Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant’s intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms.

Objective: This meta-analysis reviews robot design features of interface, controller, and appearance and statistically summarizes their effect on successful human–robot interaction (HRI) at work (that is, task performance, cooperation, satisfaction, acceptance, trust, mental workload, and situation awareness). Background: Robots are becoming an integral part of many workplaces. As interactions with employees increase, ensuring success becomes ever more vital. Even though many studies investigated robot design features, an overview on general and specific effects is missing. Method: Systematic selection of literature and structured coding led to 81 included experimental studies containing 380 effect sizes. Mean effects were calculated using a three-level meta-analysis to handle dependencies of multiple effect sizes in one study. Results: Sufficient feedback through the interface, clear visibility of affordances, and adaptability and autonomy of the controller significantly affect successful HRI, whereas appearance does not. The features of the interface and controller affect performance and satisfaction but do not affect situation awareness and trust. Specific effects of adaptability on cooperation and acceptance, as well as autonomy on mental workload, could be shown. Conclusion: Robot design at work needs to cover multiple features of interface and controller to achieve successful HRI that covers not only performance and satisfaction, but also cooperation, acceptance, and mental workload. More empirical research is needed to investigate mediating mechanisms and underrepresented design features’ effects. Application: Robot designers should carefully choose design features to balance specific effects and implementation costs with regard to tasks, work design aims, and employee needs in the specific work context.

Concentric Tube Continuum Robots are among the smallest and most flexible instruments in development for minimally invasive surgery, thereby enabling operations in areas within the human body that are difficult to reach. Unfortunately, integrating state-of-the-art force sensors is challenging for these robots due to their small form factor, although contact forces are essential information in surgical procedures. In this work, we propose a novel data-driven approach based on Deep Direct Cascade Learning (DDCL) to create a virtual sensor for computing the tip contact force of Concentric Tube Continuum Robots. By exploiting the robot’s backbone’s inherent elasticity, deflection is used to estimate the respective external tip contact force. We evaluate our approach on different data representations for a single tube and apply it subsequently on a three-segment Concentric Tube Continuum Robot. Furthermore, we devise a novel transfer learning approach through DDCL to improve the estimation accuracy by pre-training a cascaded network with simulated data. Subsequently, we fine-tune the network based on a small real-world data set recorded from the physical robot.

Neural conditioning associates cues and actions with following rewards. The environments in which robots operate, however, are pervaded by a variety of disturbing stimuli and uncertain timing. In particular, variable reward delays make it difficult to reconstruct which previous actions are responsible for following rewards. Such an uncertainty is handled by biological neural networks, but represents a challenge for computational models, suggesting the lack of a satisfactory theory for robotic neural conditioning. The present study demonstrates the use of rare neural correlations in making correct associations between rewards and previous cues or actions. Rare correlations are functional in selecting sparse synapses to be eligible for later weight updates if a reward occurs. The repetition of this process singles out the associating and reward-triggering pathways, and thereby copes with distal rewards. The neural network displays macro-level classical and operant conditioning, which is demonstrated in an interactive real-life human-robot interaction. The proposed mechanism models realistic conditioning in humans and animals and implements similar behaviors in neuro-robotic platforms.

The plasticity of the human nervous system allows us to acquire an open-ended repository of sensorimotor skills in adulthood, such as the mastery of tools, musical instruments or sports. How novel sensorimotor skills are learned from scratch is yet largely unknown. In particular, the so-called inverse mapping from goal states to motor states is underdetermined because a goal can often be achieved by many different movements (motor redundancy). How humans learn to resolve motor redundancy and by which principles they explore high-dimensional motor spaces has hardly been investigated. To study this question, we trained human participants in an unfamiliar and redundant visually-guided manual control task. We qualitatively compare the experimental results with simulation results from a population of artificial agents that learned the same task by Goal Babbling, which is an inverse-model learning approach for robotics. In Goal Babbling, goal-related feedback guides motor exploration and thereby enables robots to learn an inverse model directly from scratch, without having to learn a forward model first. In the human experiment, we tested whether different initial conditions (starting positions of the hand) influence the acquisition of motor synergies, which we identified by Principal Component Analysis in the motor space. The results show that the human participants’ solutions are spatially biased towards the different starting positions in motor space and are marked by a gradual co-learning of synergies and task success, similar to the dynamics of motor learning by Goal Babbling. However, there are also differences between human learning and the Goal Babbling simulations, as humans tend to predominantly use Degrees of Freedom that do not have a large effect on the hand position, whereas in Goal Babbling, Degrees of Freedom with a large effect on hand position are used predominantly. We conclude that humans use goal-related feedback to constrain motor exploration and resolve motor redundancy when learning a new sensorimotor mapping, but in a manner that differs from the current implementation of Goal Babbling due to different constraints on motor exploration. Even in adulthood, humans can learn to master new motor skills with unfamiliar mappings between desired goals or sensations and corresponding movements, such as playing tennis or musical instruments. To master a new skill involves the resolution of motor redundancy; that is a selection from many possible movements that all achieve the same goal. Here, we trained participants in a redundant and unfamiliar task that mapped their hand movements to shapes, in order to investigate which of the many possible redundant solution participants learn. The results show that local task feedback, which depends on the starting posture of the hand, influences participants’ motor learning. We qualitatively compared the experimental results to computer simulations of artificial agents that learned the same task by Goal Babbling, i.e., a motor learning approach used in robotics, to assess if humans might learn the task following similar principles. Both the simulated agents and the participants show sensitivity to goal-directed feedback during learning, but they use different strategies to explore the movement space. We conclude that human motor learning and redundancy resolution is guided by local goal feedback, like in Goal Babbling, but that differences in motor exploration lead to different learning outcomes.