Eloise Dalin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Eloise Dalin has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Jean-Baptiste Mouret
Université de Lorraine, CNRS, Inria, Nancy, France
3 shared publications - Serena Ivaldi
Inria, Université de Lorraine, CNRS
3 shared publications - Alexis Aubry
Université de Lorraine, CNRS, CRAN
1 shared publication Ivan Bergonzani
Inria Nancy - Grand Est, Universit de Lorraine, CNRS, Villers-ls-Nancy, France
1 shared publication- Lorenzo Vianello
University of Lorraine, CNRS, Inria, LORIA, Nancy, France
1 shared publication - Pauline Maurice
Universit de Lorraine, CNRS, Inria, LORIA, Nancy, France
1 shared publication
Latest Publications
- 6 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 9028-9035
First Do Not Fall: Learning to Exploit a Wall With a Damaged Humanoid Robot
Humanoid robots could replace humans in hazardous situations but most of such situations are equally dangerous for them, which means that they have a high chance of being damaged and falling. We hypothesize that humanoid robots would be mostly used in buildings, which makes them likely to be close to a wall. To avoid a fall, they can therefore lean on the closest wall, as a human would do, provided that they find in a few milliseconds where to put the hand(s). This letter introduces a method, called D-Reflex, that learns a neural network that chooses this contact position given the wall orientation, the wall distance, and the posture of the robot. This contact position is then used by a whole-body controller to reach a stable posture. We show that D-Reflex allows a simulated TALOS robot (1.75 m, 100 kg, 30 degrees of freedom) to avoid more than 75% of the avoidable falls and can work on the real robot.
- 6 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 9028-9035
First Do Not Fall: Learning to Exploit a Wall With a Damaged Humanoid Robot
Humanoid robots could replace humans in hazardous situations but most of such situations are equally dangerous for them, which means that they have a high chance of being damaged and falling. We hypothesize that humanoid robots would be mostly used in buildings, which makes them likely to be close to a wall. To avoid a fall, they can therefore lean on the closest wall, as a human would do, provided that they find in a few milliseconds where to put the hand(s). This letter introduces a method, called D-Reflex, that learns a neural network that chooses this contact position given the wall orientation, the wall distance, and the posture of the robot. This contact position is then used by a whole-body controller to reach a stable posture. We show that D-Reflex allows a simulated TALOS robot (1.75 m, 100 kg, 30 degrees of freedom) to avoid more than 75% of the avoidable falls and can work on the real robot.
- 13 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (1) , 342-349
Multi-Objective Trajectory Optimization to Improve Ergonomics in Human Motion
Work-related musculoskeletal disorders are a major health issue often caused by awkward postures. Identifying and recommending more ergonomic body postures requires optimizing the worker’s motion with respect to ergonomics criteria based on the human kinematic/kinetic state. However, many ergonomics scores assess different risks at different places of the human body, and therefore, optimizing for only one score might lead to postures that are either inefficient or that transfer the risk to a different location. We verified, in two work activities, that optimizing for a single ergonomics score may lead to motions that degrade scores other than the optimized one. To address this problem, we propose a multi-objective optimization approach that can find better Pareto-optimal trade-off motions that simultaneously optimize multiple scores. Our simulation-based approach is also user-specific and can be used to recommend ergonomic postures to workers with different body morphologies. Additionally, it can be used to generate ergonomic reference trajectories for robot controllers in human-robot collaboration.
- 13 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (1) , 342-349
Multi-Objective Trajectory Optimization to Improve Ergonomics in Human Motion
Work-related musculoskeletal disorders are a major health issue often caused by awkward postures. Identifying and recommending more ergonomic body postures requires optimizing the worker’s motion with respect to ergonomics criteria based on the human kinematic/kinetic state. However, many ergonomics scores assess different risks at different places of the human body, and therefore, optimizing for only one score might lead to postures that are either inefficient or that transfer the risk to a different location. We verified, in two work activities, that optimizing for a single ergonomics score may lead to motions that degrade scores other than the optimized one. To address this problem, we propose a multi-objective optimization approach that can find better Pareto-optimal trade-off motions that simultaneously optimize multiple scores. Our simulation-based approach is also user-specific and can be used to recommend ergonomic postures to workers with different body morphologies. Additionally, it can be used to generate ergonomic reference trajectories for robot controllers in human-robot collaboration.
- 4 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (3) , 6046-6053
Human Posture Prediction During Physical Human-Robot Interaction
When a human is interacting physically with a robot to accomplish a task, his/her posture is inevitably influenced by the robot movement. Since the human is not controllable, an active robot imposing a collaborative trajectory should predict the most likely human posture. This prediction should consider individual differences and preferences of movement execution, and it is necessary to evaluate the impact of the robot's action from an ergonomics standpoint. Here, we propose a method to predict, in probabilistic terms, the human postures of an individual for a given robot trajectory executed in a collaborative scenario. We formalize the problem as the prediction of the human joints velocity given the current posture and robot end-effector velocity. The key idea of our approach is to learn the distribution of the null space of the Jacobian and the weights of the weighted pseudo-inverse from demonstrated human movements: both carry information about human postural preferences, to leverage redundancy and ensure that the predicted posture will be coherent with the end-effector position. We validate our approach in a simulated toy problem and on two real human-robot interaction experiments where a human is physically interacting with a Franka robot.
- 4 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (3) , 6046-6053
Human Posture Prediction During Physical Human-Robot Interaction
When a human is interacting physically with a robot to accomplish a task, his/her posture is inevitably influenced by the robot movement. Since the human is not controllable, an active robot imposing a collaborative trajectory should predict the most likely human posture. This prediction should consider individual differences and preferences of movement execution, and it is necessary to evaluate the impact of the robot's action from an ergonomics standpoint. Here, we propose a method to predict, in probabilistic terms, the human postures of an individual for a given robot trajectory executed in a collaborative scenario. We formalize the problem as the prediction of the human joints velocity given the current posture and robot end-effector velocity. The key idea of our approach is to learn the distribution of the null space of the Jacobian and the weights of the weighted pseudo-inverse from demonstrated human movements: both carry information about human postural preferences, to leverage redundancy and ensure that the predicted posture will be coherent with the end-effector position. We validate our approach in a simulated toy problem and on two real human-robot interaction experiments where a human is physically interacting with a Franka robot.
- Open Access
- 6 November 2019
- Published by Open Source Robotics Foundation
Dynamixel under ROS Control.
Eloïse Dalin, Pierre Desreumaux and Jean-Baptiste Mouret ( INRIA / CNRS / Université de Lorraine) https://roscon.ros.org/fr/2019 dynamixel_control_hw…
- 6 November 2019
- Published by Open Source Robotics Foundation
Open AccessDynamixel under ROS Control.
Eloïse Dalin, Pierre Desreumaux and Jean-Baptiste Mouret ( INRIA / CNRS / Université de Lorraine) https://roscon.ros.org/fr/2019 dynamixel_control_hw…