Dimensionality reduction for trajectory learning from demonstration

Programming by demonstration is an attractive model for allowing both experts and non-experts to command robots' actions. In this work, we contribute an approach for learning precise reaching trajectories for robotic manipulators. We use dimensionality reduction to smooth the example trajectories and transform their representation to a space more amenable to planning. Key to this approach is the careful selection of neighboring points within and between trajectories. This algorithm is capable of creating efficient, collision-free plans even under typical real-world training conditions such as incomplete sensor coverage and lack of an environment model, without imposing additional requirements upon the user such as constraining the types of example trajectories provided. Experimental results are presented to validate this approach.

Authors

• Nik A. Melchior
• Reid G. Simmons

Keywords

• Orbital robotics
• Robot sensing systems
• Humans
• Manipulators
• Trajectory
• Navigation
• Wire
• Motion planning
• Robotics and automation
• Robotic assembly
• Dimensionality Reduction
• Learning Trajectories
• Inverse Reinforcement Learning
• Robot Manipulator
• Degrees Of Freedom
• High-dimensional
• Dimensional Space
• Time Series Data
• Environmental Model
• Path Planning
• Original Space
• Robotic Arm
• Training Examples
• Configuration Space
• Adjacent Points
• End-effector
• Human Motion
• Space Planning
• Geodesic Distance
• Robot Operating
• Neighborhood Selection
• Human Education
• Nearby Points
• Knowledge Space
• Low-dimensional Space
• Points In Space