Learning Physical Collaborative Robot Behaviors From Human Demonstrations

By Leonel Dario Rozo, Sylvain Calinon, Darwin G. Caldwell, Pablo Jiménez, Carme Torras. IEEE Transactions on robotics, 2016

301 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/b5fc1a6353cf3e7047a7d636f56d06d0d66cbd1f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Control and Systems Engineering

Citations in the corpus

Human-Robot Collaboration in Manufacturing Applications: A Review (2019, methodology): “[48] 2016 WAM robot/ KUKA LWR iiwa Impedance/ admittance Hand-guiding Assembly HRI: Robotic assistant needs to be easily reprogrammed, thus programming by demonstration Model adapts to changes in starting and ending point, task, and control mode; with high compliance, the robot can not follow trajec”
Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks (2019, background): “Similar use of variable impedance as an action representation for LfD has been demonstrated to be successful for adaptive grasping [26], manipulation of deformable objects [22], and co-adaptation to human workers [36].”
Survey on human–robot collaboration in industrial settings: Safety, intuitive interfaces and applications (2018, background): “Furthermore, focusing on tasks involving physical contact with the user, an approach to learn the robot behaviour along the task, including safety requirements into the stiffness learning process, has been proposed in [63].”
Constraints extraction from asymmetrical bimanual tasks and their use in coordinated behavior (2018, background): “Physical human-robot collaboration consists of transmitting motion through an object and relies mostly on modelling force and torque data [24] (i.”
Guiding Trajectory Optimization by Demonstrated Distributions (2017, background): “In LfD, we can design a controller that adaptively determines the controller gain based on the variance of the trajectories [10], [17]–[19].”
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration (2020, background): “However, prior work in HRI has been mainly restricted in lab environments (Goodrich & Schultz, 2007; Dautenhahn, 2007; Nikolaidis et al., 2015; Rozo et al., 2016), and the goals in the collaborative tasks were either shared by both agents or were deﬁned in a small space.”