Latent World Models with Monotone Planning Costs for Image-Goal Navigation
Latent World Models with Monotone Planning Costs for Image-Goal Navigation
This research presents a latent world model designed for image-goal navigation that utilizes a frozen DINO-family encoder. The authors propose two training objectives: an autoregressive rollout loss to align multi-step planning rollouts and a Monotone Cost Ranking (MCR) loss to ensure action sequences with higher perturbations receive higher planning costs, preventing misleading sampling-based planners like Cross-Entropy Method. By avoiding InfoNCE-based action-contrastive training which distorts latent geometry, the method achieves state-of-the-art performance on the GNM navigation dataset, reducing orientation error by 2.7 times compared to a DINO WM baseline with the same encoder. The model is also demonstrated in zero-shot deployment on a physical robot, successfully following goal-directed paths in both indoor and outdoor environments.
The paper introduces a latent world model architecture that combines an autoregressive rollout loss with a Monotone Cost Ranking (MCR) objective to improve planning cost ordering for image-goal navigation, achieving state-of-the-art results on the GNM dataset and zero-shot deployment on a physical robot in unseen environments.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Source：arXiv Robotics — research abstracts · arxiv.org