MCNav builds a dynamic cognitive map with goal re-validation and missed-goal re-exploration to reach state-of-the-art results on instance-level zero-shot navigation in HM3D environments.
hub
Goat: Go to any thing
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
baseline 2
background 1
citation-polarity summary
representative citing papers
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
Proposes online hierarchical 3D scene graph construction paired with belief-based planning to improve zero-shot semantic navigation performance in unseen environments.
SurveilNav integrates robot local perception with multi-view surveillance for improved collaborative object goal navigation and reports SOTA results on HM3D.
A VLM-based method for selecting exploration frontiers in robotics achieves up to 24% better map coverage than standard geometric heuristics in simulated indoor environments.
SAGE trains agents in physics-grounded semantic abstractions via RL with asymmetric clipping, achieving 53.21% LLM-Match Success on A-EQA (+9.7% over baseline) and encouraging physical robot transfer.
ProCompNav builds a candidate pool from ambiguous queries then uses pool-splitting binary questions for disambiguation, improving success rate and shortening responses on CoIN-Bench and TextNav.
VLMs generalize affordance inference to non-humanoid robots but produce inconsistent results with a conservative bias of low false positives and high false negatives, especially for novel object manipulations.
FSUNav's dual brain-inspired modules achieve state-of-the-art zero-shot goal navigation across heterogeneous robots with improved speed, safety, and generalization.
A map-free localization method stores posed RGB-D keyframes, retrieves and re-ranks them with a VLM, then fuses sparse depth for on-demand 3D target estimates, matching reconstruction-based performance on navigation benchmarks with far lower build cost.
FeudalNav decomposes visual navigation into hierarchical levels with a visual-similarity latent memory, delivering competitive Habitat AI results without any odometry.
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
A two-stage DRL method with a supervised collision prediction stage improves collision-free success rates on object-goal visual navigation tasks in simulation and real rooms.
Introduces a hierarchical VLN architecture with asynchronous layers, incremental memory graph, and WTRP-based exploration that improves success and efficiency on resource-constrained robots.
citing papers explorer
-
MCNav: Memory-Aware Dynamic Cognitive Map for Zero-shot Goal-oriented Navigation
MCNav builds a dynamic cognitive map with goal re-validation and missed-goal re-exploration to reach state-of-the-art results on instance-level zero-shot navigation in HM3D environments.
-
Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
-
Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation
Proposes online hierarchical 3D scene graph construction paired with belief-based planning to improve zero-shot semantic navigation performance in unseen environments.
-
SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System
SurveilNav integrates robot local perception with multi-view surveillance for improved collaborative object goal navigation and reports SOTA results on HM3D.
-
Autonomous Frontier-Based Exploration with VLM Guidance
A VLM-based method for selecting exploration frontiers in robotics achieves up to 24% better map coverage than standard geometric heuristics in simulated indoor environments.
-
Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation
SAGE trains agents in physics-grounded semantic abstractions via RL with asymmetric clipping, achieving 53.21% LLM-Match Success on A-EQA (+9.7% over baseline) and encouraging physical robot transfer.
-
ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
ProCompNav builds a candidate pool from ambiguous queries then uses pool-splitting binary questions for disambiguation, improving success rate and shortening responses on CoIN-Bench and TextNav.
-
Assessing VLM-Driven Semantic-Affordance Inference for Non-Humanoid Robot Morphologies
VLMs generalize affordance inference to non-humanoid robots but produce inconsistent results with a conservative bias of low false positives and high false negatives, especially for novel object manipulations.
-
FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation
FSUNav's dual brain-inspired modules achieve state-of-the-art zero-shot goal navigation across heterogeneous robots with improved speed, safety, and generalization.
-
Memory Over Maps: 3D Object Localization Without Reconstruction
A map-free localization method stores posed RGB-D keyframes, retrieves and re-ranks them with a VLM, then fuses sparse depth for on-demand 3D target estimates, matching reconstruction-based performance on navigation benchmarks with far lower build cost.
-
FeudalNav: A Simple Framework for Visual Navigation
FeudalNav decomposes visual navigation into hierarchical levels with a visual-similarity latent memory, delivering competitive Habitat AI results without any odometry.
-
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
-
Collision-Aware Object-Goal Visual Navigation via Two-Stage Deep Reinforcement Learning
A two-stage DRL method with a supervised collision prediction stage improves collision-free success rates on object-goal visual navigation tasks in simulation and real rooms.
-
A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration
Introduces a hierarchical VLN architecture with asynchronous layers, incremental memory graph, and WTRP-based exploration that improves success and efficiency on resource-constrained robots.
- DM$^3$-Nav: Decentralized Multi-Agent Multimodal Multi-Object Semantic Navigation