User profiles for Valerio Modugno
Valerio ModugnoAssociate Lecturer, University College London (UCL) Verified email at ucl.ac.uk Cited by 385 |
Robust real-time whole-body motion retargeting from human to humanoid
Transferring the motion from a human operator to a humanoid robot is a crucial step to enable
robots to learn from and replicate human movements. The ability to retarget in realtime …
robots to learn from and replicate human movements. The ability to retarget in realtime …
A multimode teleoperation framework for humanoid loco-manipulation: An application for the icub robot
Over the years, there have been many improvements in job-related safety standards and
working conditions, but there are still many situations and environments where human lives are …
working conditions, but there are still many situations and environments where human lives are …
Learning soft task priorities for control of redundant robots
One of the key problems in planning and control of redundant robots is the fast generation
of controls when multiple tasks and constraints need to be satisfied. In the literature, this …
of controls when multiple tasks and constraints need to be satisfied. In the literature, this …
Navigation among movable obstacles via multi-object pushing into storage zones
K Ellis, D Hadjivelichkov, V Modugno… - IEEE …, 2023 - ieeexplore.ieee.org
With the majority of mobile robot path planning methods being focused on obstacle avoidance,
this paper, studies the problem of Navigation Among Movable Obstacles (NAMO) in an …
this paper, studies the problem of Navigation Among Movable Obstacles (NAMO) in an …
Bayesian neural network modeling and hierarchical MPC for a tendon-driven surgical robot with uncertainty minimization
In order to guarantee precision and safety in robotic surgery, accurate models of the robot
and proper control strategies are needed. Bayesian Neural Networks (BNN) are capable of …
and proper control strategies are needed. Bayesian Neural Networks (BNN) are capable of …
Learning needle pick-and-place without expert demonstrations
We introduce a novel approach for learning a complex multi-stage needle pick-and-place
manipulation task for surgical applications using Reinforcement Learning without expert …
manipulation task for surgical applications using Reinforcement Learning without expert …
Gait generation using intrinsically stable MPC in the presence of persistent disturbances
From a control point of view, humanoid gait generation can be seen as a problem of
tracking a suitable ZMP trajectory while guaranteeing internal stability. In the presence of …
tracking a suitable ZMP trajectory while guaranteeing internal stability. In the presence of …
Learning robust task priorities and gains for control of redundant robots
Generating complex movements in redundant robots like humanoids is usually done by
means of multi-task controllers based on quadratic programming, where a multitude of tasks is …
means of multi-task controllers based on quadratic programming, where a multitude of tasks is …
ViT-A*: Legged Robot Path Planning using Vision Transformer A
…, S Lyu, D Hadjivelichkov, V Modugno… - 2023 IEEE-RAS …, 2023 - ieeexplore.ieee.org
Legged robots, particularly quadrupeds, offer promising navigation capabilities, especially
in scenarios requiring traversal over diverse terrains and obstacle avoidance. This paper …
in scenarios requiring traversal over diverse terrains and obstacle avoidance. This paper …
An online learning procedure for feedback linearization control without torque measurements
By exploiting an a-priori estimate of the dynamic model of a manipulator, it is possible to
command joint torques which ideally realize a Feedback Linearization (FL) controller. The exact …
command joint torques which ideally realize a Feedback Linearization (FL) controller. The exact …