes. Demostrant que la nova política és capaç de millorar i generar una locomoció robusta., Uno de los rasgos más característicos de los humanoides es el bipedismo, sin embargo lograr una locomoción robusta sigue siendo uno de los problemas más desafiantes de la robótica. Las dificultades son debidas a la altra dimensionalidad y complejidad la dinámica híbrida, combinada con las restricciones computacionales. Normalmente se emplean modelos de orden reducido para abordar este problema, sin embargo, estos modelos no logran capturar la dinámica completa del robot. En este trabajo, proponemos un marco jerárquico que combina una planificación de tareas de alto nivel, compuesta por un controlador predictivo basado en modelos (MPC) y un término residual aprendido mediante aprendizaje por refuerzo, con un whole-body controller en un nivel inferior para seguir las trayectorias deseadas en el espacio de tareas. El MPC utiliza un modelo de orden reducido para generar una política de pasos subóptima, mejorada posteriormente por la política residual, que tiene en cuenta la dinámica de todo el cuerpo del robot. El MPC actuará como guía durante el proceso de entrenamiento, facilitando un aprendizaje eficiente. El marco propuesto se prueba en simulación en tres escenarios distintos: caminar hacia delante y hacia atrás, girar, y caminar bajo fuerzas externas. Demostrando que la nueva política es capaz de mejorar y generar una locomoción robusta., Bipedal walking is one of the most characteristic features of humanoids, yet achieving a robust locomotion remains a challenging problem in robotics. The difficulties arise from the complexity of high-dimensional hybrid dynamics, combined with real-time and computational constraints. Reduced-order models are typically employed to address this problem, however, these models do not fully capture the dynamics of the robot. In this work, we propose a hierarchical framework that combines a high-level task space planner policy, composed of a model-based model predictive controller (MPC) and a residual term learned through reinforcement learning, with a lower-level whole-body controller to track the desired task space trajectories. The MPC uses a reduced-order model to generate a suboptimal footstep policy, which is subsequently improved by the residual policy, which takes into account the full-body dynamics of the robot. The MPC will act as a guide during the training process, facilitating efficient learning. The proposed framework is tested on simulation across three distinct scenarios such as forward and backward walking, turning, and walking under external forces, showing that the new policy is able to improve and generate robust locomotion., Outgoing

Creating machines that resemble a human morphology have always been an aspiring goal for mankind even from the early days of engineering. Today, this effort continues to exist especially because of how much adaptive and flexible humans can be, as we can carry out a wide variety of tasks by collectively using our arms and legs. We can run, fall, get back up, and even use our arms or tools to provide additional stability when carrying out different locomotion or manipulation tasks. Imagine how much more helpful machines could be in our lives if we could build human-like machines that could do even a fraction of what we can. Traditionally however, humanoids have been big, bulky machines that moved around very slowly and were susceptible to disturbances and falling down.Recently, with the collective advancement of key technologies, we have seen a rapid growth in the number of quadrupeds that can now dynamically walk and run in outdoor environments. Quadrupeds are inherently a stable platform, which is opposite to a biped that is inherently unstable. Yet, the underlying core principles in both hardware and software could be selectively adopted in a humanoid context to enhance their agility and robustness.Hence, this dissertation is an extension of such ideas on a humanoid to make our human-like machines dynamically walk and run such that they can do more meaningful tasks in the future. This requires a development of a hardware platform that uses similar design principles that were successful on quadrupeds, as well as a software and control stack that uses state-of-the-art techniques to robustly control the robot. Therefore, this dissertation introduces ARTEMIS, the first full-sized humanoid robot using proprioceptive actuators, its key design features, along with a real-time optimization-based dynamic locomotion stack that allows ARTEMIS to walk and run. Such hardware and software development allowed ARTEMIS to be the fastest walking humanoid reaching up to 2.1 m/s walki

