Collaborative Pushing and Grasping of Tightly Stacked Objects via Deep Reinforcement Learning.
Yuxiang YangZhihao NiMingyu GaoJing ZhangDacheng TaoPublished in: IEEE CAA J. Autom. Sinica (2022)
Keyphrases
- reinforcement learning
- object classes
- viewpoint
- data objects
- multiple objects
- machine learning
- collaborative learning
- vision system
- moving objects
- d objects
- attribute values
- state space
- evaluation function
- function approximation
- object model
- object recognition
- multi user
- complex scenes
- object models
- collaborative environment
- human hand