Papers for

traffic system operators

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Monotonicity enables scalable neural safety checks for complex systems

Scalable Neural Safety Certification via Monotonicity

Abstract: Learning-based safety certification offers a promising route for verifying complex dynamical systems when explicit models are unavailable, but existing data-driven methods often scale poorly: they treat the system as a black box, rely on dense discretizations or Lipschitz bounds, and consequently suffer from sample complexity that grows exponentially with dimension. This paper shows that a common structural property of dynamical systems--monotonicity--can be used to break this curse of dimensionality. We develop a data-driven framework for robust safety verification and safe controller synthesis for unknown monotone systems using only simulator queries. Our main theoretical result proves that, for monotone systems with upper-closed unsafe sets, safety is completely characterized by the existence of monotone inductive barrier certificates. This structure reduces certificate verification over continuous state spaces to localized boundary checks over finitely many cells. To learn such certificates, we introduce Max-Monotone Networks, a monotone neural architecture with universal approximation guarantees for monotone functions. We then propose a training and refinement algorithm that, upon successful termination, returns formally valid neural barrier certificates and, under mild partition assumptions, requires only $O(n)$ simulator queries. Across high-dimensional benchmarks, including oscillator networks with up to $13{,}659$ states and traffic networks with $1{,}000$ states, our method certifies safety in regimes where prior approaches either do not converge or exceed memory limits. These results demonstrate that exploiting order structure can make neural safety certification both scalable and formally sound.

Sun 8 NovMachine Learning
The gist
Verifying safety of complex systems can be very hard, especially when the system's exact rules are unknown. The authors show that when a system behaves in a way called "monotonicity," safety checks become much simpler and faster. They build a special kind of neural network to find safety certificates using fewer simulations. Their method works well even on very large systems, like traffic or oscillator networks, where older methods struggle or fail.
Open → 2611.11119v1

Roadside radar classification improved using point cloud pattern analysis

Refining Roadside 4D Radar Vehicle Classification Using Point-Cloud Dispersion

Abstract: Roadside sensing infrastructure is essential for Intelligent Transportation Systems (ITS), but cameras and legacy sensors are limited in range, weather robustness, and depth accuracy. 4D radar complements these modalities by resolving range, azimuth, elevation, and radial velocity under adverse conditions, though its sparse, noisy point clouds make reliable classification difficult. We present a roadside multi-sensor platform combining a 4D radar and stereo depth camera under synchronized acquisition, used to collect a real-world dataset. Our analysis reveals a substantial class-distribution discrepancy between modalities, most notably a strong radar confusion between passenger cars and motorcycles (49.01% and\ 48.60% of the dataset). To address this, we propose a Neyman-Pearson-based binary classifier on the temporally-smoothed 2D positional standard deviation of radar point cloud clusters, reducing classification error from 52.1% to 42.7%. This lightweight and edge-deployable approach improves radar-only classification reliability and lays the foundation for future camera-radar fusion.

Sun 1 NovComputer Vision and Pattern Recognition
The gist
Roadside sensors help track vehicles for smarter traffic systems, but usual cameras and older sensors don't work well in bad weather or at a distance. The authors show that 4D radar can see vehicles in all directions even in tough conditions, but it often confuses similar vehicles like cars and motorcycles because its data is noisy. They built a system combining radar and a stereo camera to gather real-world data and then found a clever way to look at how radar points spread over time. This method cuts errors in telling cars from motorcycles almost by a fifth and can work on devices with limited computing power.
Open → 2611.02147v1

Safe multi-agent training improves teamwork and safety in control tasks

SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning

Abstract: Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure this constraint outcome, but does not distinguish which agents' actions most strongly influence that violation. We present SafeDiSTL, a constrained multi-agent reinforcement learning framework that allows for credit assignment even with joint constraint measurements. We use Signal Temporal Logic (STL) robustness to measure episode-level violation through running-maximum cost increments. Smooth full-episode robustness and differentiable dynamics provide action sensitivities, which allocate each cost increment across agents at the same decision time. These sensitivities account for delayed effects when weighting agents' shares of each cost increment. We study the framework in cooperative payload transport, connected navigation, and networked traffic control tasks. SafeDiSTL achieves 1.6-5.1x the safe-success rate in transport, improves navigation safe-success by 11.1%, and delivers 50-68% more throughput in traffic when compared to constrained baselines. Results demonstrate a strong improvement of the learned policy in dealing with shared constraint while retaining the performance of unconstrained policies.

Fri 9 OctMachine LearningArtificial Intelligence
The gist
When multiple agents work together, their actions must meet shared safety rules, but it's hard to tell which agent causes a problem. The authors introduce SafeDiSTL, a method that figures out each agent’s role in joint safety issues by measuring how sensitive these safety violations are to their actions. Using a logical way to track safety over time, it breaks down joint problems into individual contributions. This helps train teams to avoid unsafe actions while working well together in tasks like carrying loads or controlling traffic.
Open → 2610.13737v1

Traffic signal system restores reliable data after sensor attacks and failures

MDRC: A Deployable State-Recovery Defense for Traffic Signal Control under Sensor Corruption

Abstract: Traffic Signal Control (TSC) is a safety-critical cyber-physical system that relies on real-time sensing. Corrupted observations caused by adversarial perturbations or sensor failures can propagate from the sensing layer into the controller and degrade traffic efficiency. Existing robust Reinforcement Learning (RL)-based TSC methods often suffer from limited cross-city generalization, high inference latency, and weak recovery under partial observability. We present MDRC (Meta-Diffusion-based framework for Resilient traffic signal Control against adversarial attacks and sensor failures), a post-detection state-recovery defense inserted between sensing and control. MDRC reconstructs trustworthy traffic states before they are consumed by the controller. It combines Denoising Diffusion Implicit Models (DDIM) for efficient state recovery with Reptile meta-learning for a transferable initialization across cities. We provide an optimization-based view of the DDIM recovery dynamics and establish a recovery-error bound that separates score approximation, numerical discretization, and initialization mismatch. Across seven real-world-derived CityFlow benchmarks, MDRC reduces Average Travel Time by 6.77% under stochastic and policy-aware attacks and by 12.75% under structured sensor loss, while improving state-recovery fidelity. We further evaluate 3,600 seconds of real roadside measurements with 50% of detector channels disabled and integrate MDRC into a hardware-in-the-loop traffic-signal stack. Over a 9.16-hour run with 32,389 sensing/control cycles, the system achieves 99.79% decision availability, produces no out-of-plan recommendations, and requires approximately 38 ms of component-wise processing per one-second control interval.

Wed 23 SeptCryptography and Security
The gist
Traffic lights rely on sensors to control traffic flow safely and efficiently, but corrupt or faulty sensor data can cause delays or unsafe signals. The authors created a recovery method called MDRC that fixes bad data before it reaches the traffic controller, using a smart combination of AI techniques. This method works across different cities and conditions, improving traffic times even when some sensors fail or are attacked. They tested MDRC in simulations and real-world traffic systems, showing it runs quickly and keeps traffic signals reliable for long periods.
Open → 2609.27528v1