Currently the prevalence of general purpose mobile robots with manipulation capabilities is still low, despite various applications of such systems such as: disaster response, payload delivery, and assistive/service tasks. A suitable design for such a robot would be that of a torque-controllable quadrupedal manipulator. Its capability for legged locomotion enables high mobility, specifically on rough terrain, while its quadrupedal morphology provides a relatively large and stable base of support compared to bipedal robots. Torque-controlled joints allow for safer and more controllable interaction with the environment. For such a system a challenge lies in the design of a controller that actually achieves the promising capabilities for locomotion and manipulation that the mechanical system offers. One of the currently most promising control frameworks for this purpose is that of hierarchical inverse dynamics. This real-time whole-body control framework allows for dynamic whole-body motions and compliant interaction with the environment while enforcing a strict priority between the desired control tasks. Although promising results have previously been attained with such controllers, it has not yet been applied for the control of a quadrupedal manipulator. The focus of this thesis is on the implementation of a hierarchical inverse dynamics controller for the control of a simulated quadrupedal manipulator, with a particular focus on the design of prioritized sets of control tasks which generate forms of stationary whole-body manipulation. First a basic set of prioritized control tasks is presented, which is shown to satisfy the robot's most crucial control requirements. Subsequently three extended sets of control tasks are presented, which result in additional desirable emergent behavior of the robot. The first one of these depends on the inclusion of kinematic joint limit tasks to prevent kinematic singularities and self-collision, and to trigger wh

Currently the prevalence of general purpose mobile robots with manipulation capabilities is still low, despite various applications of such systems such as: disaster response, payload delivery, and assistive/service tasks. A suitable design for such a robot would be that of a torque-controllable quadrupedal manipulator. Its capability for legged locomotion enables high mobility, specifically on rough terrain, while its quadrupedal morphology provides a relatively large and stable base of support compared to bipedal robots. Torque-controlled joints allow for safer and more controllable interaction with the environment. For such a system a challenge lies in the design of a controller that actually achieves the promising capabilities for locomotion and manipulation that the mechanical system offers. One of the currently most promising control frameworks for this purpose is that of hierarchical inverse dynamics. This real-time whole-body control framework allows for dynamic whole-body motions and compliant interaction with the environment while enforcing a strict priority between the desired control tasks. Although promising results have previously been attained with such controllers, it has not yet been applied for the control of a quadrupedal manipulator. The focus of this thesis is on the implementation of a hierarchical inverse dynamics controller for the control of a simulated quadrupedal manipulator, with a particular focus on the design of prioritized sets of control tasks which generate forms of stationary whole-body manipulation. First a basic set of prioritized control tasks is presented, which is shown to satisfy the robot's most crucial control requirements. Subsequently three extended sets of control tasks are presented, which result in additional desirable emergent behavior of the robot. The first one of these depends on the inclusion of kinematic joint limit tasks to prevent kinematic singularities and self-collision, and to trigger wh

With the ability to navigate natural and man-made environments and utilize standard human tools, humanoid robots have the potential to transform emergency response and disaster relief applications by serving as first responders in hazardous scenarios. Such applications will require major advances in humanoid control, enabling robots to traverse difficult, cluttered terrain with both speed and stability. To advance the state of the art, this dissertation presents a complete dynamic locomotion and whole-body control framework for compliant (torque-controlled) humanoids. We develop low-level, mid-level, and high-level controllers to enable low-impedance balancing and walking on compliant and uneven terrain. For low-level control, we present a cascaded joint impedance controller for series elastic humanoids with parallel actuation. A distributed controller architecture is implemented using a dual-axis motor controller that computes desired actuator forces and motor currents using simple models of the joint mechanisms and series elastic actuators. An inner-loop force controller is developed using feedforward and PID control with a model-based disturbance observer, enabling naturally compliant behaviors with low joint impedance. For mid-level control, we implement an optimization-based whole-body control strategy assuming a rigid body model of the robot. Joint torque setpoints are computed using an efficient quadratic program (QP) given desired joint accelerations, spatial accelerations, and momentum rates of change. Constraints on the centroidal dynamics, contact forces, and joint limits ensure admissibility of the optimized setpoints. Using this approach, we develop compliant standing and stepping behaviors based on simple feedback controllers. For high-level control, we present a dynamic planning and control approach for humanoid locomotion using a novel time-varying extension of the Divergent Component of Motion (DCM). By varying the natural frequency of the DCM, we a