Interaction dynamics are difficult to model analytically, making data-driven controllers preferable for contact-rich manipulation tasks. In this work, we approximate the intricate dynamics of food-cutting with a Long Short-Term Memory (LSTM) model to apply a Model Predictive Controller (MPC). We propose a problem formulation that allows velocity-controlled robots to learn the interaction dynamics

Learning generative models and inferring latent trajectories have shown to be challenging for time series due to the intractable marginal likelihoods of flexible generative models. It can be addressed by surrogate objectives for optimization. We propose Monte Carlo filtering objectives (MCFOs), a family of variational objectives for jointly learning parametric generative models and amortized adapt

Regeringen föreslår nio åtgärder för att hitta och utvisa papperslösa. Det kommer att slå hårt och främst gå ut över redan svaga och jagade människor. Vi uppmanar därför regeringen att ta tillbaka åtgärderna, skriver 43 forskare.

In this work, the problem of human-robot collaborative object transfer to unknown target poses is addressed. The desired pattern of the end-effector pose trajectory to a known target pose is encoded using DMPs (Dynamic Movement Primitives). During transportation of the object to new unknown targets, a DMP-based reference model and an EKF (Extended Kalman Filter) for estimating the target pose and

Deformable object manipulation tasks have long been regarded as challenging robotic problems. However, until recently very little work has been done on the subject, with most robotic manipulation methods being developed for rigid objects. Deformable objects are more difficult to model and simulate, which has limited the use of model-free Reinforcement Learning (RL) strategies, due to their need fo

Deep Neural Networks (NNs) have been widely utilized in contact-rich manipulation tasks to model the complicated contact dynamics. However, NN-based models are often difficult to decipher which can lead to seemingly inexplicable behaviors and unidentifiable failure cases. In this work, we address the interpretability of NN-based models by introducing the kinodynamic images. We propose a methodolog

Recent advances in machine learning have triggered an enormous interest in using learning-based approaches for robot control and object manipulation. While the majority of existing algorithms are evaluated under the assumption that the involved bodies are rigid, a large number of practical applications contain deformable objects. In this work we focus on Deformable Linear Objects (DLOs) which can

The framework of Dynamical Movement Primitives (DMPs) has become a popular method for trajectory generation in robotics. Most robotic systems are subject to saturation and/or kinematic constraints on motion variables, but DMPs do not inherently encode constraints and this may lead to poor tracking performance. Temporal coupling (online temporal scaling) of DMPs represents a possible way for handli

In this letter, we propose a task-based role allocation control scheme for the cooperative manipulation of a rigid-body object held jointly by a human and a robot. The task-based allocation scheme allows an assistive robot to take an active role when the task is known. To deal with the translation/rotation problem, we define rotation and translation as distinct parameterized tasks. The task that d

Background and purpose — Older patients with a displaced femoral neck fracture (FNF) are often treated with a cemented primary hemiarthroplasty (HA). The DAICY trial investigates whether high-dose dual-impregnated antibiotic-loaded cement (DIAC) including gentamicin and clindamycin can reduce the risk of periprosthetic joint infection (PJI) in comparison with low-dose single-impregnated gentamicin

Coordinated dual-arm manipulation tasks can be broadly characterized as possessing absolute and relative motion components. Relative motion tasks, in particular, are inherently redundant in the way they can be distributed between end-effectors. In this work, we analyse cooperative manipulation in terms of the asymmetric resolution of relative motion tasks. We discuss how existing approaches enable