Skip to content

[HUMANOID] Vis-RL Tasks #47

Description

@danielsanei

The goal is to ultimately train the humanoid robot to do soccer kicking with a form of visual RL.

Currently we are exploring Vis-RL using the SO100 robot arms for pick and place tasks to get a feel for the pipeline, then will move onto visual RL using the humanoid for dynamic tasks like soccer kicking.

Currently setting up the Vis-RL environment.

Deadline: 2 weeks from now (2/21/26) for demonstrating a pick and place task.

Metadata

Metadata

Labels

No labels
No labels

Type

No type

Fields

No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions