Multimodal Affect Recognition for Assistive Human-Robot Interactions
Bibliographic record
Abstract
Socially assistive robots can provide cognitive assistance with activities of daily living, and promote social interactions to those suffering from cognitive impairments and/or social disorders. They can be used as aids for a number of different populations including those living with dementia or autism spectrum disorder, and for stroke patients during post-stroke rehabilitation [1]. Our research focuses on developing socially assistive intelligent robots capable of partaking in natural human-robot interactions (HRI). In particular, we have been working on the emotional aspects of the interactions to provide engaging settings, which in turn lead to better acceptance by the intended users. Herein, we present a novel multimodal affect recognition system for the robot Luke, Fig. 1(a), to engage in emotional assistive interactions. Current multimodal affect recognition systems mainly focus on inputs from facial expressions and vocal intonation [2], [3]. Body language has also been used to determine human affect during social interactions, but has yet to be explored in the development of multimodal recognition systems. Body language has been strongly correlated to vocal intonation [4]. The combined modalities provide emotional information due to the temporal development underlying the neural interaction in audiovisual perception [5]. In this paper, we present a novel multimodal recognition system that uniquely combines inputs from both body language and vocal intonation in order to autonomously determine user affect during assistive HRI.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".