Scalable Quasi-static Self-modeling for Physical Legged Locomotion

Training data and evaluation results for models developed in the paper 'Scalable Quasi-static Self-modeling for Physical Legged Locomotion' by Yuhang Hu. The data file consists of the data used for training models and all the evaluation results.

Use Cases

• Training machine learning models for legged locomotion based on the provided training data.
• Benchmarking new locomotion algorithms against the included evaluation results.
• Studying quasi-static self-modeling approaches for physical robots.
• Reproducing the experiments and findings from the associated research paper.

Strengths

• Data is directly associated with a published research paper, providing context and methodology.
• Includes both training data and evaluation results, enabling full replication of the study.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Yuhang Hu via paperswithcode.

Collection Method

Created for the research paper 'Scalable Quasi-static Self-modeling for Physical Legged Locomotion'.