Pith. sign in

REVIEW 5 cited by

Learning Generalizable Feature Fields for Mobile Manipulation

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 2403.07563 v2 pith:JKOV33SJ submitted 2024-03-12 cs.RO cs.CVcs.LG

classification cs.ROcs.CVcs.LG
keywords manipulationfeaturegeffgeneralizablenavigationcapturingfieldsmobile
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

An open problem in mobile manipulation is how to represent objects and scenes in a unified manner so that robots can use both for navigation and manipulation. The latter requires capturing intricate geometry while understanding fine-grained semantics, whereas the former involves capturing the complexity inherent at an expansive physical scale. In this work, we present GeFF (Generalizable Feature Fields), a scene-level generalizable neural feature field that acts as a unified representation for both navigation and manipulation that performs in real-time. To do so, we treat generative novel view synthesis as a pre-training task, and then align the resulting rich scene priors with natural language via CLIP feature distillation. We demonstrate the effectiveness of this approach by deploying GeFF on a quadrupedal robot equipped with a manipulator. We quantitatively evaluate GeFF's ability for open-vocabulary object-/part-level manipulation and show that GeFF outperforms point-based baselines in runtime and storage-accuracy trade-offs, with qualitative examples of semantics-aware navigation and articulated object manipulation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. QuASH: Using Natural-Language Heuristics to Query Visual-Language Robotic Maps

    cs.RO 2025-10 conditional novelty 6.0 of 10

    Querying VLM robot maps with an SVM trained on LLM-generated synonym/antonym embeddings outperforms cosine-threshold and single-antonym baselines on images and OpenSeg maps, but not consistently on LSeg maps.

  2. Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator

    cs.RO 2025-09 accept novelty 6.0 of 10

    A simulation-trained teacher-student policy with progressive policy expansion achieves 78.3% real-world success on a long-horizon mobile pick-and-place task.

  3. Representative Volume Element: Existence and Extent in Cracked Heterogeneous Medium

    cs.CE 2025-08 unverdicted novelty 5.0 of 10

    Modified periodic boundary conditions that add strain periodicity to displacement periodicity are claimed to reduce mesh and size sensitivity in cracked-composite RVE simulations, tested on 1,200 samples.

  4. MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation

    cs.RO 2025-09 conditional novelty 4.0 of 10

    MoTo turns existing fixed-base manipulation models into mobile manipulators by using VLM-picked contact keypoints and trajectory optimization to find docking points, with no training of MoTo itself.

  5. CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity

    cs.RO 2025-06

Pith tools