Hierarchical Instruction-aware Embodied Visual Tracking

TL;DR

This paper introduces HIEVT, a hierarchical agent that improves embodied visual tracking by translating user instructions into spatial goals and using reinforcement learning for robust, generalizable target tracking across diverse environments.

Contribution

The paper proposes a novel hierarchical framework that bridges instruction understanding and action generation using spatial goals, enhancing generalization and robustness in embodied visual tracking.

Findings

HIEVT outperforms existing methods in unseen environments.

The model demonstrates robustness across diverse target dynamics.

Real-world deployment confirms effectiveness and generalizability.

Abstract

User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in language models (e.g., LLMs, VLMs, VLAs) have improved instruction comprehension, these models face critical limitations in either inference speed (LLMs, VLMs) or generalizability (VLAs) for UC-EVT tasks. To address these challenges, we propose \textbf{Hierarchical Instruction-aware Embodied Visual Tracking (HIEVT)} agent, which bridges instruction comprehension and action generation using \textit{spatial goals} as intermediaries. HIEVT first introduces \textit{LLM-based Semantic-Spatial Goal Aligner} to translate diverse human instructions into spatial goals that directly annotate the desired spatial position. Then the \textit{RL-based Adaptive Goal-Aligned Policy}, a general offline policy, enables the tracker to position the target as specified by the spatial goal. To benchmark UC-EVT tasks, we collect over ten million trajectories for training and evaluate across one seen environment and nine unseen challenging environments. Extensive experiments and real-world deployments demonstrate the robustness and generalizability of HIEVT across diverse environments, varying target dynamics, and complex instruction combinations. The complete project is available at https://sites.google.com/view/hievt.