AirGroundVLN enables better drone and robot navigation together
AirGroundVLN: A Large-Scale Benchmark for Goal-Oriented Air-Ground Collaborative Vision-and-Language Navigation
Robotics
Summary
Finding and reaching places using language instructions can be tough when relying on only ground robots or only drones because their views are very different. The authors created AirGroundVLN, a big set of navigation challenges in virtual worlds to test how well drones and ground robots can work together. They also built a system called AG-CoNAV that helps these devices remember and share what they see from above and on the ground to plan better paths. Their experiments show that this combined approach is promising for tasks needing both wide perspective and close-up details.
What this means in practice
- •For robotics engineering teams: Develop navigation systems where drones guide ground robots for tasks needing broad search and precise location in complex environments.
- •For drone software developers: Create aerial guidance tools that support ground-level robots in moving efficiently by sharing spatial memory and planning information.
Authors
Zhenxuan Zeng, Qingle Wu, Wei Suo, Maojia Wu, Bairong Zhang, Hangzheng Yu, Peng Wang
Abstract
Goal-oriented Vision-and-Language Navigation (VLN) requires agents to locate and reach targets described in natural language without prescribed routes. Air--ground collaboration is valuable for tasks requiring both wide-area search and fine-grained localization. However, systematic study of goal-oriented air--ground collaborative VLN remains limited by the lack of large-scale, diverse benchmarks and two core challenges: 1) substantial differences between aerial and ground views, together with useful observations becoming unavailable as navigation proceeds, make it difficult to maintain spatially consistent context across platforms and over time; and 2) asymmetric spatial observability makes ground perception locally detailed but spatially limited and aerial perception broad but locally coarse, limiting the reliability of single-platform planning. To address these limitations, we introduce AirGroundVLN, a benchmark containing 10,281 navigation episodes and 955 target instances across 19 Unreal Engine environments, with seen/unseen splits and an aerial-visibility protocol for systematic evaluation. Alongside the benchmark, we propose AG-CoNAV, a trainable reference framework comprising two key components: Spatiotemporally Anchored Collaborative Memory (SACM) and Aerial-Guided Regional-to-Local Planning (AGRLP). SACM maintains and retrieves spatially consistent historical context across aerial and ground observations. Meanwhile, AGRLP combines regional aerial guidance with fine-grained ground navigation. Extensive experiments demonstrate the effectiveness of AG-CoNAV and establish AirGroundVLN as a comprehensive benchmark for future exploration.