Aug 2026· International Conference on Biomedical Robotics and Biomechatronics· pp. 1137-1144· 0 citations· 23 references
Abstract
Traditional control interfaces for powered assistive devices are often inaccessible to individuals with severe mobility impairments. Embodied AI, which integrates perception, reasoning, and action within robotic systems, offers a promising approach to improve accessibility and autonomy. This work presents Speak2Move, an embodied AI framework that enables intuitive voice-based control of assistive mobility devices. By integrating a large language model with object detection, semantic segmentation, SLAM, and autonomous navigation, Speak2Move creates a closed-loop pipeline connecting perception, reasoning, and action. The system incorporates a novel semantic mapping method and is deployed on a physical robot equipped with an RGB-D camera. Performance is evaluated through nine real-world navigation trials assessing spatial reasoning, obstacle avoidance, semantic understanding, and high-level task planning. A user study with five participants showed that Speak2Move consistently reduced cognitive workload during navigation, highlighting the potential of embodied AI to enhance accessibility, independence, and user experience in assistive mobility.
As robots are increasingly deployed in human-centric environments like homes and hospitals, their ability to navigate safely while respecting social norms is essential. Vision-and-Language Navigation (VLN) offers a promising interface by allowing robots to follow natural language instructions. However, current VLN rese...
Experimental results in various task scenarios show that the proposed framework consistently improves overall task success rates compared with unimodal settings with different LLMs and achieves a higher success rate compared to using only visual or force data.
This work proposes MobileVLA-R1 2.0, an RL-enhanced VLA framework that explicitly couples structured embodied reasoning with executable mobile robot control, and introduces a reasoning-conditioned action decoder that maps multimodal reasoning representations to task-level action targets, which are subsequently translat...
Ting Huang, Yue Huang, Ze-Yu Zhang et al.· 1 citation
Large Language Models (LLMs) have emerged as powerful tools for enabling intuitive human-robot interaction through natural language. However, existing approaches often lack evaluated voice control in languages other than English, integrated vision, and comprehensive safety mechanisms. We present SMaRTAban (Smart Mult...
Eduard Zelenay, Maroš Kocúr, Martin Lukáč et al.· International Journal of Int...· 0 citations
Embodied AI aims to develop agents capable of perceiving, acting, and collaborating with humans in dynamic environments. However, existing Vision-Language Model (VLM)-based approaches to Human-Robot Interaction (HRI) often assume accurate shared understanding and depend on task-specific finetuning, limiting robustness...
Tien Pham, Xin-Yun Chi, A. Cangelosi· IEEE International Symposium...· 0 citations
LightNav-0 is presented, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads, and establishes compact VLMs as a unified and transferable backbone for generalist embodied navigation.
Shao-An Wang, Ao-Cheng Luo, Fei Huang et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
