The reviewed record of science sign in
Pith

arxiv: 2410.23968 · v1 · pith:ETLHFF36 · submitted 2024-10-31 · cs.RO

EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning

Reviewed by Pithpith:ETLHFF36open to challenge →

classification cs.RO
keywords embodiedragplanningrobotsceneenvironmentllm-basedadaptchanges
0
0 comments X
read the original abstract

Recent advances in Large Language Models (LLMs) have helped facilitate exciting progress for robotic planning in real, open-world environments. 3D scene graphs (3DSGs) offer a promising environment representation for grounding such LLM-based planners as they are compact and semantically rich. However, as the robot's environment scales (e.g., number of entities tracked) and the complexity of scene graph information increases (e.g., maintaining more attributes), providing the 3DSG as-is to an LLM-based planner quickly becomes infeasible due to input token count limits and attentional biases present in LLMs. Inspired by the successes of Retrieval-Augmented Generation (RAG) methods that retrieve query-relevant document chunks for LLM question and answering, we adapt the paradigm for our embodied domain. Specifically, we propose a 3D scene subgraph retrieval framework, called EmbodiedRAG, that we augment an LLM-based planner with for executing natural language robotic tasks. Notably, our retrieved subgraphs adapt to changes in the environment as well as changes in task-relevancy as the robot executes its plan. We demonstrate EmbodiedRAG's ability to significantly reduce input token counts (by an order of magnitude) and planning time (up to 70% reduction in average time per planning step) while improving success rates on AI2Thor simulated household tasks with a single-arm, mobile manipulator. Additionally, we implement EmbodiedRAG on a quadruped with a manipulator to highlight the performance benefits for robot deployment at the edge in real environments.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

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

  1. eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents

    cs.RO 2026-06 unverdicted novelty 7.0

    eMEM is a multi-index memory architecture with tiered consolidation and ten recall tools for embodied agents, scoring 80.8 weighted mean on eMEM-Bench covering eight cognitive psychology paradigms and outperforming a ...

  2. LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation

    cs.CV 2026-04 unverdicted novelty 7.0

    LookasideVLN improves aerial vision-and-language navigation by encoding directional cues from instructions into an egocentric graph and lightweight knowledge base, outperforming prior methods like CityNavAgent even wi...

  3. DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors

    cs.CV 2026-07 unverdicted novelty 5.0

    DeWorldSG improves 3D scene graph generation from RGB-D sequences by using depth-guided 3D Gaussian object nodes and V-JEPA 2 world-model priors for spatiotemporal relation refinement, reporting large recall gains on ...

  4. ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration

    cs.CV 2026-06 unverdicted novelty 5.0

    ObsGraph is a hierarchical observation-centric scene graph that unifies representation, retrieval, and multi-scale exploration for embodied reasoning.

  5. TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning

    cs.AI 2026-05 unverdicted novelty 5.0

    TaskGround introduces a Ground-Infer-Execute framework for full-scene household reasoning that improves success rates on the FullHome benchmark and enables compact models to match larger ones at up to 18x lower token cost.

  6. TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation

    cs.CV 2026-05 unverdicted novelty 5.0

    TrajRAG uses a topological-polar trajectory representation and hierarchical retrieval to accumulate and reuse geometric-semantic navigation experiences, improving zero-shot ObjectNav on MP3D and HM3D benchmarks.

  7. RoboAgent: Chaining Basic Capabilities for Embodied Task Planning

    cs.RO 2026-04 unverdicted novelty 5.0

    RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.

  8. Agentic Reasoning for Large Language Models

    cs.AI 2026-01 unverdicted novelty 4.0

    The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applicat...