Optimizing the Human-Robot Workplace

#artificialintelligence

Case Western Reserve University engineers are working with partners at two other universities and an Italian-owned company in Michigan to study, predict, and optimize how robots will interact with human co-workers in factories of the future. While robots have been increasingly integrated into manufacturing since their introduction in the early 1960s, true human-robot workplace collaboration is still in the early stages and is only recently being earnestly studied by academics. Most researchers anticipate humans taking on the more nimble decision-making, while robots contribute by lifting heavy tools or putting the right tool at a worker's side when needed. "You could see this more on an assembly line, where the human is building an engine, screwing the spark plugs into the engine block, and the robot is handing him the right tools and parts at the right time," says Robert Gao, Chairman of Mechanical and Aerospace Engineering. Gao is principal investigator on a National Science Foundation-funded project examining robot-human collaborations in manufacturing workplaces.


Generating Plans that Predict Themselves

arXiv.org Artificial Intelligence

Collaboration requires coordination, and we coordinate by anticipating our teammates' future actions and adapting to their plan. In some cases, our teammates' actions early on can give us a clear idea of what the remainder of their plan is, i.e. what action sequence we should expect. In others, they might leave us less confident, or even lead us to the wrong conclusion. Our goal is for robot actions to fall in the first category: we want to enable robots to select their actions in such a way that human collaborators can easily use them to correctly anticipate what will follow. While previous work has focused on finding initial plans that convey a set goal, here we focus on finding two portions of a plan such that the initial portion conveys the final one. We introduce $t$-\ACty{}: a measure that quantifies the accuracy and confidence with which human observers can predict the remaining robot plan from the overall task goal and the observed initial $t$ actions in the plan. We contribute a method for generating $t$-predictable plans: we search for a full plan that accomplishes the task, but in which the first $t$ actions make it as easy as possible to infer the remaining ones. The result is often different from the most efficient plan, in which the initial actions might leave a lot of ambiguity as to how the task will be completed. Through an online experiment and an in-person user study with physical robots, we find that our approach outperforms a traditional efficiency-based planner in objective and subjective collaboration metrics.


From the Programmer's Apprentice to Human-Robot Interaction: Thirty Years of Research on Human-Computer Collaboration

AAAI Conferences

We summarize the continuous thread of research we have conducted over the past thirty years on human-computer collaboration. This research reflects many of the themes and issues in operation in the greater field of AI over this period, such as knowledge representation and reasoning, planning and intent recognition, learning, and the interplay of human theory and computer engineering.


Speech, Gesture, and Space: Investigating Explicit and Implicit Communication in Multi-Human Multi-Robot Collaborations

AAAI Conferences

Effective communication is often required for agents to properly handle collaborative multi-agent tasks. This is particularly true when humans are working alongside synthetic agents and traditional wireless communication modes are impractical. A framework for communication must allow for both explicit communication, where actions are directly execute to convey information, and implicit communication, where the agent projects information indirectly as a consequence of actions taken to achieve the tasks. We propose a Theory of Mind-based approach to communication that allows an agent to reason about its own state, the states of the other agents, and the other agents’ beliefs about each other’s state.


Are You Prepared to Partner with the Machines?

#artificialintelligence

Artificial intelligence (AI) is no longer just a futuristic notion--it's here now, and more and more businesses are using it to fuel efficiency, growth and innovation. How is that going to impact your career--and are you prepared to partner with the machines? Reimagining business We believe that AI will not replace human workers, but will actually augment their abilities by complementing their skills, collaborating on complex tasks and freeing them from routine or repetitive tasks through automation. When we reviewed what 1,200 businesses around the world are doing with AI, we found that the leaders in this group are, in fact, investing in this kind of human and machine collaboration to grow faster, earn more and hire more people than their competitors. They are moving toward the idea of highly flexible teams that partner humans with AI solutions as they bring voice recognition, machine learning, intelligent robotics and other kinds of AI into the organization.