No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
Humanoids operating in real-world workspaces must frequently execute task-driven, short-range movements to SE(2) target poses. To be practical, these transitions must be fast, robust, and energy efficient.
Evidence notes
- Experiments use Digit as the physical evaluation platform.
- The evaluation connects the reported method to Digit hardware in locomotion and planning tasks.
Company context
US robotics company focused on humanoid systems for logistics and warehouse automation. Digit is designed for real-world material handling tasks in structured environments.