Harnessing human expertise for high-precision robotic assembly in industrialized construction: A sample-efficient installer-in-the-loop interactive reinforcement learning framework
Abstract
Industrialized construction imposes stringent precision requirements on robotic assembly of modular components such as prefabricated window units. In tolerance-critical operations, the central bottleneck is not only mechanical clearance but also converting tacit installer expertise into data-efficient autonomy under sparse acceptance feedback, contact variability, and millimeter-scale constraints. We present an installer-in-the-loop interactive reinforcement learning framework that acquires expertise through offline teleoperated demonstrations, sparse event-driven binary takeovers at contact-failure boundaries, and acceptance-aligned terminal rewards, logged under a unified schema for traceable offline-to-online adaptation. A temporally abstract action-sequence policy built on Q-chunking with Flow Q-Learning captures multimodal recovery maneuvers under sparse terminal rewards, while a non-updating warm-start phase stabilizes the offline-to-online transition. The framework is evaluated in MuJoCo across the workflow from suction acquisition through clearance-limited seating, under structured staging and end-to-end randomized placement. Within a defined stress-test regime with 2 mm per-side clearance, bounded pose perturbations, and friction randomization, the pipeline attains 100\% autonomous seating with 12--15 min of cumulative installer supervision over 3.0 h of online training, and reaches the 95\% success milestone in approximately 0.5 h and 1.5 h in the two experiments. We also report wall-clock adaptation time, cumulative takeover minutes, intervention-rate decay, and stage-wise failure attribution to inform supervision budgeting. Ablations isolate the complementary contributions of temporal abstraction, installer intervention, and warm-start value calibration.
Versions
Related
- Toward Maximizing Algebraic Connectivity via Density-Dependent Backbone Construction and Reinforcement Learning Completion
- Harnessing Mutual Coupling in Cell-Free mMIMO
- Harnessing LLMs with Direction-Scope Control for Combinatorial Solver Refinement
- Inference in an interactive multi-type branching network
- From Walks to Skeletons: A Reusable Transport Architecture for Interactive Monte Carlo PDE Solvers
BibTeX
@misc{jin2026harnessing,
title = {{Harnessing human expertise for high-precision robotic assembly in industrialized construction: A sample-efficient installer-in-the-loop interactive reinforcement learning framework}},
author = {Zekai Jin and Huiguang Wang and Xiaoning Sun and Yi Shao},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.13234},
eprint = {2609.13234},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.13234},
}
RIS
TY - UNPB
TI - Harnessing human expertise for high-precision robotic assembly in industrialized construction: A sample-efficient installer-in-the-loop interactive reinforcement learning framework
AU - Zekai Jin
AU - Huiguang Wang
AU - Xiaoning Sun
AU - Yi Shao
PY - 2026
DA - 2026/09/02
PB - arXiv
DO - 10.48550/arxiv.2609.13234
UR - https://arxiv.org/abs/2609.13234
AB - Industrialized construction imposes stringent precision requirements on robotic assembly of modular components such as prefabricated window units. In tolerance-critical operations, the central bottleneck is not only mechanical clearance but also converting tacit installer expertise into data-efficient autonomy under sparse acceptance feedback, contact variability, and millimeter-scale constraints. We present an installer-in-the-loop interactive reinforcement learning framework that acquires expertise through offline teleoperated demonstrations, sparse event-driven binary takeovers at contact-failure boundaries, and acceptance-aligned terminal rewards, logged under a unified schema for traceable offline-to-online adaptation. A temporally abstract action-sequence policy built on Q-chunking with Flow Q-Learning captures multimodal recovery maneuvers under sparse terminal rewards, while a non-updating warm-start phase stabilizes the offline-to-online transition. The framework is evaluated in MuJoCo across the workflow from suction acquisition through clearance-limited seating, under structured staging and end-to-end randomized placement. Within a defined stress-test regime with 2 mm per-side clearance, bounded pose perturbations, and friction randomization, the pipeline attains 100\% autonomous seating with 12--15 min of cumulative installer supervision over 3.0 h of online training, and reaches the 95\% success milestone in approximately 0.5 h and 1.5 h in the two experiments. We also report wall-clock adaptation time, cumulative takeover minutes, intervention-rate decay, and stage-wise failure attribution to inform supervision budgeting. Ablations isolate the complementary contributions of temporal abstraction, installer intervention, and warm-start value calibration.
ER -