arXiv subjects

Alexandre M. Bayen

Publications and source records attributed to Alexandre M. Bayen.

At least 19 recordsLinked to original sources

arXiv2026

Online Hamilton-Jacobi Reachability Onboard the Robot Control Loop: A Real-Time GPU Solver for Safety-Critical Autonomy

Hamilton-Jacobi (HJ) reachability provides certified backward reachable tubes (BRTs) for safety-critical robotic systems, but the level-set computation scales exponentially in the state dimension and has historically been performed offline. As autonomy stacks (ADAS/AV, humanoid robotics, and vision-language-action models) increasingly rely on black-box, probabilistic policies, a deterministic safety layer with formal guarantees is an essential complement. We present a CUDA implementation of the canonical WENO5 + TVD-RK3 + Lax-Friedrichs level-set Hamilton-Jacobi-Isaacs solver for 2D, 3D, and 4D dynamics that is fast enough to run inside a robot's control loop. In 32-bit floating point (FP32) on a single workstation GPU (NVIDIA RTX 4000 Ada), it computes the 3D Air3D BRT at 112 Hz, a 4D pursuit-evasion BRT at 61 Hz, and a 2D wind-affected drifter BRT at 74-147 Hz, 5.9-17.5x faster than the JAX reference hj_reachability at matched precision and 1.7-16x faster than a torch.compile reimplementation of the same scheme. In 64-bit floating point (FP64) it agrees with hj_reachability on eight benchmark cases, reproduces Mitchell's Air3D BRT to within 0.04% of the reference cell count, and runs 2.0-4.6x faster. On an embedded NVIDIA Jetson AGX Thor it computes Air3D at 66 Hz (N=41) and the 2D drifter at 54 Hz, 3.8-8.9x faster than hj_reachability on the same device. As a multi-agent application, an in-kernel label-propagation extension recovers the K-agent capture-basin Voronoi tessellation from a single combined HJ solve, independent of fleet size; it runs at 4.0 ms per tick in a closed-loop wildfire-response simulation of six quadcopters under time-varying, non-uniform wind.

cs.RO↗

arXiv2026

Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning

When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty should be allocated across agents. Uniform penalties ignore heterogeneity in the rewards agents sacrifice, while agent-specific multipliers may still rely on the same aggregate cost signal. We introduce Lagrangian Responsibility Allocation (LiRA), which learns each agent's share of a common multiplier by optimizing social welfare over a finite training horizon. The multiplier enforces the aggregate budget, while responsibility shares redistribute its influence without modifying the original rewards or constraints. For convex games under standard regularity conditions, varying these shares induces a smooth family of normalized generalized Nash equilibria in which active constraints remain at their budgets while welfare varies. To optimize responsibility before convergence, we derive a welfare gradient that accounts for both learning updates and the induced change in data distribution. Across CityLearn, MABIM, Harvest, and MetaDrive, spanning 3 to 400 agents, LiRA improves average social welfare by up to 29% over uniform and agent-specific multiplier baselines. Grid and driving costs remain within budget, inventory violations decrease, and Harvest makes more effective use of available budget.

cs.LG↗

arXiv2026

Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI

Unattended interactive autonomy - machines that step into danger in place of humans and complete tasks with human tools - remains a missing capability in mission-critical operations. These domains offer scarce training data and only onboard compute, yet deployed systems must face novelty without erasing prior competence. We introduce Continual Field-Adaptive Models (CFAMs), which learn efficiently in the lab and continue learning after deployment through autonomous, gradient-free, on-device updates. CFAM uses a complementary learning architecture with a frozen slow-learning component and a fast-learning Capsule Field. The slow component contains three cortices: Sensor, which maps multimodal input into 3D-grounded geometry; Reasoning, which decomposes tasks into skills and evaluates outcomes; and Action, which executes geometric skills. The Capsule Field stores field learning one-shot and gradient-free as Competence Capsules. Skill installation is few-shot in the lab and continual in the field; open-world novelty is outside scope. We evaluate CFAM across five embodiments: manipulator, quadruped, humanoid, quadrotor, and off-road vehicle. Baselines (pi0, CogACT, SpatialVLA) use the same in-house multi-embodiment dataset for physical-platform comparisons. CFAM reaches the operating point of a standard policy trained on the full prior-training dataset using 40% of the data, or 2.5x fewer trajectories. At test time, autonomous capture of verified near-OOD cases improves action success by 13.9 percentage points. In sequential simulation, backward transfer is -0.5 percentage points versus -11.4 for LoRA. CFAM therefore provides a bounded form of post-deployment physical intelligence: few-shot skill learning, autonomous field growth from verified near-OOD experience, and retention of prior competence.

cs.RO↗

arXiv2026

FlowATC: Aircraft Trajectory Prediction via Flow Matching

Building accurate decision-support tools for next-generation air traffic control requires robust trajectory prediction models. We present a flow-matching architecture trained exclusively on historical aircraft trajectories, with no route labels or chart supervision. Trained on 1.15 million Automatic Dependent Surveillance-Broadcast trajectory windows collected over the San Francisco Bay Area, the model generates aircraft trajectory distributions that closely match historical traffic, reproducing known airspace structure around San Francisco Airport such as the shape of SFO's published NIITE FOUR departure procedure. Our model is trained directly on the native, irregular ADS-B sampling interval. Trajectory prediction is cast as sequence inpainting using a block-causal Transformer that denoises future state tokens conditioned on the observed history using Conditional Flow Matching or Denoising Diffusion Probabilistic Models. We compare our architecture against constant-velocity, deterministic-Long Short Term Memory, and Conditional Variational Autoencoders baselines. At matched parameter count, CFM outperforms DDPM by 11-26% in minADE@20, and both generative objectives surpass the CVAE baseline by 31-41%. We further show that the error degrades gracefully with prediction horizon, and the architecture remains effective when retrained on temporally decimated feeds. Lastly, we sample $K$ independent completions, yielding spatial probabilistic occupancy estimates that can serve as input to downstream conflict-risk estimation.

