Curvature-Optimal Robot Path Parameters for Linear and Circular Transitions

Neural networks were trained on this dataset of curvature-optimal geometry parameters for smoothing robot motion paths. Benjamin Kaiser at the University of Stuttgart generated the data by offline solving an optimization problem for corner smoothing. The collection includes example trajectories for a Kuka KR500 R3330 robot, both smoothed and non-smoothed, with velocity planned under jerk limits.

Use Cases

• Training neural networks for robot trajectory smoothing based on optimal geometry parameters.
• Benchmarking motion planning algorithms using the provided non-smoothed and smoothed example trajectories.
• Analyzing the effect of jerk-limited velocity planning on robot path execution.
• Studying the application of polynomial splines for smoothing linear-linear and linear-circular transitions in robot paths.

Strengths

• Data was generated by solving a specific optimization problem for curvature-optimal corner smoothing.
• Includes comparative example trajectories (smoothed vs. non-smoothed) for a specific industrial robot model.
• Trajectory data incorporates jerk-limited velocity planning, a key constraint for realistic robot motion.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and overall dataset size are unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

University of Stuttgart

Collection Method

Data was generated by offline solving an optimization problem described in a related publication.