REVIEW 6 cited by
How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers
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
How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers
read the original abstract
Object goal navigation is an important problem in Embodied AI that involves guiding the agent to navigate to an instance of the object category in an unknown environment -- typically an indoor scene. Unfortunately, current state-of-the-art methods for this problem rely heavily on data-driven approaches, \eg, end-to-end reinforcement learning, imitation learning, and others. Moreover, such methods are typically costly to train and difficult to debug, leading to a lack of transferability and explainability. Inspired by recent successes in combining classical and learning methods, we present a modular and training-free solution, which embraces more classic approaches, to tackle the object goal navigation problem. Our method builds a structured scene representation based on the classic visual simultaneous localization and mapping (V-SLAM) framework. We then inject semantics into geometric-based frontier exploration to reason about promising areas to search for a goal object. Our structured scene representation comprises a 2D occupancy map, semantic point cloud, and spatial scene graph. Our method propagates semantics on the scene graphs based on language priors and scene statistics to introduce semantic knowledge to the geometric frontiers. With injected semantic priors, the agent can reason about the most promising frontier to explore. The proposed pipeline shows strong experimental performance for object goal navigation on the Gibson benchmark dataset, outperforming the previous state-of-the-art. We also perform comprehensive ablation studies to identify the current bottleneck in the object navigation task.
Forward citations
Cited by 6 Pith papers
-
ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation
ReMemNav improves zero-shot object navigation success and efficiency by integrating episodic memory and rethinking with VLMs, achieving SR/SPL gains of 1.7%/7.0% on HM3D v0.1, 18.2%/11.1% on HM3D v0.2, and 8.7%/7.9% on MP3D.
-
VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs
VL-LN Bench turns instance-goal navigation into an interactive dialog task, contributes a 41k-trajectory house-scale benchmark with a GPT-4o oracle, and shows active questioning improves embodied agents' success.
-
Beyond Frontiers: Scene-Anomaly Guided Autonomous Exploration
Modeling exploration as geometric anomaly minimization improves both volumetric coverage and 3D reconstruction quality over frontier and next-best-view baselines in simulated indoor scenes.
-
HRO: Hierarchical Room-to-Object Framework for Zero-Shot Object Goal Navigation with Large Language Models
Hierarchical LLM room-type inference plus object-room affinity scoring yields 84.0% Gibson and 53.0% HM3D success for zero-shot object-goal navigation.
-
N2M: Bridging Navigation and Manipulation by Learning Pose Preference from Rollout
N2M predicts preferable base poses for manipulation policies from ego-centric point clouds, learned from rollouts, lifting success from 3% to 54% in the PnPCounterToCab task.
-
Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning
A curriculum-trained DRL agent with a VLM query action and layered rewards is claimed to improve semantic exploration and object discovery in AI2-THOR.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.