Event
Multimodal Framework Aligns Human Language Goals as Robot Drives
1 reports · 1 sources
Diana Cerdas-Vargas, Alejandro Romero, and Richard J. Duro published a paper proposing a multimodal framework that uses large language models and vision-language models to translate human purposes expressed in natural language into robot tasks and drives, aligning the behavior of autonomous robots engaged in open-ended learning with human intent. The system has three layers: semantic alignment, task generation, and drive modeling, forming a bidirectional closed loop in which human input defines high-level purposes, the robot expands them into executable tasks, and feedback maintains alignment. The authors state that simulation and physical robot experiments show the pipeline can generate effective tasks and behaviors, supporting human-robot alignment in interactive scenarios.
Report timeline
- From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Intent
The study proposes a multimodal framework that uses large language models and vision-language models to translate human purposes expressed in natural language into robot missions and drives, aligning the behavior of open-ended learning autonomous robots with human intent. The system has three layers—semantic alignment, mission generation, and drive modeling—forming a bidirectional interaction loop in which human input defines high-level purposes, the robot expands them into executable missions, and feedback maintains alignment. Simulation and physical robot experiments show that the pipeline can generate effective missions and behaviors.
arXiv cs.RO ·