In this paper, we address the problem of simultaneously achieving low trajectory tracking errors and compliant control without using explicit mathematical models of task dynamics. To achieve this goal, we propose a new movement representation called compliant movement primitives (CMPs), which encodes position trajectory and associated torque profiles and can be learned from a single user demonstration. With the proposed control framework, the robot can remain compliant and consequently safe for humans sharing its workspace, even if high trajectory tracking accuracy is required. We developed a statistical learning approach that can use a database of existing CMPs and compute new ones, adapted for novel task variations. The proposed approach was evaluated on a Kuka LWR-4 robot performing 1) a discrete pick-and-place task with objects of varying weight and 2) a periodic handle turning operation. The evaluation of the discrete task showed a 15-fold decrease of the tracking error while exhibiting compliant behavior compared to the standard feedback control approach. It also indicated no significant rise in the tracking error while using generalized primitives computed by the statistical learning method. With respect to unforeseen collisions, the proposed approach resulted in a 75% drop of contact forces compared to standard feedback control. The periodic task demonstrated on-line use of the proposed approach to accomplish a task of handle turning.

In this paper, we address the most pressing challenges faced by the manufacturing sector, particularly the manufacturing of small and medium-sized enterprises (SMEs), where the transition towards high-mix low-volume production and the availability of cost-effective solutions are crucial. To overcome these challenges, this paper presents 14 innovative solutions that can be utilized to support the introduction of agile manufacturing processes in SMEs. These solutions encompass a wide range of key technologies, including reconfigurable fixtures, low-cost automation for printed circuit board (PCB) assembly, computer-vision-based control, wireless sensor networks (WSNs) simulations, predictive maintenance based on Internet of Things (IoT), virtualization for operator training, intuitive robot programming using virtual reality (VR), autonomous trajectory generation, programming by demonstration for force-based tasks, on-line task allocation in human–robot collaboration (HRC), projector-based graphical user interface (GUI) for HRC, human safety in collaborative work cells, and integration of automated ground vehicles for intralogistics. All of these solutions were designed with the purpose of increasing agility in the manufacturing sector. They are designed to enable flexible and modular manufacturing systems that are easy to integrate and use while remaining cost-effective for SMEs. As such, they have a high potential to be implemented in the manufacturing industry. They can be used as standalone modules or combined to solve a more complicated task, and contribute to enhancing the agility, efficiency, and competitiveness of manufacturing companies. With their application tested in industrially relevant environments, the proposed solutions strive to ensure practical implementation and real-world impact. While this paper presents these solutions and gives an overview of their methodologies and evaluations, it does not go into their details. It provides summaries of comprehensive and multifaceted solutions to tackle the evolving needs and demands of the manufacturing sector, empowering SMEs to thrive in a dynamic and competitive market landscape.

In order to be effective, learning of robotic motion by demonstration should not remain limited to direct repetition of movements, but should enable modifications with respect to the state of the external environment, and generation of actions for previously unencountered situations. In this paper we propose an approach that combines these two features, and applies them in the framework of dynamic movement primitives (DMP). The proposed approach is based on the notion of motion adaptation through the use of coupling terms introduced to the DMPs at the velocity level. The coupling term is learned in a few repetitions of the motion with iterative learning control (ILC). The adaptation, which is based on force feedback, derives from either autonomous contact with the environment, or from human intervention. It can adapt to a given constraint, e.g., to a desired force of contact or to a given position. The major novelty of this paper is in extending this notion with statistical generalization between the coupling terms, allowing online adaptation of motion to a previously unexplored situation. The benefit of the approach is in reduced effort in human demonstration, because a single demonstration can be autonomously adapted to different situations with ILC, and recording the learned coupling terms builds up a database for generalization. A side-effect of learning, which takes a few iterations, is that also the coupling terms of the learning attempts can be stored in the database, allowing for different generalization queries and outcomes. In the paper we provide the details on the approach, followed by simulated and real-world evaluations.

Continuous learning of object affordances in a cognitive robot is a challenging problem, the solution to which arguably requires a developmental approach. In this paper, we describe scenarios where robotic systems interact with household objects by pushing them using robot arms while observing the scene with cameras, and which must incrementally learn, without external supervision, both the effect classes that emerge from these interactions as well as a discriminative model for predicting them from object properties. We formalize the scenario as a multi-view learning problem where data co-occur over two separate data views over time, and we present an online learning framework that uses a self-supervised form of learning vector quantization to build the discriminative model. In various experiments, we demonstrate the effectiveness of this approach in comparison with related supervised methods using data from experiments performed using two different robotic platforms.

Human robot cooperation is a challenging task of future generation home robots and is relevant also for industrial applications, where robots are supposed to act together with humans in non-structured environments. The paper focuses on on-line adaptation of robot trajectories, where robots and humans are autonomous agents coupled only through the manipulated object. Within the proposed approach, the robot adapts to the human intentions through the sensory feedback, where safety is one of the most important issues. The algorithm is based on representation of trajectories with the Dynamic Movement Primitives, where the adaptation of the corresponding robot trajectories relies on the Iterative Learning Controller framework. In order to demonstrate the effectiveness of the proposed approach, we applied two KUKA LWR robots in a bimanual human-robot collaborative task.