A5100755023- Robotic Locomotion and Control
- Prosthetics and Rehabilitation Robotics
- Topic Modeling
- Social Robot Interaction and HRI
- Muscle activation and electromyography studies
- Robotics and Automated Systems
- Sentiment Analysis and Opinion Mining
- Robot Manipulation and Learning
- Neurogenetic and Muscular Disorders Research
- Robotic Mechanisms and Dynamics
- Advanced Neural Network Applications
- Advanced MRI Techniques and Applications
- Multimodal Machine Learning Applications
- Balance, Gait, and Falls Prevention
- Robotics and Sensor-Based Localization
- Domain Adaptation and Few-Shot Learning
- Traumatic Brain Injury and Neurovascular Disturbances
- Mental Health via Writing
- Face recognition and analysis
- Anomaly Detection Techniques and Applications
- Advanced Sensor and Energy Harvesting Materials
- Air Quality Monitoring and Forecasting
- Stroke Rehabilitation and Recovery
- Advanced Image and Video Retrieval Techniques
- Cerebral Palsy and Movement Disorders
University of Waterloo
2022-2025
Midwestern University
2025
Ningbo University
2022-2024
Affiliated Hospital of Southwest Medical University
2024
Yale New Haven Health System
2024
Capital Medical University
2016-2024
Harbin Institute of Technology
2022-2024
City University of Hong Kong
2023-2024
Soochow University
2018-2024
Chongqing Municipal Government
2023-2024
Continuous monitoring of arterial blood pressure (BP) outside a clinical setting is crucial for preventing and diagnosing hypertension related diseases. However, current continuous BP instruments suffer from either bulky systems or poor user-device interfacial performance, hampering their applications in monitoring. Here, we report thin, soft, miniaturized system (TSMS) that combines conformal piezoelectric sensor array, an active adaptation unit, signal processing module, advanced machine...
In a world designed for legs, quadrupeds, bipeds, and humanoids have the opportunity to impact emerging robotics applications from logistics, agriculture, home assistance. The goal of this survey is cover recent progress toward these that been driven by model-based optimization real-time generation control movement. majority research community has converged on idea generating locomotion laws solving an optimal problem (OCP) in either or data-driven manner. However, most general problems...
Multi-agent collaborative perception could significantly upgrade the performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between and communication bandwidth. To tackle this bottleneck issue, we propose spatial confidence map, which reflects heterogeneity of perceptual information. empowers only spatially sparse, yet perceptually critical information, contributing where communicate. Based on...
Emotional support conversation aims at reducing the emotional distress of help-seeker, which is a new and challenging task. It requires system to explore cause help-seeker's understand their psychological intention provide supportive responses. However, existing methods mainly focus on sequential contextual information, ignoring hierarchical relationships with global local behind conversations, thus leads weak ability support. In this paper, we propose Global-to-Local Hierarchical Graph...
Importance Black patients are more likely than White to be restrained during behavioral crises in emergency departments (EDs). Although the perils of policing mental health for individuals recognized, it is unclear whether or what extent police transport mediates association between race and use physical restraint EDs. Objective To evaluate degree which Design, Setting, Participants This retrospective, cross-sectional study used electronic record data from ED visits by adults (aged ≥18...
Unanticipated physical actions from the robot on humans [active human–robot interaction (pHRI)] may be inevitable with deployment of robots in human-populated environments. However, it is still unclear how would perceive such and should execute them a physically psychologically safe manner. The objective this article to explore possibility quantifying humans' mental state during an active robot, by means laboratory experiment. We hypothesize that could cause measurable alterations users'...
Sit-to-stand (STS) transfer is a fundamental but challenging movement that plays vital role in older adults' daily activities. The decline muscular strength and coordination ability can result difficulties performing STS and, therefore, the need for mobility assistance by humans or assistive devices. Robotics rollators are being developed to provide active adults, including assistance. In this paper, we consider robotic walker SkyWalker, which moving handles upwards forward bring user...
Humans possess an extraordinary ability to understand and execute complex manipulation tasks by interpreting abstract instruction manuals. For robots, however, this capability remains a substantial challenge, as they cannot interpret instructions translate them into executable actions. In paper, we present Manual2Skill, novel framework that enables robots perform assembly guided high-level manual instructions. Our approach leverages Vision-Language Model (VLM) extract structured information...
Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings - spanning environment, action, and perception largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. support task, present CityEQA-EC, first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded realistic 3D...
Graph neural networks (GNNs) are popularly used to analyze non-Euclidean graph data. Despite their successes, the design of requires heavy manual work and rich domain knowledge. Recently, architecture search algorithms widely automatically architectures for CNNs RNNs. Inspired by success algorithms, we present a algorithm GraphNAS that enables automatic best based on reinforcement learning. Specifically, uses recurrent network as controller generate variable-length strings describe networks,...
Background Pinus massoniana is an important timber species with high ecological and economic value in southern China a pioneer for the reforestation of barren mountains. The structure function existing Masson pine ecosystem have been seriously affected by worsening habitats under current climate change. Its suitable habitat likely to change greatly near future. Methods To estimate potential geographic distribution P. its response change, Maxent model was selected simulate potentially...
In future robotic applications in environments such as nursing houses, construction sites, private homes, etc, robots might need to take unpredicted physical actions according the state of users overcome possible human errors. Referring these active human-robot interactions (active pHRI), this letter, goal is verify possibility identifying measurable interaction factors that could be used pHRI controllers, by exploring and analyzing during pHRI. We hypothesize robot can cause alterations...