Robots that follow natural-language instructions in everyday indoor environments must act on incomplete human utterances. Instructions often omit essential information, such as the identity of an out-of-view object, an intended destination, or the user's goal. Existing datasets contain little real-world situated dialogue and provide few practice-grounded criteria for deciding when a robot should act, confirm, clarify, or refuse. We retrospectively analyze a pilot Wizard-of-Oz study in which five participants performed everyday indoor tasks, including door opening, drawer opening, feeding, drinking, and cleaning, with a wheelchair-mounted mobile manipulator while the wizard responded without a formal communication policy. This preserved authentic user behavior but produced inconsistent robot-side decisions, motivating an explicit decision scheme. From 40 episodes, we derived a hierarchical taxonomy of six response modes (ANSWER, REPORT_DONE, REFUSE, CONFIRM, CLARIFY, ACT) and four ambiguity types (intent, referential, spatial, intelligibility). Two human annotators and an AI annotator applied the scheme to the pilot data. Clean-label rates were 91% and 89%, and Cohen's ranged from 0.72 to 0.95 across decision-point, mode, and ambiguity levels for both human-human and human-AI comparisons. Fine-tuning LLaVA-1.6-7B on taxonomy-derived labels for ACT and CLARIFY indicates the feasibility of training vision-language models using annotations from our taxonomy. Remaining boundary cases in decision-point identification and REPORT_DONE motivate a constrained protocol for more consistent dialogue collection.
Guang-Ping Liu, Nicholas Hawkins, Tipu Sultan et al.· 0 citations
Pediatric stroke has a broad etiological spectrum, with inborn errors of metabolism (IEM) increasingly recognized as an important and potentially treatable cause. This study aimed to characterize the clinical, radiological, and electroencephalographic features of IEM-related pediatric stroke and to evaluate short-term functional outcomes.
This prospective cohort study was conducted at The Children’s Hospital Lahore, Pakistan, and Sultan Qaboos University Hospital, Muscat, Oman (January 2024–December 2025). Children with confirmed stroke secondary to IEM were enrolled. Functional outcome was assessed at 3 months using the modified Rankin Scale (mRS), with scores 0–3 defined as favorable and 4–6 as unfavorable.
Forty-four patients were included (59.1% male), with a mean age of 4.6 ± 4.2 years. Focal neurological deficits and encephalopathy were the most frequent presentations. Mitochondrial disorders and homocystinuria were the leading etiologies. MRI demonstrated heterogeneous patterns, most commonly focal ischemic lesions and brainstem–striatal involvement. Management included mitochondrial cocktails, vitamin therapy, and targeted metabolic treatments. Poorer outcomes (mRS 4–6) were associated with generalized epileptiform discharges with diffuse slowing on EEG, whereas favorable outcomes correlated with focal epileptiform discharges or normal EEG findings (
p
= 0.00018). Outcomes also varied by etiology, with homocystinuria and mitochondrial complex I deficiency associated with better recovery and Leigh disease and glutaric aciduria with worse prognosis (
p
= 0.041).
IEM represent an important and potentially treatable cause of pediatric stroke, particularly in populations with high consanguinity. Recognition of characteristic clinical features, distinctive MRI patterns, and supportive EEG findings can facilitate early diagnosis. Prompt metabolic and genetic evaluation is essential to guide targeted therapy and improve outcomes.
J. Alvi, Areeba Wasim, Saher Gul Ahdi et al.· Frontiers in Neurology· 0 citations
The data establish BHLHE22 as a previously unrecognized neurodevelopmental disease gene that results in a distinct syndrome characterised by abnormalities in brain development, cognition, tone and movement.
Carolyn Le, T. Kalaycı, Z. Uyguner et al.· Journal of Medical Genetics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
