Cloud-hosted vision-language models (VLMs) offer greater contextual reasoning capabilities than smaller onboard models, but frequent visual uploads increase communication overhead and add network and inference latency to tactical decisions. We present a risk-adaptive edge-cloud architecture in which onboard traffic assessment determines when cloud reasoning is requested. An onboard VLM and a lightweight detector capture temporal traffic conditions and path-relative hazards for conservative local response and selective cloud access. The cloud model provides tactical advice, while validation, vehicle control, and automatic emergency braking remain local. In CARLA experiments, our method matched the task success rate of periodic cloud access while reducing cloud requests by 54.1% and recording fewer automatic emergency braking (AEB) activations. In a delayed-roadwork ablation, semantic events triggered requests before the next scheduled audit. Across three emulated network profiles, the method continued to reduce cloud traffic, although lane changes took longer than with periodic access. Onboard traffic assessment therefore served as a practical trigger for selective VLM inference in these experiments.
Meng Ma, Shuyang Li, Naigang Wang et al.· 0 citations
Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize corner cases with photorealistic observations. Corner-case generation is inherently a multi-source problem spanning visual representation, scene reasoning, and vehicle trajectory generation and control. Prior knowledge- and model-based approaches typically focus on scene or trajectory components in isolation, while diffusion-based methods attempt end-to-end generation but still struggle to ensure spatiotemporal consistency and physical realism. To unify these aspects within a single framework, we propose CARLA-GS, a modular corner-case synthesis pipeline that decouples visual representation, semantic reasoning, and physics-based execution while maintaining tight cross-module coupling. Starting from real driving data, we reconstruct an editable gaussian scene with additional geometry-consistent constraints. A multi-agent LLM then performs scene-level reasoning to identify risky interactions and generate intent-level waypoint trajectories, while the low-level motion control is delegated to CARLA, where a PID controller ensures kinematic and dynamic feasibility. The simulated vehicle states are finally re-projected into the gaussian scene for ego-centric rendering. This design enables high-level semantic reasoning, low-level physically executable motion, and photorealistic corner-case generation within a unified pipeline. Experiments on the Waymo Open Dataset show, both quantitatively and qualitatively, that our framework enables controllable corner-case generation and produces photorealistic, spatiotemporally consistent videos aligned with semantic intent and physically feasible motion.
Cooperative platooning can reduce the energy use of Connected and Autonomous Vehicle (CAV) fleets, but the routing problem becomes difficult when vehicles must meet on the same road segments at compatible times while moving through unstable urban traffic. This paper develops an edge-assisted, closed-loop evaluation pipeline for platooning-aware vehicle routing. Roadside Units estimate local traffic kinematics from video, classify segment-level flow stability, and activate platooning rewards only on road segments where close-gap coordination is physically appropriate. The resulting multi-vehicle routing problem is written directly as a Quadratic Unconstrained Binary Optimization (QUBO) model, so pairwise platooning interactions are represented as native quadratic Ising terms instead of requiring auxiliary MILP linearization variables. We evaluate the framework using a 24-hour microscopic SUMO simulation of Troy, NY, together with localized IBM Quantum hardware benchmarks. The SUMO study shows an $18.5\%$ reduction in fleet tractive-energy demand relative to a non-cooperative baseline. On 25-active-qubit benchmark instances executed on $\texttt{ibm_boston}$, Linear-Chain QAOA reduces two-qubit CNOT depth by $66.7\%$ compared with dense QAOA and samples the exact classical ground state with $P_{\text{feas}} = 38.6\%$ and $P_{\text{opt}} = 14.2\%$ at $p=2$. These results suggest that edge perception and shallow quantum optimization can work together as a useful component of closed-loop CAV platoon dispatching.
A federated quantum feature-sketching pipeline for traffic-stability gating using Pauli expectations and NGSIM trajectories, SUMO predictive gating with sensing noise, and IBM Quantum hardware is presented.