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

06/29/2022
by   Ryan Hoque, et al.
2

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 https://tinyurl.com/fleet-dagger for code, videos, and supplemental material.

READ FULL TEXT
03/31/2021

Learning Human Objectives from Sequences of Physical Corrections

When personal, assistive, and interactive robots make mistakes, humans n...
09/17/2021

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

Effective robot learning often requires online human feedback and interv...
07/04/2022

Robot Vitals and Robot Health: Towards Systematically Quantifying Runtime Performance Degradation in Robots Under Adverse Conditions

This paper addresses the problem of automatically detecting and quantify...
03/31/2021

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning

Corrective interventions while a robot is learning to automate a task pr...
04/21/2022

Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research

Autonomous fabric manipulation is a longstanding challenge in robotics, ...
12/22/2020

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...
11/10/2020

Untangling Dense Knots by Learning Task-Relevant Keypoints

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