首页|Stanford University Researcher Details New Studies and Findings in the Area of R obotics (Foundation models in robotics: Applications, challenges, and the future )
Stanford University Researcher Details New Studies and Findings in the Area of R obotics (Foundation models in robotics: Applications, challenges, and the future )
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in robotic s. According to news originating from Stanford, California, by NewsRx correspond ents, research stated, “We survey applications of pretrained foundation models i n robotics.” Funders for this research include Directorate For Engineering; Defense Advanced Research Projects Agency; Office of Naval Research; Asee E-fellows; Nsf Graduate Research Fellowship. The news journalists obtained a quote from the research from Stanford University : “Traditional deep learning models in robotics are trained on small datasets ta ilored for specific tasks, which limits their adaptability across diverse applic ations. In contrast, foundation models pretrained on internet-scale data appear to have superior generalization capabilities, and in some instances display an e mergent ability to find zero-shot solutions to problems that are not present in the training data. Foundation models may hold the potential to enhance various c omponents of the robot autonomy stack, from perception to decisionmaking and co ntrol. For example, large language models can generate code or provide common se nse reasoning, while vision-language models enable open-vocabulary visual recogn ition. However, significant open research challenges remain, particularly around the scarcity of robot-relevant training data, safety guarantees and uncertainty quantification, and real-time execution. In this survey, we study recent papers that have used or built foundation models to solve robotics problems.”
Stanford UniversityStanfordCaliforni aUnited StatesNorth and Central AmericaEmerging TechnologiesMachine Lear ningRobotRobotics
NETL
NSTL
