This paper presents an ADL recommendation system based on a Vision Language Model (VLM), which runs locally, describes the objects in the scene, and recommends different ADLs based on the objects in the scene and the capabilities of the robotic system.
Abstract
Assistive robotics has established itself as a vital solution for supporting users with motor impairments in performing Activities of Daily Living (ADLs). In this context, the use of bimanual upper-limb exoskeletons presents a promising option for helping people with motor impairments perform ADLs. However, using these devices can be complex for the user, so intuitive interaction methods must be designed to facilitate easy use. This paper presents an ADL recommendation system based on a Vision Language Model (VLM). The model runs locally, describes the objects in the scene, and recommends different ADLs based on the objects in the scene and the capabilities of the robotic system.
Stroke represents one of the leading causes of chronic physical disability, leaving a large proportion of survivors with severe motor deficits in the upper limbs that limit their autonomy. Driven by the need to restore this functional independence, this study proposes the development and preliminary validation of a bim...
Esther Peral-Semepre, Yolanda Vales, Pablo Rubira Úbeda et al.· Jornadas de Automática· 0 citations
The development of myoelectric robotic prostheses has improved the autonomy of people with limb loss, although their high cost and the complexity of muscle control lead to high abandonment rates. In order to solve this problem, a virtual reality training system has been created for users with transradial amputation, al...
Pablo Orgiler, Cristina Romero, Raquel Martínez Pérez et al.· Jornadas de Automática· 0 citations
Neurological disorders, such as stroke, multiple sclerosis, or severe neuropathies, drastically impact patient autonomy and quality of life. Although rehabilitation technologies have demonstrated great potential, their application remains limited in patients with severe impairments, particularly those presenting high l...
Fco. Javier Miñano, D. Díaz-Díaz, Javier Chinchilla-Pastor et al.· Jornadas de Automática· 0 citations
This work presents a haptic control strategy for a cable-driven parallel robot designed to assist lower-limb rehabilitation. The proposed approach uses a harness as an input interface, estimating locomotor intention from the forces measured by four load cells attached to the corresponding suspension straps, together wi...
Enrique Riveiro Fernández, D. Silva-Muñiz, Uxía Pérez García et al.· Jornadas de Automática· 0 citations
Injuries to the central nervous system, such as strokes, have a significant impact on people’s independence, as they cause motor disorders such as spasticity, thereby limiting and affecting the quality of life of those affected. In recent years, work has been carried out on the NOHA project, investigating a new paradig...
Javier Chinchilla-Pastor, M. Herraiz-Sala, Fco. Javier Miñano et al.· Jornadas de Automática· 0 citations
Large Language Models (LLMs) offer new possibilities for simplifying interaction with robotic rehabilitation platforms, whose low-level parameterisation represents a recognised barrier to clinical usability. This work proposes an architecture for the semantic control of the Discover2Walk platform, a cable-driven roboti...
Pablo Romero-Sorozábal, Iñaki Dellibarda Varela, R. Sendra-Arranz et al.· Jornadas de Automática· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
