Search papers, labs, and topics across Lattice.
The paper introduces SignNav, a new embodied navigation task where agents must interpret signage to navigate large-scale indoor environments. To tackle the challenges of dynamically changing hints and sparse signage, they propose the Spatial-Temporal Aware Transformer (START) model, incorporating spatial and temporal awareness. Experiments on the newly constructed LSI-Dataset demonstrate that START, trained with a two-stage DAgger approach, achieves state-of-the-art performance with an 80% success rate and 0.74 NDTW on unseen validation splits, and shows promise in real-world deployment.
Forget pre-built maps: this new navigation agent interprets signs like a human, achieving 80% success in complex indoor environments.
Humans routinely leverage semantic hints provided by signage to navigate to destinations within novel Large-Scale Indoor (LSI) environments, such as hospitals and airport terminals. However, this capability remains underexplored within the field of embodied navigation. This paper introduces a novel embodied navigation task, SignNav, which requires the agent to interpret semantic hint from signage and reason about the subsequent action based on current observation. To facilitate research in this domain, we construct the LSI-Dataset for the training and evaluation of various SignNav agents. Dynamically changing semantic hints and sparse placement of signage in LSI environments present significant challenges to the SignNav task. To address these challenges, we propose the Spatial-Temporal Aware Transformer (START) model for end-to-end decision-making. The spatial-aware module grounds the semantic hint of signage into physical world, while the temporal-aware module captures long-range dependencies between historical states and current observation. Leveraging a two-stage training strategy with Dataset Aggregation (DAgger), our approach achieves state-of-the-art performance, recording an 80% Success Rate (SR) and 0.74 NDTW on val-unseen split. Real-world deployment further demonstrates the practicality of our method in physical environment without pre-built map.
