Collaborative Programming of Conditional Robot Tasks

Conventional robot programming methods are not suited for non-experts to intuitively teach robots new tasks. For this reason, the potential of collaborative robots for production cannot yet be fully exploited. In this work, we propose an active learning framework, in which the robot and the user collaborate to incrementally program a complex task. Starting with a basic model, the robot's task knowledge can be extended over time if new situations require additional skills. An on-line anomaly detection algorithm therefore automatically identifies new situations during task execution by monitoring the deviation between measured- and commanded sensor values. The robot then triggers a teaching phase, in which the user decides to either refine an existing skill or demonstrate a new skill. The different skills of a task are encoded in separate probabilistic models and structured in a high-level graph, guaranteeing robust execution and successful transition between skills. In the experiments, our approach is compared to two state-of-the-art Programming by Demonstration frameworks on a real system. Increased intuitiveness and task performance of the method can be shown, allowing shop-floor workers to program industrial tasks with our framework.

Authors

• Christoph Willibald
• Thomas Eiband
• Dongheui Lee

Keywords

• Service robots
• Collaboration
• Production
• Robot sensing systems
• Task analysis
• Robots
• Robot programming
• Collaborative Program
• Active Learning
• Probabilistic Model
• Task Execution
• Anomaly Detection
• Sensor Values
• Online Detection
• Statistical Models
• Covariance Matrix
• Expectation Maximization
• Teaching Process
• Graphical User Interface
• Task Conditions
• State Machine
• Gaussian Mixture Model
• Mahalanobis Distance
• Sensor Readings
• Program Strategies
• Executive Skills
• Dynamic Time Warping
• Objective Weight
• Object Geometry
• Successful Execution
• Active Learning Strategies
• Sensor Modalities