Embodied Referring Expression Comprehension in Human-Robot Interaction
Islam, Md Mofijul, Gladstone, Alexi, Sarker, Sujan, Nanduru, Ganesh, Fahim, Md, Du, Keyan, Chadha, Aman, Iqbal, Tariq
–arXiv.org Artificial Intelligence
As robots enter human workspaces, there is a crucial need for them to comprehend embodied human instructions, enabling intuitive and fluent human-robot interaction (HRI). However, accurate comprehension is challenging due to a lack of large-scale datasets that capture natural embodied interactions in diverse HRI settings. Existing datasets suffer from perspective bias, single-view collection, inadequate coverage of nonverbal gestures, and a predominant focus on indoor environments. To address these issues, we present the Refer360 dataset, a large-scale dataset of embodied verbal and nonverbal interactions collected across diverse viewpoints in both indoor and outdoor settings. Additionally, we introduce MuRes, a multimodal guided residual module designed to improve embodied referring expression comprehension. MuRes acts as an information bottleneck, extracting salient modality-specific signals and reinforcing them into pre-trained representations to form complementary features for downstream tasks. We conduct extensive experiments on four HRI datasets, including the Refer360 dataset, and demonstrate that current multimodal models fail to capture embodied interactions comprehensively; however, augmenting them with MuRes consistently improves performance. These findings establish Refer360 as a valuable benchmark and exhibit the potential of guided residual learning to advance embodied referring expression comprehension in robots operating within human environments.
arXiv.org Artificial Intelligence
Dec-9-2025
- Country:
- Asia > Bangladesh
- Dhaka Division > Dhaka District > Dhaka (0.04)
- Europe
- Netherlands > North Holland
- Amsterdam (0.04)
- United Kingdom
- England > Cambridgeshire
- Cambridge (0.04)
- Scotland > City of Edinburgh
- Edinburgh (0.05)
- England > Cambridgeshire
- Netherlands > North Holland
- North America > United States
- Illinois > Cook County
- Chicago (0.04)
- New York > New York County
- New York City (0.04)
- Virginia (0.04)
- Illinois > Cook County
- Asia > Bangladesh
- Genre:
- Research Report > New Finding (0.93)
- Industry:
- Leisure & Entertainment (0.46)
- Materials (0.46)
- Technology: