Adria Colome

Institute of Robotics and Industrial Informatics

Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the realworld. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between de...

Robotic cloth manipulation is a challenging problem for robotic systems. Textile items can adopt multiple configurations and shapes during their manipulation. Hence, robots should not only understand the current configuration of the item but also be able to predict its future possible behaviors and perform real-time control during manipulation. Thi...

Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the real-world. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between d...

Over the last years, significant advances have been made in robotic manipulation, but still, the handling of non-rigid objects, such as cloth garments, is an open problem. Physical interaction with non-rigid objects is uncertain and complex to model. Thus, extracting useful information from sample data can considerably improve modeling performance....

Learning from demonstration allows to encode task constraints from observing the motion executed by a human teacher. We present a Gaussian-process-based learning from demonstration (LfD) approach that allows robots to learn manipulation skills from demonstrations of a human teacher. By exploiting the potential that Gaussian process (GP) models offe...

Estimating the pose of an object from a monocular image is an inverse problem fundamental in computer vision. The ill-posed nature of this problem requires incorporating deformation priors to solve it. In practice, many materials do not perceptibly shrink or extend when manipulated, constituting a powerful and well-known prior. Mathematically, this...

Reinforcement Learning (RL) of trajectory data has been used in several fields, and it is of relevance in robot motion learning, in which sampled trajectories are run and their outcome is evaluated with a reward value. The responsibility on the performance of a task can be associated to the trajectory as a whole, or distributed throughout its point...

Robotic cloth manipulation is a relevant challenging problem for autonomous robotic systems. Highly deformable objects as textile items can adopt multiple configurations and shapes during their manipulation. Hence, robots should not only understand the current cloth configuration but also be able to predict the future possible behaviors of the clot...

This paper proposes to enrich robot motion data with trajectory curvature information. To do so, we use an approximate implementation of a topological feature named writhe, which measures the curling of a closed curve around itself, and its analog feature for two closed curves, namely the linking number. Despite these features have been established...

Over the last years, robotic cloth manipulation has gained relevance within the research community. While significant advances have been made in robotic manipulation of rigid objects, the manipulation of non-rigid objects such as cloth garments is still a challenging problem. The uncertainty on how cloth behaves often requires the use of model-base...

Learning from Demonstration (LfD) is a paradigm that allows robots to learn complex manipulation tasks that can not be easily scripted, but can be demonstrated by a human teacher. One of the challenges of LfD is to enable robots to acquire skills that can be adapted to different scenarios. In this paper, we propose to achieve this by exploiting the...

Learning from Demonstration (LfD) is a paradigm that allows robots to learn complex manipulation tasks that can not be easily scripted, but can be demonstrated by a human teacher. One of the challenges of LfD is to enable robots to acquire skills that can be adapted to different scenarios. In this paper, we propose to achieve this by exploiting the...

Endowed with higher levels of autonomy, robots are required to perform increasingly complex manipulation tasks. Learning from demonstration is arising as a promising paradigm for easily extending robot capabilities so that they adapt to unseen scenarios. We present a novel Gaussian-Process-based approach for learning manipulation skills from observ...

As mentioned in Chap. 5, Movement Primitives are nowadays widely used as movement parametrization for learning robot trajectories, because of their linearity in the parameters, rescaling robustness and continuity. However, when learning a movement with MPs, a very large number of Gaussian approximations needs to be performed. Adding them up for all...

Policy Search (PS) algorithms are nowadays widely used for their simplicity and effectiveness in finding solutions for robotic problems. However, most current PS algorithms derive policies by statistically fitting the data from the best experiments only. This means that those experiments yielding a poor performance are usually discarded or given to...

In this part of the monograph, we use the kinematic and control architectures built in Part I in order to learn cooperative manipulation. To this end, we will firstly introduce Policy Search (PS), a subtype of Reinforcement Learning in Sect. 5.1. For further details on PS, [4] presents a more exhaustive review, with a detailed description of many o...

Robot kinematics, specially Inverse Kinematics (IK) for redundant serial robots.

Robot compliant control aims at building controllers that react softly when a contact or deviation occurs. Contrary to a stiff control, where a robot will track the desired position commands and try to quickly compensate any deviation from such reference position, a compliant controller will allow deviations from such reference position. Such devia...

In this chapter we propose a framework for easily initializing ProMPs with synthetic data, and building a conditioning dataset in order to map context variables to motion parameters, which can be used for both exploiting its features by executing such contextualized trajectories, or improving through contextual PS. This method is combined with a st...

