Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt

Author

Tianrui Zhu

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Open access Aug 2026

An Integrated Product Service System Framework for On-Site Digital Human Guide Systems

On-site digital human guide systems, which integrate intelligent interactive technologies with guidance, interpretation, and information services, are emerging as an important form of intelligent on-site service. However, existing knowledge remains largely fragmented across technological configurations, interaction modalities, application contexts, and user experience objectives, lacking an integrated cross-dimensional analytical perspective that explains how these systems create and deliver value. To address this gap, this paper aims to adopt a Product–Service Systems (PSS) perspective to systematically examine the development of on-site digital human guide systems. Specifically, it explores their product–service configurations, service delivery modes and user participation, and artificial intelligence (AI) capability integration pathways, while identifying the value creation opportunities and challenges associated with system development and continuous optimization. The PSS paradigm offers such an integrative lens, which has gained renewed relevance as the Fourth Industrial Revolution (Industry 4.0) accelerates the servitization and digital transformation of traditional services. This paper conducts a scoping review employing content analysis based on a structured cross-database search across Google Scholar, Scopus, and Web of Science, supplemented by snowball sampling, covering 40 studies, including 34 deployed projects. The findings reveal that: (1) on-site digital human guide systems can be categorized into four product–service configurations: fixed terminal (stationary dialogue); mobile terminal (location-aware guidance); Head-Mounted Display/Mixed Reality (immersive experience); and robot (full-process mobile service). The selection of these configurations is shaped by spatial characteristics, target user group, and institutional operational conditions; (2) a user behavior taxonomy of nine active and five passive types was developed, demonstrating that user participation patterns are jointly shaped by control allocation in service delivery and the social behavior design of digital humans, with users showing a preference for controllable and interruptible engagement; (3) AI integration has evolved from rule-and-script-driven approaches to modular AI integration, and subsequently to large language model (LLM)/Retrieval-Augmented Generation (RAG)-driven architectures, with corresponding design implications proposed; and (4) challenges were classified into four major categories and 26 subcategories across three digital transformation stages. The contribution of this paper lies in the development of an integrated PSS analytical framework for on-site digital human guide systems, spanning product, service, and AI integration layers. The framework provides a multi-layer analytical lens for understanding system configurations, user participation, technological evolution, and implementation challenges, while offering structured guidance for configuration and service selection, system design, and continuous optimization across diverse deployment contexts. These findings provide practical implications for researchers and practitioners seeking to design, deploy, and optimize on-site digital human guide systems across diverse service environments.

Zhen Liu, Tianrui Zhu, Fenghong Wang et al. · 0 citations
Review Aug 2026

Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning

Physically grounded robot intelligence requires robots to perceive, reason about, and regulate their interactions with the physical world. This capability is particularly critical in contact-sensitive manipulation, where successful task execution depends not only on visual perception and motion generation, but also on force regulation and adaptive control. In this context, recent robot learning methods have made substantial progress by integrating force, tactile, vision, language, and proprioceptive sensing into learned manipulation policies. In parallel, many systems adopt multi-phase architectures that combine high-level policies, action-refinement modules, and low-level controllers to bridge semantic task understanding with reactive physical execution. Despite these advances, existing surveys have not explicitly reviewed force- and tactile-aware robot learning from a unified perspective that jointly captures multimodal sensing and multi-phase system design. This survey addresses this gap by proposing TF-ART, a Tactile/Force-Aware Robot learning Taxonomy for multimodal and multi-phase frameworks, which maps individual methods into a unified hierarchical structure. The framework characterizes how recent works organize observation modalities, encode and fuse heterogeneous sensory inputs, generate and refine actions across multiple phases, and connect learned policies to reactive robot-end control. Building on this methodological view, we further examine the task settings and infrastructure requirements of physical interaction, thereby integrating both algorithmic and practical perspectives on force- and tactile-aware robot learning.

Shilin Shan, Chuhao Zhou, Ruize Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.