Physically-Proximal Human-Robot Collaboration: Enhancing Safety and Efficiency Through Intent Prediction

McGhan, Catharine L. R.; Atkins, Ella M.

doi:10.2514/6.2009-1950

Cited by 4 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our primary graduate research objective has been to optimize human-robot mission performance such that the direct supervision of the robot's abilities by a human collaborator or operator is unnecessary. 11 This ultimately requires that the robot sense and identify the human's action trajectories, match them to tasks, and predict intent -translated to the human's most likely future actions and anticipated schedule of their execution -to minimize the likelihood of physically interfering with the human's arm movements or task-focused visual gaze. This also necessitates that the robot be able to sense and react safely and efficiently to the human in cases where the human does not move as anticipated.…”

Section: B Research: Human-robot Collaborationmentioning

confidence: 99%

A Low-Cost Manipulator for Space Research and Undergraduate Engineering Education

McGhan

Atkins

2010

AIAA Infotech@Aerospace 2010

Self Cite

View full text Add to dashboard Cite

This paper describes a supervised undergraduate design-build-test effort in which young students supported by the University of Michigan's Undergraduate Research Opportunities Program (UROP) were able to design, build, test, and extend a robotic manipulator of dimensions comparable to those of a human arm. This project had two goals: to expose students to the design-build-test process in the context of robotic electrical, mechanical, and software systems, and to construct an artifact, the manipulator, for the subsequent support of graduate-level research in human-robot collaboration pursued by the first author. This manipulator system was low-cost, required little prior knowledge of machining, and was required to operate robustly and safely in an environment shared with its human collaborator. In this paper, we describe the design-build-test process from the pedagogical and system engineering perspectives. Ultimately, the students focused their efforts on research in sensing, software, and mathematical modeling of the manipulator, emphasizing the fact that hardware DBT is only the first step to a fully-operational robotic system. This was a key observation not made by many Aerospace students, even those exposed to DBT activities that typically highlight physical vehicle design while "black-boxing" sensors and software. This paper describes the process by which this group was educated in the context of the manipulator DBT process. We briefly discuss subsequent manipulator use and extension both for graduate research and ongoing undergraduate DBT exposure.

show abstract

Section: B Research: Human-robot Collaborationmentioning

confidence: 99%

A Low-Cost Manipulator for Space Research and Undergraduate Engineering Education

McGhan

Atkins

2010

AIAA Infotech@Aerospace 2010

Self Cite

View full text Add to dashboard Cite

show abstract

“…To focus our attention on human-robot productivity rather than robot capabilities and limitations, we provide 'ideal' intent data to the robot: a human test conductor presses keys indicating which next task the human test subject appears to be pursuing when that task is initiated. This enables the robot to predict near-term conflicts and react appropriately to complete its own motion-based task(s), either by avoiding physical contact with the human or line-of-sight occlusion of the human's gaze [1].…”

mentioning

confidence: 99%

Human Productivity in a Workspace Shared with a Safe Robotic Manipulator

McGhan

Atkins

2014

Journal of Aerospace Information Systems

View full text Add to dashboard Cite

“…From previous human subject testing, we have determined that, in our ground-based scenario, the inclusion of the robot in shared-workspace operations without explicit communications did not significantly reduce human productivity, even when only minimal conflict-avoidance algorithms were used for 'intelligent' task-selection. 14,16 This implies that so long as the robot causes only minimal interference or conflict with the human, the human would be expected to have similar productivity as if the robot was not there, so any additional goals accomplished by the robot would improve overall team productivity.…”

Section: The Use Of Predicted Companion Intent Results In Improved Rementioning

confidence: 99%

“…Our previous experiments in which a seated human executes these tasks in an environment shared by a fixed-based robot manipulator confirm HRI is feasible for this scenario. 16 We hypothesize that our basic simulation and experimental results will translate to models of humans performing similar activities in IVA in space. In our HRI scenario, the human is asked to type solutions to simple arithmetic problems as quickly and efficiently as possible while not overly concerning themselves with the robot's motion.…”

Section: Case Study: Space Hri Domain Representationmentioning

confidence: 97%

See 1 more Smart Citation

Towards Guaranteeing Safe and Efficient Human-Robot Collaboration Using Human Intent Prediction

McGhan

Atkins²

2012

AIAA SPACE 2012 Conference &Amp; Exposition

Self Cite

View full text Add to dashboard Cite

This paper describes an autonomous framework for determining a robotic manipulator's optimal actions in real-time when interacting in close physical proximity to a human in a shared workspace environment. This framework allows the robot to purposefully choose to avoid physical and mental conflicts with a human companion while each agent performs tasks to complete their respective, separately-assigned goals. We pose scenarios in which the human does not need to divert attention to internally model the robot's behavior, or track or acknowledge the robot's actions during operations. The robot is meant to unobtrusively 'work around' the human rather than directly collaborate on task completion. The distinction of this work is in its use of human intent prediction (HIP) as a key factor in robot action selection for task-level planning. We choose to model HIP with a Markov Decision Process (MDP). Human state data is input into the HIP MDP policy that then outputs the predicted human intent, which we define as the best-matched or most-likely in-progress and future action-choice(s) that the human is or will be pursuing to complete mission goals. Predicted human intent is then used by a second MDP to determine the optimal policy with respect to the robot's action-choice. We present an autonomous framework that integrates the HIP MDP and robot action-choice (RAC) MDP to support autonomous close-proximity operations and propose offline and online (scaled) formulations of the two MDPs. During real-time policy execution, once the optimal action for the robot to take is determined, it is passed to the robot's path planner to be translated from a task-level command to a trajectory and motion primitives, which are then given to a low-level controller to enact. We evaluate our HIP MDP in simulation, and find that the policy output from our system is consistent and smooth across small changes in parameter values.

show abstract

Physically-Proximal Human-Robot Collaboration: Enhancing Safety and Efficiency Through Intent Prediction

Cited by 4 publications

References 5 publications

A Low-Cost Manipulator for Space Research and Undergraduate Engineering Education

A Low-Cost Manipulator for Space Research and Undergraduate Engineering Education

Human Productivity in a Workspace Shared with a Safe Robotic Manipulator

Towards Guaranteeing Safe and Efficient Human-Robot Collaboration Using Human Intent Prediction

Contact Info

Product

Resources

About