MaNIduck-101: Robotic Manipulation Simulation for Complex Interactions

MaNIduck-101 is a real-world simulation dataset for robotic manipulation, focusing on complex human-object interaction and fine-grained motion modeling. It systematically covers manipulation types like grasping, pushing, pulling, rotating, assembly, and tool use through high-fidelity physical simulation. The dataset was created by author bh2821 and was last updated on the Hugging Face platform in February 2026.

Use Cases

• Training robotic control policies based on simulated grasping and pushing actions.
• Modeling fine-grained motion for tasks like assembly and tool use described in the dataset.
• Benchmarking simulation-to-real transfer for manipulation tasks involving contact and friction.
• Developing multi-modal perception models for human-object interaction scenarios.

Strengths

• Models real-world physics including contact, friction, constraints, and dynamics.
• Systematically covers multiple common robotic manipulation types.
• Last updated on 2026-02-22, indicating recent maintenance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and dataset size are unknown, which may limit suitability assessment.
• The full description is hosted externally, requiring a click-through for complete details.

Provenance

Source

Hugging Face dataset uploaded by author bh2821.

Collection Method

Created through high-fidelity physical simulation.

Freshness

Last updated 2026-02-22 04:19:16