Predicting object interactions from contact distributions

Contacts between objects play an important role in manipulation tasks. Depending on the locations of contacts, different manipulations or interactions can be performed with the object. By observing the contacts between two objects, a robot can learn to detect potential interactions between them. Rather than defining a set of features for modeling the contact distributions, we propose a kernel-based approach. The contact points are first modeled using a Gaussian distribution. The similarity between these distributions is computed using a kernel function. The contact distributions are then classified using kernel logistic regression. The proposed approach was used to predict stable grasps of an elongated object, as well as to construct towers out of assorted toy blocks.

Authors

• Oliver Kroemer
• Jan Peters 0001

Keywords

• Robots
• Kernel
• Error analysis
• Three-dimensional displays
• Logistics
• Computational modeling
• Gaussian distribution
• Contact Point
• Kernel Function
• Manipulation Tasks
• Local Contact
• Error Rate
• Support Vector Machine
• Covariance Matrix
• Center Of Mass
• Mixture Model
• Point Cloud
• Rotation Axis
• Position Of Point
• Tactile Sensor
• Central Objective
• Force Estimation
• Classification Ability
• Coordinate Frame
• Real Robot
• Object Placement
• Set Of Contacts
• Benchmark Approaches
• Mean Contact
• Object Point Cloud