Search papers, labs, and topics across Lattice.
This paper introduces the Unified Embodied Seeking and Following Benchmark (UESF-Bench), which addresses the limitations of existing benchmarks by requiring agents to locate and follow a language-described target in dynamic environments. The authors propose SeekFollow-VLA, a vision-language-action framework that integrates semantic-guided exploration and behavior switching, enabling agents to effectively manage the transition between seeking and following tasks. Experimental results demonstrate that SeekFollow-VLA significantly outperforms both single-head and dual-head baselines in various scenarios, establishing a new standard for evaluating embodied agents in these tasks.
Agents can now seamlessly transition between seeking and following tasks in dynamic environments, setting a new benchmark for embodied AI performance.
Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode. This setting simplifies the problem and overlooks a more realistic requirement: an agent often needs to first find a language-described target and then persistently follow that target in a dynamic environment. While recent work has started to study human search, existing settings are typically evaluated in task-specific scenarios and often rely on stronger prior knowledge of the environment. Moreover, they usually treat searching and following as separate tasks and still lack a unified benchmark for systematic evaluation. To address these limitations, we introduce the Unified Embodied Seeking and Following Benchmark (UESF-Bench), a large-scale and diverse benchmark for embodied human seeking and following. The benchmark requires agents to handle semantic-guided exploration, reliable behavior switching and recovery, and delayed identity grounding. To this end, we propose SeekFollow-VLA, a vision-language-action framework with a task-driven routing mechanism for latent phase inference and transition modeling between seeking and following. Experimental results show that SeekFollow-VLA achieves clear improvements over both single-head and dual-head baselines across single-person and multi-person environments, establishing a baseline for unified embodied seek-and-follow.
