DRL4CONBOTS logo DRL4CONBOTS Evidence Atlas

Automation in Construction manuscript companion

Evidence atlas for deep reinforcement learning in construction robotics.

A system-level view of task regimes, learning formulations, runtime authority, runtime assurance, and validation exposure across construction-robotics DRL studies.

Explore readiness matrix Repository
Author affiliations Multi-institutional research team
McGill University UC Santa Barbara NVIDIA New York University University of British Columbia

Institution names indicate author affiliations only, not institutional endorsement.

At a glance

What the companion repository makes visible.

Manuscript Under review in Automation in Construction
Evidence base 152 coded construction-robotics instances
Primary DRL synthesis 75 primary DRL instances across five competency regimes
Diagnostic message Readiness depends on authority, assurance, and exposure, not algorithm labels alone

A1-A5 framework

Five axes keep the review evidence-bound.

The atlas treats each reported system as a bounded claim. Switch axes to see what each dimension contributes to deployment-relevant interpretation.

Readiness diagnostic

Runtime assurance and validation exposure separate demonstration from deployment evidence.

Representative papers

Filter examples by construction-robotics regime.

Figure gallery

Core visuals from the evidence map.

Graphical overview of the evidence framework Graphical overview Evidence framework for deployment-relevant DRL PRISMA flow diagram Corpus and screening Report-level PRISMA flow Five competency regimes Competency regimes Task-specific evidence organization Evidence-closure map Evidence-closure map Deployment-relevant claim scope

Citation

Manuscript companion metadata.

The citation will be updated after preprint, acceptance, or archival release.

@misc{jin2026drl4conbots,
  title        = {Deep Reinforcement Learning for Construction Robotics: A System-Level Taxonomy and Evidence Map toward Real-World Readiness},
  author       = {Jin, Zekai and Wang, Huiguang and Tang, Yihong and Dong, Zhen and Feng, Chen and Shao, Yi},
  year         = {2026},
  howpublished = {Companion repository for a manuscript under review in Automation in Construction},
  url          = {https://github.com/ZekaiJ/DRL4CONBOTS}
}