[2301.02555] “No, to the Right” – Online Language Corrections for Robotic Manipulation via Shared Autonomy

Systems for language-guided human-robot interaction must satisfy two key desiderata for broad adoption: adaptivity and learning efficiency. Unfortunately, existing instruction-following agents cannot adapt, lacking the…

“No, to the Right” – Online Language Corrections for Robotic Manipulation via Shared Autonomy Yuchen Cui yuchenc@cs.stanford.edu Stanford University Stanford CA USA , Siddharth Karamcheti skaramcheti@cs.stanford.edu Stanford University Stanford CA USA , Raj Palleti Stanford University Stanford CA USA , Nidhya Shivakumar The Harker School San Jose CA USA , Percy Liang Stanford University Stanford CA USA and Dorsa Sadigh Stanford University Stanford CA USA (2023) Abstract. Systems for language-guided human-robot interaction must satisfy two key desiderata for broad adoption: adaptivity and learn

related reading

• [2310.17555] Interactive Robot Learning from Verbal Correctionar5iv.labs.arxiv.org
• [2109.01115] Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationarxiv.org
• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
• [2204.05186] Correcting Robot Plans with Natural Language Feedbackar5iv.labs.arxiv.org
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• State of Robot Learning, December 2025vedder.io
• [2602.10556] LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transferarxiv.org
• drocarxiv.org
• [2203.02155] Training language models to follow instructions with human feedbackarxiv.org
• Yell At Your Robot \emojishout Improving On-the-Fly from Language Correctionsarxiv.org
• Mixed-Initiative Dialog for Human-Robot Collaborative Manipulationarxiv.org