We present experimental analysis on subjects performing a bowing task, and we estimate the motion and kinetics quantities.
This paper details the implementation of state-of-the-art whole-body control algorithms on the humanoid robot iCub.
This paper describes an algorithm to perform dynamic computations . The method is computationally optimised with a sparse matrix factorisation.
This paper presents the goals and steps of the AnDy project, which leverages existing technologies to endow robots with the ability to control physical collaboration through intentional interaction.
This paper introduces the basis for human-in-the-loop robot controllers. We present a momentum-based torque controller exploiting human help.
This paper details a method for retargeting loco-manipulation motions from human demonstrations to humanoid robots. Our method allows the robot to adapt its motion to compensate for manipulated objects with different dynamics parameters.
The present study investigated how humans adapt to biological and non-biological velocity patterns in robot movements. Participants held the end-effector of a robot that traced an elliptic path with either biological (two-thirds power law) or non-biological velocity profiles.
The main purpose of this paper is to review the state-of-the-art on intermediate human–robot interfaces (bi-directional), robot control modalities, system stability, benchmarking and relevant use cases, and to extend views on the required future developments in the realm of human–robot collaboration.
This article describes our open-source software for predicting the intention of a user physically interacting with the humanoid robot iCub based on Probabilistic Movement Primitives (ProMPs), a versatile method for representing, generalizing, and reproducing complex motor skills.
In this paper, we introduce a trial-and-error learning algorithm that allows whole-body controllers to operate in spite of inaccurate models, without needing to update these models.
In this work, we optimize the task trajectories for whole-body balancing tasks with switching contacts, ensuring that the optimized movements are safe and never violate any of the robot and problem constraints. We use (1+1)-CMA-ES with Constrained Covariance Adaptation as a constrained black box stochastic optimization algorithm, with an instance of (1+1)- CMA-ES for bootstrapping the search.
This paper proposes a method for multi-modal prediction of intention based on a probabilistic description of movement primitives and goals. We target dyadic interaction between a human and a robot in a collaborative scenario.
This paper describes how to use musculoskeletal modelling to simulate physiological discomfort of exoskeletons. We introduce three biomechanical discomfort measures, muscle activation effort, representative joint reaction force and total metabolic cost
Towards real-time whole-body human dynamics estimation through probabilistic sensor fusion algorithms
This paper describes real-time whole-body human dynamics estimation during physical human-robot interaction.