evButtonPush: Robot Arm Simulation for Elevator Button Pressing

A simulation demonstration dataset of a ROBOTIS OMY 6-DoF arm pressing an elevator call button in the NVIDIA Isaac Sim / Isaac Lab environment. The dataset was automatically collected using a scripted IK teacher. The dataset page is hosted by RobotisAI and was last updated on 2026-04-28.

Use Cases

• Training reinforcement learning agents for contact-rich manipulation tasks based on the described button-pressing scenario.
• Benchmarking inverse kinematics (IK) and control policies for a 6-DoF arm with a two-finger gripper.
• Developing and testing state machines for robotic tasks based on the mention of an improved version with a Finite State Machine (FSM).
• Studying the effects of randomized environment variants on task performance, as the elevator model includes 100 variants.

Strengths

• Data was generated in a controlled simulation environment (NVIDIA Isaac Sim/Lab), which allows for precise and repeatable conditions.
• The description specifies key robot parameters, including a pedestal height of 0.908 m and gripper stiffness/effort values.
• An improved version (v02) with a contact-force based teacher is referenced, suggesting iterative development.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and sample data are unknown, which may limit suitability assessment.
• The license is unspecified, which could restrict usage.

Provenance

Source

RobotisAI

Collection Method

Automatically collected using a scripted inverse kinematics (IK) teacher in NVIDIA Isaac Sim / Isaac Lab.

Time Range

Dataset version dated 260422 (likely 2022-04-26).

Freshness

Last updated 2026-04-28 02:16:55; freshness should be verified.

Geography

Simulation-based; no real-world geography.