A probabilistic framework for task-oriented grasp stability assessment

We present a probabilistic framework for grasp modeling and stability assessment. The framework facilitates assessment of grasp success in a goal-oriented way, taking into account both geometric constraints for task affordances and stability requirements specific for a task. We integrate high-level task information introduced by a teacher in a supervised setting with low-level stability requirements acquired through a robot's self-exploration. The conditional relations between tasks and multiple sensory streams (vision, proprioception and tactile) are modeled using Bayesian networks. The generative modeling approach both allows prediction of grasp success, and provides insights into dependencies between variables and features relevant for object grasping.

Authors

• Yasemin Bekiroglu
• Dan Song 0002
• Lu Wang 0006
• Danica Kragic

Keywords

• Robot sensing systems
• Bayes methods
• Stability analysis
• Probabilistic logic
• Planning
• Grasping
• Stability Assessment
• Probabilistic Framework
• Grasp Stability
• Bayesian Model
• General Approach
• Proprioceptive
• Geometric Constraints
• Stability Requirements
• High-level Tasks
• Discretion
• Classification Performance
• Variable Selection
• Probabilistic Model
• Conditional Distribution
• Object Classification
• Graphical Model
• Object Features
• Low-dimensional Space
• Object Shape
• Structure Learning
• Tactile Sensor
• Partial Observation
• Task Requirements
• Observation Of Others
• Markov Blanket
• Conditional Probability Distribution
• Problem Domain
• Real Setup
• Hand Position
• Discrete Data