DeepAI AI Chat
Log In Sign Up

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

by   Ryan Hoque, et al.

Commercial and industrial deployments of robot fleets often fall back on remote human teleoperators during execution when robots are at risk or unable to make task progress. With continual learning, interventions from the remote pool of humans can also be used to improve the robot fleet control policy over time. A central question is how to effectively allocate limited human attention to individual robots. Prior work addresses this in the single-robot, single-human setting. We formalize the Interactive Fleet Learning (IFL) setting, in which multiple robots interactively query and learn from multiple human supervisors. We present a fully implemented open-source IFL benchmark suite of GPU-accelerated Isaac Gym environments for the evaluation of IFL algorithms. We propose Fleet-DAgger, a family of IFL algorithms, and compare a novel Fleet-DAgger algorithm to 4 baselines in simulation. We also perform 1000 trials of a physical block-pushing experiment with 4 ABB YuMi robot arms. Experiments suggest that the allocation of humans to robots significantly affects robot fleet performance, and that our algorithm achieves up to 8.8x higher return on human effort than baselines. See for code, videos, and supplemental material.


Learning Human Objectives from Sequences of Physical Corrections

When personal, assistive, and interactive robots make mistakes, humans n...

IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors

Imitation learning has been applied to a range of robotic tasks, but can...

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

Effective robot learning often requires online human feedback and interv...

Web-based Experiment on Human Performance in Dual-Robot Teleoperation

In most cases, upgrading from a single-robot system to a multi-robot sys...

SEAN-EP: A Platform for Collecting Human Feedback for Social Robot Navigation at Scale

We introduce the SEAN Experimental Platform (SEAN-EP), an open-source sy...

Untangling Dense Knots by Learning Task-Relevant Keypoints

Untangling ropes, wires, and cables is a challenging task for robots due...