SOR-Nav improves robot object search by deciding when to explore or move
SOR-Nav: Search or Relocate? Context-Gated Exploration and Cross-Region Relocation for Object Navigation
Robotics
Summary
Finding objects in new places is hard because robots can't see everything and have limited movement. The authors created SOR-Nav, a robot system that decides whether to keep searching nearby or move to a new area that looks more promising. It builds a map of objects and possible places to explore, then uses smart decision-making to choose where to go next. Tests show it finds objects more successfully and efficiently than before, even in real-world settings.
What this means in practice
- •For robotics engineers: Enable robots to efficiently find objects in unfamiliar indoor environments by deciding when to explore nearby or move to better search areas.
- •For warehouse automation teams: Improve autonomous robots’ ability to locate items in complex warehouse layouts by structuring search with persistent object maps and strategic moves.
Authors
Yuan Ji, Zirui Li, Yuxin Cai, Shuge Wu, Boon Siew Han, Chen Lv
Abstract
Object navigation requires an embodied agent to find an object in an unseen environment under partial observability and a limited motion budget. Existing methods primarily optimize where the robot should go next by ranking candidate destinations. In contrast to these methods, we present SOR-Nav, a hierarchical navigation system that explicitly arbitrates between continuing to explore the current context and abandoning it for a more promising reachable region. First, an autonomous semantic exploration system is built that accumulates persistent 3D object clusters and organizes reachable frontiers into a cluster decision graph to provide an efficient search abstraction. Then, SOR-Nav uses a context-gated LLM-driven object-search supervisor to evaluate the suitability of the current search context and decide whether to continue exploration or perform cross-region relocation to another reachable frontier cluster. Across the complete, unfiltered validation sets of HM3D-v1, HM3D-v2, and MP3D, SOR-Nav achieves the strongest reported Success Rate (SR) and Success weighted by Path Length (SPL) on all three benchmarks. On MP3D in particular, it more than doubles the previous best SPL from 18.1\% to 38.5\% while increasing SR from 50.7\% to 61.8\%. Nested HM3D-v2 ablations validate the proposed decision structure, while a continuous three-target physical deployment demonstrates persistent ObjectNav operation in real-world scenarios.