Abstract
The field of Human-Robot Collaboration (HRC) has seen a considerable amount of progress in recent years. Thanks in part to advances in control and perception algorithms, robots have started to work in increasingly unstructured environments, where they operate side by side with humans to achieve shared tasks. However, little progress has been made toward the development of systems that are truly effective in supporting the human, proactive in their collaboration, and that can autonomously take care of part of the task. In this work, we present a collaborative system capable of assisting a human worker despite limited manipulation capabilities, incomplete model of the task, and partial observability of the environment. Our framework leverages information from a high-level, hierarchical model that is shared between the human and robot and that enables transparent synchronization between the peers and mutual understanding of each other’s plan. More precisely, we firstly derive a partially observable Markov model from the high-level task representation; we then use an online Monte-Carlo solver to compute a short-horizon robot-executable plan. The resulting policy is capable of interactive replanning on-the-fly, dynamic error recovery, and identification of hidden user preferences. We demonstrate that the system is capable of robustly providing support to the human in a realistic furniture construction task.
Highlights
In this work we provide shared task modeling through hierarchical task models (HTMs)
To Kaelbling and Lozano-Pérez (2013) we find approximate solutions to large Partially Observable Markov Decision Process (POMDP) problems through planning in belief space combined with just-in-time replanning
Our work differs from the literature in a number of ways: 1) the hierarchical nature of the task is not explicitly dealt with in the POMDP model, but rather at a higher level of abstraction
Summary
Recent trends in collaborative robotics are shifting focus on mixed human-robot environments where robots are flexibly adaptable to the rapid changes of the modern manufacturing process and can safely and effectively interoperate with humans. The human-robot collaboration (HRC) is still fundamentally unbalanced, with the bulk of the perceptual, cognitive and manipulation authority pertaining to the human To fill this gap, recent works have begun to investigate truly collaborative framework that allow the human and the robot to focus on the part of the task for which they are best suited, and mutually assist each other when needed (Shah and Breazeal, 2010; Hayes and Scassellati, 2015; El Makrini et al, 2017; Roncone et al, 2017; Chang and Thomaz, 2021). We explicitly account for uncertainty in the state of the world (e.g., task progression, availability of objects in the workspace) as well as in the state of the human partner (i.e., their beliefs, intents, and preferences) To this end, we employ a Partially Observable Markov Decision Process (POMDP) that plans optimal actions in the belief space.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
