REVIEW 7 cited by
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
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
For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inference). We explore these capabilities in a unified setting: language-driven zero-shot object navigation (L-ZSON). Inspired by the recent success of open-vocabulary models for image classification, we investigate a straightforward framework, CLIP on Wheels (CoW), to adapt open-vocabulary models to this task without fine-tuning. To better evaluate L-ZSON, we introduce the Pasture benchmark, which considers finding uncommon objects, objects described by spatial and appearance attributes, and hidden objects described relative to visible objects. We conduct an in-depth empirical study by directly deploying 21 CoW baselines across Habitat, RoboTHOR, and Pasture. In total, we evaluate over 90k navigation episodes and find that (1) CoW baselines often struggle to leverage language descriptions, but are proficient at finding uncommon objects. (2) A simple CoW, with CLIP-based object localization and classical exploration -- and no additional training -- matches the navigation efficiency of a state-of-the-art ZSON method trained for 500M steps on Habitat MP3D data. This same CoW provides a 15.6 percentage point improvement in success over a state-of-the-art RoboTHOR ZSON model.
Forward citations
Cited by 7 Pith papers
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.
-
Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics
JITOMA keeps 3D scene graph nodes dormant until a natural-language query activates only task-relevant objects, bounding active graph size and captioning latency while preserving grounding accuracy.
-
CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
Counterfactual language-action relabeling raises instruction-following success from about 26% to 53% in real-world navigation tests.
-
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.
-
CogDDN: A Cognitive Demand-Driven Navigation with Decision Optimization and Dual-Process Thinking
CogDDN uses a fast heuristic VLM paired with a slow analytic reflection process and a growing knowledge base to navigate to objects that implicitly satisfy a user's demand, with large reported gains on AI2Thor DDN benchmarks.
-
OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots
OV-MAP projects 2D masks into 3D and uses mesh-area voting to create zero-shot, open-vocabulary 3D instance segmentation maps.
-
Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning
The thesis demonstrates that combining implicit 3D scene representations with LLM-based reasoning, using text as an interface, yields strong performance on robotic perception and spatial language tasks.
Discussion (0). Sign in to comment.