ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation

2026-04-28

AI Summary

This work addresses the frequent execution failures of domestic service robots in open-vocabulary, long-horizon tasks caused by the disconnect between symbolic planning and the physical world—manifested in outdated semantic maps, unreachable navigation goals, and coarse-grained exception handling. To bridge this gap, the authors propose a physically aware closed-loop task execution framework that tightly couples symbolic reasoning with geometric and kinematic feasibility through physically anchored task planning, affordance-aware base alignment, and a hierarchical minimal-responsibility recovery mechanism. This design enables localized error isolation and efficient recovery. Evaluated across 60 real-world trials in previously unseen environments, the approach improves task success rate from 53.3% to 71.7% and achieves a 71.4% recovery rate under perturbations, substantially enhancing system robustness and deployment reliability.

Abstract

Recent advances in open-vocabulary mobile manipulation have brought robots into real domestic environments. In such settings, reliable long-horizon execution under open-set object references and frequent disturbances becomes essential. However, many failures persist. These are not caused by semantic misunderstanding but by inconsistencies between symbolic plans and the evolving physical world, manifested as three recurring limitations: (i) existing systems often rely on pre-scanned semantic maps that become inconsistent after scene changes and disturbances; (ii) they select navigation endpoints without considering downstream manipulation feasibility, causing the "arrived but inoperable" problem; and (iii) they handle anomalies through undifferentiated global replanning, which often fails to contain local errors. To address this execution inconsistency, we present ANCHOR, a physically grounded closed-loop framework that aligns symbolic reasoning with verifiable physical state during execution. ANCHOR integrates three mechanisms: (i) physically anchored task planning, which binds symbolic predicates to observable geometric anchors and re-validates them after each action; (ii) operability-aware base alignment, which ensures that navigation endpoints satisfy kinematic reachability and local collision feasibility; and (iii) minimum-responsible-layer hierarchical recovery, which localizes failures across perception, base-arm coordination, and execution layers to prevent cascading retries. Across 60 real-robot trials in previously unseen environments, ANCHOR improves task success from 53.3% to 71.7% and achieves a 71.4% recovery rate under perturbations, demonstrating that explicit physical grounding and structured failure containment are critical for robust mobile manipulation. Our project page is available at https://anchor9178.github.io/ANCHOR/ .

Problem

• mobile manipulation
• symbolic-physical inconsistency
• domestic environments
• task execution robustness
• disturbance recovery

Innovation

• physically grounded planning
• operability-aware navigation
• hierarchical recovery
• mobile manipulation
• closed-loop execution