计算机科学
操纵杆
障碍物
人机交互
轮椅
估计
概率逻辑
相关性(法律)
人工智能
避障
形势意识
组分(热力学)
机器学习
用户界面
人机交互
控制(管理)
凝视
移动机器人
透视图(图形)
姿势
噪音(视频)
机器人
计算机视觉
任务分析
接口(物质)
增强现实
隐马尔可夫模型
传感器融合
机器人学
流离失所(心理学)
用户建模
运动规划
自治
数据建模
还原(数学)
任务(项目管理)
作者
Fernando E. Casado,Rodrigo Chacón Quesada,Yiannis Demiris
标识
DOI:10.1109/tro.2025.3637101
摘要
User intention estimation is essential in shared control systems for powered wheelchairs. It enables seamless navigation assistance that enhances safety, efficiency, and usability, while preserving user autonomy and reducing effort. This paper presents Diffusion-based Wheelchair User Intention Estimation (DIWIE), a novel multimodal learning framework that leverages a Denoising Diffusion Probabilistic Model (DDPM) to forecast multiple plausible future trajectories, addressing uncertainty in human behaviour. DIWIE conditions on diverse inputs, including obstacle information, user attention cues from eye gaze and head pose, semantic context, wheelchair kinematics, and joystick commands, operating without predefined maps or target destinations. Evaluated on a large new dataset of natural navigation by multiple drivers, DIWIE outperforms state-of-the-art methods, achieving lower displacement errors and collision rates, making it a valuable component for integration into shared control systems. This work also analyses the relevance of different data sources for intention estimation and aligns evaluation metrics with related fields to foster reproducibility.
科研通智能强力驱动
Strongly Powered by AbleSci AI