rldx1-ft-rc365-nf4

Execute kitchen manipulation tasks on PandaMobile robots using a fine-tuned Vision-Language-Action policy.

Updated Jul 5, 2026
One-click install
npx skills add https://github.com/bensonlee5/openral --skill rldx1-ft-rc365-nf4
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rldx1-ft-rc365-nf4
Source: https://github.com/bensonlee5/openral/tree/main/rskills/rldx1-ft-rc365-nf4
Command: npx skills add https://github.com/bensonlee5/openral --skill rldx1-ft-rc365-nf4

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openral, pytorch, rldx, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a generalist Vision-Language-Action policy for robot agents, enabling tasks like picking, placing, opening, closing, pouring, wiping, and pushing within a kitchen environment on PandaMobile robots.

Core Features & Use Cases

  • Generalist Policy: Capable of a wide range of tasks such as picking, placing, opening, closing, pouring, wiping, and pushing.
  • Embodiment: Optimized for PandaMobile robots with specific sensor and actuator requirements.
  • Scene: Designed for kitchen environments.
  • Use Case: Imagine a robot in a kitchen that needs to pick up a bottle and pour it into another container. This Skill can be used to automate this task.

Quick Start

Run the skill with the command: openral sim run --config scenes/sim/robocasa_pnp.yaml --rskill rskills/rldx1-ft-rc365-nf4 --view

Frequently Asked Questions about rldx1-ft-rc365-nf4

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate robot control for kitchen tasks like pouring and picking using a vision-language-action policy?

You can automate kitchen robot control by running a fine-tuned vision-language-action policy that handles visual perception, language understanding, and action execution for PandaMobile robots in a simulated environment.

What kitchen tasks can a generalist vision-language-action policy perform for PandaMobile robots?

A generalist vision-language-action policy can perform picking, placing, opening, closing, pouring, wiping, and pushing tasks for PandaMobile robots operating in kitchen environments.

Do I need OpenRAL and RoboCasa simulation to run the RLDX-1 vision-language-action policy?

Yes, you need the OpenRAL runtime and access to the RoboCasa simulation environment to execute the RLDX-1 vision-language-action policy for PandaMobile robots.

How do I start a robot simulation with OpenRAL for kitchen tasks?

Start the robot simulation by running the command `openral sim run --config scenes/sim/robocasa_pnp.yaml --rskill rskills/rldx1-ft-rc365-nf4 --view` in your terminal.

Does the vision-language-action policy work with robots other than PandaMobile?

No, this specific policy is optimized for PandaMobile robots with specific sensor and actuator requirements, meaning it is not directly compatible with other robot embodiments.

What dependencies are required to implement vision-language-action models for robotics?

Implementing vision-language-action models for robotics requires dependencies including OpenRAL, PyTorch, and RLDX to support the simulation and policy execution.