3 accepted papers
While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge due to their lack of explicit physical grounding and inability to perfo…
This paper introduces H-MaP, a hybrid sequential manipulation planner that addresses complex tasks requiring both sequential actions and dynamic contact mode switches. Our approach reduces configuration space dimensionality by decoupling object trajectory planning from manipulation planning through …
This letter introduces H-MaP, a hybrid sequential manipulation planner that addresses complex tasks requiring both sequential actions and dynamic contact mode switches. Our approach reduces configuration space dimensionality by decoupling object trajectory planning from manipulation planning through