REVIEW 6 cited by
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with 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
read the original abstract
To fully leverage the capabilities of mobile manipulation robots, it is imperative that they are able to autonomously execute long-horizon tasks in large unexplored environments. While large language models (LLMs) have shown emergent reasoning skills on arbitrary tasks, existing work primarily concentrates on explored environments, typically focusing on either navigation or manipulation tasks in isolation. In this work, we propose MoMa-LLM, a novel approach that grounds language models within structured representations derived from open-vocabulary scene graphs, dynamically updated as the environment is explored. We tightly interleave these representations with an object-centric action space. Given object detections, the resulting approach is zero-shot, open-vocabulary, and readily extendable to a spectrum of mobile manipulation and household robotic tasks. We demonstrate the effectiveness of MoMa-LLM in a novel semantic interactive search task in large realistic indoor environments. In extensive experiments in both simulation and the real world, we show substantially improved search efficiency compared to conventional baselines and state-of-the-art approaches, as well as its applicability to more abstract tasks. We make the code publicly available at http://moma-llm.cs.uni-freiburg.de.
Forward citations
Cited by 6 Pith papers
-
ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation
ANCHOR raises mobile manipulation success from 53.3% to 71.7% in unseen homes by binding plans to observable geometry, ensuring operable navigation endpoints, and using layered local recovery instead of global replans.
-
CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation
CAGE-SGG improves open-vocabulary scene graph generation by verifying candidate relations through counterfactual removal of specific visual evidence rather than relying on language priors.
-
CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation
CAGE-SGG uses counterfactual relation verification and evidence decomposition to produce more reliable open-vocabulary scene graphs than direct generation from vision-language models.
-
CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation
A counterfactual verification framework for open-vocabulary scene graph generation that decomposes predicates into evidence types and tests whether relation predictions are sensitive to removal of necessary visual evidence.
-
Open Scene Graphs for Open-World Object-Goal Navigation
OSG Navigator adds auto-generated scene-graph schemas as spatial memory to foundation models, reporting SOTA ObjectNav performance with zero-shot generalization across environments, goals, and robots.
-
An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees
NRTrans uses a small Robot Skill Language with a compiler and iterative error feedback to improve the success rate of LLM-generated robot control programs.
Discussion (0). Sign in to comment.