Skill Generalization with Verbs
Autor: | Ma, Rachel, Lam, Lyndon, Spiegel, Benjamin A., Ganeshan, Aditya, Patel, Roma, Abbatematteo, Ben, Paulius, David, Tellex, Stefanie, Konidaris, George |
---|---|
Rok vydání: | 2024 |
Předmět: | |
Druh dokumentu: | Working Paper |
DOI: | 10.1109/IROS55552.2023.10341472 |
Popis: | It is imperative that robots can understand natural language commands issued by humans. Such commands typically contain verbs that signify what action should be performed on a given object and that are applicable to many objects. We propose a method for generalizing manipulation skills to novel objects using verbs. Our method learns a probabilistic classifier that determines whether a given object trajectory can be described by a specific verb. We show that this classifier accurately generalizes to novel object categories with an average accuracy of 76.69% across 13 object categories and 14 verbs. We then perform policy search over the object kinematics to find an object trajectory that maximizes classifier prediction for a given verb. Our method allows a robot to generate a trajectory for a novel object based on a verb, which can then be used as input to a motion planner. We show that our model can generate trajectories that are usable for executing five verb commands applied to novel instances of two different object categories on a real robot. Comment: 7 pages + 2 pages (references), 6 figures. Accepted at IROS 2023. Code, dataset info and demo videos can be found at: https://rachelma80000.github.io/SkillGenVerbs/ |
Databáze: | arXiv |
Externí odkaz: |