EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models

TL;DR

EgoActor introduces a vision-language model that grounds high-level instructions into precise, spatially aware humanoid actions, enabling real-time, robust task execution in complex environments.

Contribution

The paper presents EgoActor, a scalable VLM that integrates perception and action grounding for humanoid robots, addressing real-world challenges with egocentric data and spatial reasoning.

Findings

EgoActor performs real-time action inference under 1 second.

The model generalizes across diverse tasks and unseen environments.

EgoActor effectively bridges task planning and motor execution.

Abstract

Deploying humanoid robots in real-world settings is fundamentally challenging, as it demands tight integration of perception, locomotion, and manipulation under partial-information observations and dynamically changing environments. As well as transitioning robustly between sub-tasks of different types. Towards addressing these challenges, we propose a novel task - EgoActing, which requires directly grounding high-level instructions into various, precise, spatially aware humanoid actions. We further instantiate this task by introducing EgoActor, a unified and scalable vision-language model (VLM) that can predict locomotion primitives (e.g., walk, turn, move sideways, change height), head movements, manipulation commands, and human-robot interactions to coordinate perception and execution in real-time. We leverage broad supervision over egocentric RGB-only data from real-world demonstrations, spatial reasoning question-answering, and simulated environment demonstrations, enabling EgoActor to make robust, context-aware decisions and perform fluent action inference (under 1s) with both 8B and 4B parameter models. Extensive evaluations in both simulated and real-world environments demonstrate that EgoActor effectively bridges abstract task planning and concrete motor execution, while generalizing across diverse tasks and unseen environments.