Human-Robot Collaborative Assembly Planning using Hybrid Conditional Planning

Abstract

For assembly planning, robots necessitate certain cognitive skills: high-level planning of actuation actions is needed to decide for the order of actuation actions, while geometric reasoning is needed to check the feasibility of these actions. For collaborative assembly tasks with humans, robots require further cognitive capabilities, such as commonsense reasoning, sensing, and communication skills, not only to cope with the uncertainty caused by incomplete knowledge about the humans' behaviors but also to ensure safe collaborations. We introduce a novel formal framework for collaborative assembly planning that utilizes hybrid conditional planning extended with commonsense reasoning and a rich set of communication actions for collaborative tasks. We evaluate this method by a set of experiments in a furniture assembly domain.

International Symposium on Occupational Safety and Hygiene: Proceedings Book of the SHO2021

“…Moreover, Landi et al, (2018), also focus on the reduction of the operators workload, considering the interaction tasks between both robot and human and analysing the mental workload of the operator, so that the robotic system can then adapt its performance accordingly through the utilization of assistive technologies, and the goal of reducing the stress of the operator intends to increase the overall productivity. Rizwan et al, (2018) introduces a framework for HRC that uses hybrid conditional planning and a set of communication actions for collaborative tasks, stating that robots require a certain level of cognitive skills, such as communication skills, to ensure the safety of the collaboration process. Rückert et al, (2018) specifies that to a robot to adapt fast towards the different product variants and to be able to assist the worker in personalized tasks, there is the need for a greater connectivity, such as mentioned by Rizwan et al, (2018), so the implementation of systems such has infrared cameras and 3D image processing can be better performed.…”

“…Rizwan et al, (2018) introduces a framework for HRC that uses hybrid conditional planning and a set of communication actions for collaborative tasks, stating that robots require a certain level of cognitive skills, such as communication skills, to ensure the safety of the collaboration process. Rückert et al, (2018) specifies that to a robot to adapt fast towards the different product variants and to be able to assist the worker in personalized tasks, there is the need for a greater connectivity, such as mentioned by Rizwan et al, (2018), so the implementation of systems such has infrared cameras and 3D image processing can be better performed. Tan et al, (2010) demonstrated four main design factors for the design of HRC in cellular workstations, the first factor being the collaboration planning by task modelling, the second factor the collaboration safety, the most important consideration, the third factor considering the mental workload collaboration and the fourth the man-machine interface.…”

Socially intelligent task and motion planning for human-robot interaction

“…Endowing robots with social agency-the understanding of oneself as a social actor-is an open challenge that must be addressed before robots can plan safe and reliable behavior in HSEs [1][2][3][4]14]. Socially-aware planning seeks to model social context in order to generate appropriate policies for HSEs [13][14][15][16]. Many existing socially-aware planners use proxemics, the social affordance of space [5], to represent social context as an objective function over the environment [17][18][19].…”