Abstract
Language-guided object retrieval under partial observability requires deciding whether to gather more evidence, interact with the scene, grasp a candidate, or abstain. We present a closed-loop framework that coordinates these decisions for retrieving a target specified in relation to a reference container. The framework maintains a persistent joint belief over target identity, container relation, and presence through tracked-object, unobserved-target, and target-absent hypotheses. View-conditioned categorical VLM observations update this belief; conformal grasp eligibility and robot feasibility govern commitment, while finite-horizon belief-space planning selects information-gathering actions. Across five different scenarios, our proposed method succeeds in 19/25 simulation episodes versus 12/25 for the best-performing task-adapted baseline and is the only evaluated policy to achieve at least one success in each scenario. Ablations show that cross-view memory improves success under partial occlusion, while the full system does not consistently outperform simplified variants. Real-robot trials demonstrate closed-loop re-observation and autonomous recovery from injected grasp failures, while injected viewpoint failures end in false defer. Experimental results demonstrate the feasibility of coordinating evidence gathering and selective grasp commitment within a unified framework for retrieval under partial observability.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Koh, W., Dinesh, S. S., Ko, H., Park, S., & Lee, E. (2026). Selective Commitment for Language-Guided Object Retrieval under Partial Observability. https://omanscience.com/en/articles/selective-commitment-for-language-guided-object-retrieval-under-partial-observability
MLA 9
Koh, Wonhee, et al. "Selective Commitment for Language-Guided Object Retrieval under Partial Observability." https://omanscience.com/en/articles/selective-commitment-for-language-guided-object-retrieval-under-partial-observability.
Chicago (author–date)
Koh, Wonhee, Sushil Samuel Dinesh, Hansol Ko, Shinkyu Park, and Eungjoo Lee. 2026. "Selective Commitment for Language-Guided Object Retrieval under Partial Observability." https://omanscience.com/en/articles/selective-commitment-for-language-guided-object-retrieval-under-partial-observability.
Harvard
Koh, W., Dinesh, S. S., Ko, H., Park, S. and Lee, E. (2026) 'Selective Commitment for Language-Guided Object Retrieval under Partial Observability', Available at: https://omanscience.com/en/articles/selective-commitment-for-language-guided-object-retrieval-under-partial-observability.
Vancouver
Koh W, Dinesh SS, Ko H, Park S, Lee E. Selective Commitment for Language-Guided Object Retrieval under Partial Observability. https://omanscience.com/en/articles/selective-commitment-for-language-guided-object-retrieval-under-partial-observability
IEEE
W. Koh, S. S. Dinesh, H. Ko, S. Park, and E. Lee, "Selective Commitment for Language-Guided Object Retrieval under Partial Observability," https://omanscience.com/en/articles/selective-commitment-for-language-guided-object-retrieval-under-partial-observability.