Synergistic Scheduling of Learning and Allocation of Tasks in Human-Robot Teams

  title={Synergistic Scheduling of Learning and Allocation of Tasks in Human-Robot Teams},
  author={Shivam Vats and Oliver Kroemer and Maxim Likhachev},
  journal={2022 International Conference on Robotics and Automation (ICRA)},
We consider the problem of completing a set of $n$ tasks with a human-robot team using minimum effort. In many domains, teaching a robot to be fully autonomous can be counterproductive if there are finitely many tasks to be done. Rather, the optimal strategy is to weigh the cost of teaching a robot and its benefit- how many new tasks it allows the robot to solve autonomously. We formulate this as a planning problem where the goal is to decide what tasks the robot should do autonomously (act… 

Figures from this paper

Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision

Experiments suggest that the allocation of humans to robots significantly affects robot fleet performance, and that the proposed Fleet-DAgger algorithm achieves up to 8.8 × higher return on human effort than baselines.



Towards Successful Coordination of Human and Robotic Work using Automated Scheduling Tools : An Initial Pilot Study

With the latest advancements in robotic manufacturing technology, there is a desire to integrate robot workers into the labor force to increase productivity and efficiency. However, coordinating the

Discovering task constraints through observation and active learning

This work introduces and experimentally validates two demonstration-based active learning strategies that a robot can utilize to accelerate context-free task comprehension, and shows an increased effectiveness of active learning when utilizing feature-based query strategies, especially in multi-instructor scenarios.

Adaptive mission planning for coupled human-robot teams

This work develops fast algorithms that integrate humans into the planning problem to produce allocations for tightly coupled human-robot teams that outperform those of alternative strategies.

A Framework for Learning From Demonstration With Minimal Human Effort

This work considers robot learning in the context of shared autonomy, where control of the system can switch between a human teleoperator and autonomous control, and learns to predict the success probability for each controller, given the initial state of an episode.

A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms

A formalization of the robot manipulation learning problem is described that synthesizes existing research into a single coherent framework and highlights the many remaining research opportunities and challenges.

Relational Learning for Skill Preconditions

This work proposes an object-relation model that learns continuous representations for pairwise object relations in simulation, and once learned, is used by a separate precondition model to predict skill preconditions for real world tasks.

Data-Efficient Generalization of Robot Skills with Contextual Policy Search

This work proposes a new model-based policy search approach that can also learn contextual upper-level policies and achieves a substantial improvement in learning speed compared to existing methods on simulated and real robotic tasks.

Human-Autonomy Teaming Using Flexible Human Performance Models: An Initial Pilot Study

An unmanned aerial vehicle (UAV) simulation is used to evaluate flexible human performance models over traditional static modeling approaches for multi-agent task allocation and scheduling and indicates that adaptivehuman performance models significantly increase total mission reward.

ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning

ThriftyDAgger, an algorithm for actively querying a human supervisor given a desired budget of human interventions, is presented and a novel metric for estimating risk under the current robot policy is introduced.