REVIEW 9 cited by
Rapid Exploration for Open-World Navigation with Latent Goal Models
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
We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration. Trained on a large offline dataset of prior experience, the model acquires a representation of visual goals that is robust to task-irrelevant distractors. We demonstrate our method on a mobile ground robot in open-world exploration scenarios. Given an image of a goal that is up to 80 meters away, our method leverages its representation to explore and discover the goal in under 20 minutes, even amidst previously-unseen obstacles and weather conditions. Please check out the project website for videos of our experiments and information about the real-world dataset used at https://sites.google.com/view/recon-robot.
Forward citations
Cited by 9 Pith papers
-
Uncertainty-Aware World Model for Aerial Image-Goal Navigation
UA-NWM predicts an uncertainty subspace of plausible future aerial views and scores candidate trajectories by the goal's distance to that subspace, improving image-goal navigation in simulation and on a real drone.
-
RAE-NWM: Navigation World Model in Dense Visual Representation Space
Navigation world models trained in dense DINOv2 space with flow-matching CDiT-DH and time-gated action injection improve structural stability and planning over VAE baselines.
-
SplatSearch: Instance Image Goal Navigation for Mobile Robots using 3D Gaussian Splatting and Diffusion Models
SplatSearch combines sparse-view 3D Gaussian Splatting, multi-view diffusion inpainting, and semantic/visual frontier scoring to achieve viewpoint-invariant instance image-goal navigation in unknown environments.
-
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
A unified diffusion transformer that jointly denoises future frames, waypoints, and geometry tokens improves image-goal navigation accuracy and can omit image tokens at test time for 0.1s latency.
-
Mollified Value Learning
Mollified Value Learning regularizes offline goal-conditioned value estimates with a Feynman-Kac expectation version of the viscous HJB equation instead of a pointwise Eikonal constraint.
-
DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features
An in-air trained diffusion navigation policy, whose depth encoder is fine-tuned on underwater depth estimation, drives a BlueROV2 through cluttered water using only camera images.
-
From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
Pretraining a navigation foundation model on videos and then fine-tuning only a residual attention module with reinforcement learning improves success rate and collision avoidance compared to behavior cloning or super...
-
PixelNav: Towards Model-based Vision-Only Navigation with Topological Graphs
A camera-only navigation system combining visual place recognition, traversability segmentation, and model predictive control over a topological graph, evaluated on a real robot.
-
PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models
A pretrained image-goal navigation model combining early-fusion ViT, auxiliary objectives, and game-video data reports higher success than GNM, ViNT, and NoMaD, though zero-shot generalization is clouded by possible p...
Discussion (0). Continue with ORCID to comment.