Human Preferences' Optimization in pHRI Collaborative Tasks

Franceschi, Paolo; Maccarini, Marco; Piga, Dario; Beschi, Manuel; Roveda, Loris

doi:10.1109/ur57808.2023.10202313

Cited by 1 publication

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In pHRC, something in between was done by Nikolaidis et al (2017b), where the human objective function is estimated while the human is learning the "true global cooperative reward" initially known only by the robot. More recent work takes the DG theoretical approach in haptic shared control, either assuming a known human cost function (Musić & Hirche, 2020) or learning one through Inverse Optimal Control (Franceschi et al, 2023). On the same motor-control level, Hafs et al (2024) apply IDG to estimate the human cost function in collaboration with an exoskeleton.…”

Section: Inverse Reinforcement Learningmentioning

confidence: 99%

Simultaneously learning intentions and preferences during physical human-robot cooperation

van der Spaa,

Kober,

Gienger

2024

Auton Robot

View full text Add to dashboard Cite

The advent of collaborative robots allows humans and robots to cooperate in a direct and physical way. While this leads to amazing new opportunities to create novel robotics applications, it is challenging to make the collaboration intuitive for the human. From a system’s perspective, understanding the human intentions seems to be one promising way to get there. However, human behavior exhibits large variations between individuals, such as for instance preferences or physical abilities. This paper presents a novel concept for simultaneously learning a model of the human intentions and preferences incrementally during collaboration with a robot. Starting out with a nominal model, the system acquires collaborative skills step-by-step within only very few trials. The concept is based on a combination of model-based reinforcement learning and inverse reinforcement learning, adapted to fit collaborations in which human and robot think and act independently. We test the method and compare it to two baselines: one that imitates the human and one that uses plain maximum entropy inverse reinforcement learning, both in simulation and in a user study with a Franka Emika Panda robot arm.

show abstract

Section: Inverse Reinforcement Learningmentioning

confidence: 99%