Can Aerial VLA Models Cooperate? Evaluating Closed-Loop Air-Ground Coordination with CARLA-Air

• URL: http://arxiv.org/abs/2605.31066v1
• Date: Fri, 29 May 2026 09:36:08 GMT
• Title: Can Aerial VLA Models Cooperate? Evaluating Closed-Loop Air-Ground Coordination with CARLA-Air
• Abstract summary: We study whether single-UAV capabilities can transfer to air-ground cooperation.<n>We use CARLA-Air, a single-process evaluation environment that unifies CARLA and AirSim inside one Unreal Engine runtime.<n>Results show that current aerial VLA models can often track or follow a ground partner, but struggle to convert this single-agent competence into stable cooperative behavior.
• Score: 2.061094726550731
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent aerial vision-language-action (VLA) models show promising single-UAV capabilities, such as tracking moving objects and navigating to language-specified landmarks. However, it remains unclear whether these capabilities can transfer to air-ground cooperation, where a UAV and a UGV must act jointly in a shared, closed-loop physical world. We study this question with CARLA-Air, a single-process air-ground evaluation environment that unifies CARLA and AirSim inside one Unreal Engine runtime. By sharing the same world state, physics tick, and sensing pipeline, CARLA-Air enables physically consistent UAV--UGV interaction and precise measurement of simulation-timestamp alignment and effective coordination latency. Using CARLA-Air, we evaluate representative aerial VLA and planning baselines on two complementary diagnostic tasks: moving-platform landing and occlusion-recovery escort. The results show that current aerial VLA models can often track or follow a ground partner, but struggle to convert this single-agent competence into stable cooperative behavior. State prompting provides limited benefit, and naive bidirectional interaction fails to consistently improve performance and can amplify errors for most baselines. These findings suggest that, under the tested text-based cue interfaces, zero-shot cooperative air-ground VLA requires three components beyond the current paradigm: explicit partner-state grounding, low-latency action coordination, and team-level objective alignment. Our code is available at https://github.com/louiszengCN/CarlaAir.

Related papers

• Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps [23.62701600758693]
  Air-ground collaborative Vision-and-Language Navigation (VLN) pairs an unmanned aerial vehicle (UAV) with a global bird's-eye view and an unmanned ground vehicle (UGV) with a local first-person view.<n>We establish AGC-VLN (Air-Ground Collaborative VLN), the first training-free baseline for air-ground collaborative VLN.<n>On 100 closed-loop episodes in CARLA-Air's Town10HD scene, AGC-VLN reaches a 77.0% joint success rate, a collaboration gain of +27.0% over the weaker individual agent
  arXiv  Detail & Related papers  (2026-09-03T07:38:41Z)
• VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation [50.18051979020699]
  VIPS is a benchmark for cooperative autonomous driving in V2I settings based on pseudo-simulation.<n>CoS-V2X is a cooperative planning framework based on sparse representations.
  arXiv  Detail & Related papers  (2026-09-02T11:32:52Z)
• Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance [108.46436073194546]
  We argue that effective planning should be local, visually grounded, internally generated, and directly aligned with action.<n>We propose Afford-VLA, a unified framework that internalizes task-conditioned affordance as an explicit visual planning interface within VLA models.
  arXiv  Detail & Related papers  (2026-05-22T20:43:47Z)
• CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence [2.061094726550731]
  We present CARLA-Air, an open-source infrastructure that unifies high-fidelity urban driving and physics-accurate multirotor flight within a single Unreal Engine process.<n>Within a shared physics tick and rendering pipeline, CARLA-Air delivers environments with rule-compliant traffic, socially-aware pedestrians, and aerodynamically consistent UAV dynamics.
  arXiv  Detail & Related papers  (2026-03-30T04:49:29Z)
• AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation [15.824903784302562]
  Vision-Language-Action (VLA) models have achieved remarkable success in ground-based embodied intelligence.<n>Their application to Aerial Manipulation Systems (AMS) remains a largely unexplored frontier.<n>We propose textbfAIR-VLA, the first VLA benchmark specifically tailored for aerial manipulation.
  arXiv  Detail & Related papers  (2026-01-29T12:09:00Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [70.72227437717467]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)
• UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning [39.07541452390107]
  Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction.<n>We formalize this problem as the Flying-on-a-Word (Flow) task and introduce UAV imitation learning as an effective approach.<n>We present UAV-Flow, the first real-world benchmark for language-conditioned, fine-grained UAV control.
  arXiv  Detail & Related papers  (2025-05-21T16:31:28Z)
• Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmark [15.405137983083875]
  Aerial-ground cooperation offers a promising solution by integrating UAVs' aerial views with ground vehicles' local observations.<n>This paper presents a comprehensive solution for aerial-ground cooperative 3D perception through three key contributions.
  arXiv  Detail & Related papers  (2025-03-10T07:00:07Z)
• Wireless-Enabled Asynchronous Federated Fourier Neural Network for Turbulence Prediction in Urban Air Mobility (UAM) [101.80862265018033]
  Urban air mobility (UAM) has been proposed in which vertical takeoff and landing (VTOL) aircraft are used to provide a ride-hailing service. In UAM, aircraft can operate in designated air spaces known as corridors, that link the aerodromes. A reliable communication network between GBSs and aircraft enables UAM to adequately utilize the airspace.
  arXiv  Detail & Related papers  (2021-12-26T14:41:52Z)
• Attention-based Reinforcement Learning for Real-Time UAV Semantic Communication [53.46235596543596]
  We study the problem of air-to-ground ultra-reliable and low-latency communication (URLLC) for a moving ground user. We propose a novel multi-agent deep reinforcement learning framework, coined a graph attention exchange network (GAXNet) GAXNet achieves 6.5x lower latency with the target 0.0000001 error rate, compared to a state-of-the-art baseline framework.
  arXiv  Detail & Related papers  (2021-05-22T12:43:25Z)
• Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms [98.78553146823829]
  Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks. In this paper, a novel framework is proposed to implement distributed learning (FL) algorithms within a UAV swarm.
  arXiv  Detail & Related papers  (2020-02-19T14:04:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.