![]() ![]() We use our framework on several downstream tasks. The contact predictor allows the agent to learn the affordance information ( i.e., where to act for the robotic arm on the object) from previous manipulation experience, and such affordance semantics then helps the agent learn effective policies through RL updates. In this study, we fill such a research gap by designing algorithms that can automatically learn affordance semantics through a contact prediction process. ![]() Nevertheless, how to learn affordance in an end-to-end fashion within the RL process is unknown. For example, an effective policy should know the pulling force on the handle to open a door. Visual affordance provides object-centric information priors that offer actionable semantics for objects with movable parts. It is hard to train a policy that can generalize over different objects with vast semantic categories, diverse shape geometry, and versatile functionality. Learning to manipulate 3D articulated objects in an interactive environment has been challenging in reinforcement learning (RL) studies. ![]() Official Implementation of "RLAfford: End-to-end Affordance Learning with Reinforcement Learning" ICRA 2023 ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |