用推荐系统思路让机器人按人喜好行事，更懂人心。
StARS: Socially Appropriate Robot Actions via a Recommender System-Driven Approach
- 把用户当‘用户’、场景当‘物品’，用协同过滤预测动作是否合适
- 在两个数据集上显著提升与人工评分的一致性，效果稳定
- 无需重做模型就能适配不同人，适合个性化服务场景
人类-机器人交互中的社会恰当性并非普适：同一情境下不同人对相同机器人行为的判断可能不同。为捕捉这种个体差异，我们将社会恰当行为生成重新建模为推荐系统中的偏好建模问题，将标注者视为用户，场景视为物品，候选机器人动作的恰当性评分作为目标。提出StARS——一种模型无关的框架，结合协同过滤与可学习的场景表示，生成针对用户的动作恰当性评分。该框架可与多种场景编码器和主干网络集成，实现个性化而无需重设计底层模型。我们在MannersDB+和SocNav1两个社交感知机器人数据集上评估了StARS，并分析其在稀疏偏好反馈下的鲁棒性。跨数据集与主干网络，StARS均持续提升性能与人工评分的一致性，支持与用户规范一致的动作选择。代码已公开于https://github.com/Cambridge-AFAR/StARS.git。
原文摘要 · Abstract (English)
Social appropriateness in human-robot interaction (HRI) is not universal: different people can judge the same robot action differently in the same situation. To capture this inter-subject variability, we reformulate socially appropriate action generation as a preference modelling problem inspired by recommender systems, treating annotators as users, contexts/scenes as items, and appropriateness scores over a set of candidate robot actions as targets. We propose StARS, a novel model-agnostic framework that integrates collaborative filtering with learnable scene representations to generate user-specific appropriateness scores over candidate robot actions. StARS is model-agnostic: it can be integrated with various scene encoders and backbones, enabling personalisation without redesigning the underlying model. We evaluate StARS on two socially aware robotics datasets, MannersDB+ and SocNav1, and analyse robustness under sparse preference feedback. Across datasets and backbones, StARS consistently improves performance and agreement with annotators, supporting personalised action selection aligned with user norms. Our code is publicly available at https://github.com/Cambridge-AFAR/StARS.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。