Learning action failure models from interactive physics-based simulations

Predicting the outcome of an action can help a robot detect failures in advance, and schedule action replanning before an error occurs. We propose using an interactive physics based simulator with the aim of collecting realistic data to be used for learning. We then show how we save and query for specific information from the data more effectively. The data from the simulation is used to learn a failure detection model which is utilized by a real robot performing the same actions. We show that learning from simulation data is realistic enough to be applied on a real robot. The learning algorithm is more simple in design and outperforms the more complex one from our previous work.

Authors

• Andrei Haidu
• Daniel Kohlsdorf
• Michael Beetz

Keywords

• Robots
• Data models
• Physics
• Hidden Markov models
• Computational modeling
• Detectors
• Databases
• Simulated Data
• Real Robot
• Data In Order
• Simulation Environment
• Virtual World
• Simulation Step
• Manipulation Tasks
• Negative Sequence
• Dynamic Time Warping
• Physics Engine
• Robotic Hand
• Remote Devices
• Inverse Reinforcement Learning
• Commonsense Knowledge
• Multidimensional Case