Pith. sign in

REVIEW 6 cited by

ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.13166 v3 pith:NCM4QMXL submitted 2023-01-30 cs.AI cs.CVcs.LGcs.RO

classification cs.AIcs.CVcs.LGcs.RO
keywords navigationobjectcommonsenseenvironmentsexplorationobjectspre-trainedsoft
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The ability to accurately locate and navigate to a specific object is a crucial capability for embodied agents that operate in the real world and interact with objects to complete tasks. Such object navigation tasks usually require large-scale training in visual environments with labeled objects, which generalizes poorly to novel objects in unknown environments. In this work, we present a novel zero-shot object navigation method, Exploration with Soft Commonsense constraints (ESC), that transfers commonsense knowledge in pre-trained models to open-world object navigation without any navigation experience nor any other training on the visual environments. First, ESC leverages a pre-trained vision and language model for open-world prompt-based grounding and a pre-trained commonsense language model for room and object reasoning. Then ESC converts commonsense knowledge into navigation actions by modeling it as soft logic predicates for efficient exploration. Extensive experiments on MP3D, HM3D, and RoboTHOR benchmarks show that our ESC method improves significantly over baselines, and achieves new state-of-the-art results for zero-shot object navigation (e.g., 288% relative Success Rate improvement than CoW on MP3D).

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. VTM-Nav: Harnessing Cross-Episode Experience for Object-Goal Navigation with Hierarchical Visual-Topological Memory

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A hierarchical room-and-object memory that persists across independent ObjectNav episodes yields small success-rate gains, but most of the gain comes from within-episode memory rather than the cross-episode component.

  2. FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning

    cs.RO 2025-09 unverdicted novelty 6.0 of 10

    FiLM-Nav fine-tunes VLMs on a mixture of simulated navigation tasks to reach state-of-the-art SPL and success on HM3D ObjectNav and OVON benchmarks with generalization to unseen categories.

  3. OpenGuide: Assistive Object Retrieval in Indoor Spaces for Individuals with Visual Impairments

    cs.RO 2025-09 conditional novelty 6.0 of 10

    OpenGuide combines vision-language value maps, frontier exploration, and POMDP planning to locate multiple objects in unfamiliar indoor spaces, reaching about 55% success in simulation and 54% in real-world trials.

  4. NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

    cs.CV 2024-02 unverdicted novelty 6.0 of 10

    NaVid, a video-based VLM trained on 510k navigation and 763k web samples, achieves SOTA VLN performance using only monocular RGB video for next-step action planning in sim and real environments.

  5. IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations

    cs.RO 2026-06 unverdicted novelty 5.0 of 10

    IntentNav is a spatial-visual imitation framework that infers human search intent via frontier labeling to train VLM policies for object navigation, reporting SOTA on MP3D and HM3D benchmarks with zero-shot transfer t...

  6. Imaging the disk-halo interface of NGC 891: a 2.7 kpc-thick molecular gas disk

    astro-ph.GA 2026-03 unverdicted novelty 5.0 of 10

    NGC 891’s molecular gas has a thin (~360 pc) plus thick (~1.1 kpc FWHM) disk, with CO detected to 1.3–1.4 kpc and up to ~27% of H2 mass in the thick component.

Pith tools