When attempting to perform bimanual robot manipulation, using reliable Inverse Kinematics methods is crucial, but also how to position two robots in order to cooperate. This chapter proposes two enhancements to the current state-of-the-art Closed-Loop Inverse Kinematics (CLIK) algorithms in Sect. 3.1, to then apply them to analyze the workspace and...

This book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It propose...

Transferring human motion to a mobile robotic manipulator and ensuring safe physical human-robot interaction are crucial steps towards automating complex manipulation tasks in human-shared environments. In this work we present a robot whole-body teleoperation framework for human motion transfer. We propose a general solution to the correspondence p...

Movement Primitives (MPs) have been widely adopted for representing and learning robotic movements using reinforcement learning policy search. Probabilistic Movement Primitives (ProMPs) are a kind of MP based on a stochastic representation over sets of trajectories, able to capture the variability allowed while executing a movement. This approach h...

Robotic manipulation often requires adaptation to changing environments. Such changes can be represented by a certain number of contextual variables that may be observed or sensed in different manners. When learning and representing robot motion -usually with movement primitives-, it is desirable to adapt the learned behaviors to the current contex...

Dynamic movement primitives (DMPs) are widely used as movement parametrization for learning robot trajectories, because of their linearity in the parameters, rescaling robustness, and continuity. However, when learning a movement with DMPs, a very large number of Gaussian approximations needs to be performed. Adding them up for all joints yields to...

In the context of assistive robotics, robots need to make multiple decisions. We explore the problem where a robot has multiple choices to perform a task and must select the action that maximizes success probability among a repertoire of pre-trained actions. We investigate the case in which sensory data is only available before making the decision,...

Assistant robots are designed to perform specific tasks for the user, but their performance is rarely optimal, hence they are required to adapt to user preferences or new task requirements. In the previous work, the potential of an interactive learning framework based on user intervention and reinforcement learning (RL) was assessed. The framework...

Policy search (PS) algorithms are widely used for their simplicity and effectiveness in finding solutions for robotic problems. However, most current PS algorithms derive policies by statistically fitting the data from the best experiments only. This means that experiments yielding a poor performance are usually discarded or given too little influe...

Social robots are expected to adapt to their users and, like their human counterparts, learn from the interaction. In our previous work, we proposed an interactive learning framework that enables a user to intervene and modify a segment of the robot arm trajectory. The framework uses gesture teleoperation and reinforcement learning to learn new mot...

Learning motion tasks in a real environment with deformable objects requires not only a Reinforcement Learning (RL) algorithm, but also a good motion characterization, a preferably compliant robot controller, and an agent giving feedback for the rewards/costs in the RL algorithm. In this paper, we unify all these parts in a simple but effective way...

Motivated by the need of a robust and practical inverse kinematics (IK) algorithm for the WAM robot arm, we reviewed the most used closed-loop IK methods for redundant robots, analyzing their main points of concern: convergence, numerical error, singularity handling, joint limit avoidance, and the capability of reaching secondary goals. As a result...

Humans as well as humanoid robots can use a large number of degrees of freedom to solve very complex motor tasks. The high-dimensionality of these motor tasks adds difficulties to the control problem and machine learning algorithms. However, it is well known that the intrinsic dimensionality of many human movements is small in comparison to the num...

Dynamic Movement Primitives (DMP) are nowadays widely used as movement parametrization for learning trajectories, because of their linearity in the parameters, rescaling robustness and continuity. However, when learning a movement with a robot using DMP, many parameters may need to be tuned, requiring a prohibitive number of experiments/simulations...

Bimanual manipulation of objects is receiving a lot of attention nowadays, but there is few literature addressing the design of the arms configuration. In this paper, we propose a way to analyze the relative positioning of two redundant arms, both equipped with spherical wrists, in order to obtain the best common workspace for grasping purposes. Co...

In this paper we present an automated system that is able to track and grasp a moving object within the workspace of a manipulator using range images acquired with a Microsoft Kinect sensor. Realtime tracking is achieved by a geometric particle filter on the affine group. Based on the tracked output, the pose of a 7-DoF WAM robotic arm is continuou...

This paper presents a method to estimate external forces exerted on a manipulator during motion, avoiding the use of a sensor. The method is based on task-oriented dynamics model learning and a robust disturbance state observer. The combination of both leads to an efficient torque observer that can be incorporated to any control scheme. The use of...

Motivated by the need of a robust and practical Inverse Kinematics (IK) algorithm for the WAM robot arm, we reviewed the most used closed-loop methods for redundant robots, analysing their main points of concern: convergence, numerical error, singularity handling, joint limit avoidance, and the capability of reaching secondary goals. As a result of...