cs.LG↗

arXiv2026

Learning to Recommend in Unknown Games

We study preference learning through recommendations in multi-agent game settings, where a moderator repeatedly interacts with agents whose utility functions are unknown. In each round, the moderator issues action recommendations and observes whether agents follow or deviate from them. We consider two canonical behavioral feedback models-best response and quantal response-and study how the information revealed by each model affects the learnability of agents' utilities. We show that under quantal-response feedback the game is learnable, up to a positive affine equivalence class, with logarithmic sample complexity in the desired precision, whereas best-response feedback can only identify a larger set of agents' utilities. We give a complete geometric characterization of this set. Moreover, we introduce a regret notion based on agents' incentives to deviate from recommendations and design an online algorithm with low regret under both feedback models, with bounds scaling linearly in the game dimension and logarithmically in time. Our results lay a theoretical foundation for AI recommendation systems in strategic multi-agent environments, where recommendation compliances are shaped by strategic interaction.

cs.GT↗

arXiv2026

Average Unfairness in Routing Games

We propose average unfairness as a new measure of fairness in routing games, defined as the ratio between the average latency and the minimum latency experienced by users. This measure is a natural complement to two existing unfairness notions: loaded unfairness, which compares maximum and minimum latencies of routes with positive flow, and user equilibrium (UE) unfairness, which compares maximum latency with the latency of a Nash equilibrium. We show that the worst-case values of all three unfairness measures coincide and are characterized by a steepness parameter intrinsic to the latency function class. We show that average unfairness is always no greater than loaded unfairness, and the two measures are equal only when the flow is fully fair. Besides that, we offer a complete comparison of the three unfairness measures, which, to the best of our knowledge, is the first theoretical analysis in this direction. Finally, we study the constrained system optimum (CSO) problem, where one seeks to minimize total latency subject to an upper bound on unfairness. We prove that, for the same tolerance level, the optimal flow under an average unfairness constraint achieves lower total latency than any flow satisfying a loaded unfairness constraint. We show that such improvement is always strict in parallel-link networks and establish sufficient conditions for general networks. We further illustrate the latter with numerical examples. Our results provide theoretical guarantees and valuable insights for evaluating fairness-efficiency tradeoffs in network routing.

cs.MA↗

arXiv2026

Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs

We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a trainable neural network while preserving the conservative structure of the scheme. The model can be trained both in a supervised setting with efficiently generated synthetic data or in an unsupervised manner, leveraging the weak formulation of the partial differential equation. We provide theoretical results that our model can perform arbitrarily well, and provide associated upper bounds on neural network size. Extensive experiments demonstrate that our method often outperforms efficient schemes such as Godunov's scheme, WENO, and Discontinuous Galerkin for comparable computational budgets. Finally, we demonstrate the effectiveness of our method on a traffic prediction task, leveraging field experimental highway data from the Berkeley DeepDrive drone dataset.

math.NA↗

arXiv2025

Optimal Control of ODE Car-Following Models: Applications to Mixed-Autonomy Platoon Control via Coupled Autonomous Vehicles

In this paper, we study the optimal control of a mixed-autonomy platoon driving on a single lane to smooth traffic flow. The platoon consists of autonomous vehicles, whose acceleration is controlled, and human-driven vehicles, whose behavior is described using a microscopic car-following model. We formulate the optimal control problem where the dynamics of the platoon are describing through a system of non-linear ODEs, with explicit constraints on both the state and the control variables. Theoretically, we analyze the well-posedness of the system dynamics under a reasonable set of admissible controls and establish the existence of minimizers for the optimal control problem. To solve the problem numerically, we propose a gradient descent-based algorithm that leverages the adjoint method, along with a penalty approach to handle state constraints. We demonstrate the effectiveness of the proposed numerical scheme through several experiments, exploring various scenarios with different penetration rates and distributions of controlled vehicles within the platoon.

math.OC↗

arXiv2025

(U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs

We introduce (U)NFV, a modular neural network architecture that generalizes classical finite volume (FV) methods for solving hyperbolic conservation laws. Hyperbolic partial differential equations (PDEs) are challenging to solve, particularly conservation laws whose physically relevant solutions contain shocks and discontinuities. FV methods are widely used for their mathematical properties: convergence to entropy solutions, flow conservation, or total variation diminishing, but often lack accuracy and flexibility in complex settings. Neural Finite Volume addresses these limitations by learning update rules over extended spatial and temporal stencils while preserving conservation structure. It supports both supervised training on solution data (NFV) and unsupervised training via weak-form residual loss (UNFV). Applied to first-order conservation laws, (U)NFV achieves up to 10x lower error than Godunov's method, outperforms ENO/WENO, and rivals discontinuous Galerkin solvers with far less complexity. On traffic modeling problems, both from PDEs and from experimental highway data, (U)NFV captures nonlinear wave dynamics with significantly higher fidelity and scalability than traditional FV approaches.

cs.LG↗

arXiv2025

Pareto Control Barrier Function for Inner Safe Set Maximization Under Input Constraints

This article introduces the Pareto Control Barrier Function (PCBF) algorithm to maximize the inner safe set of dynamical systems under input constraints. Traditional Control Barrier Functions (CBFs) ensure safety by maintaining system trajectories within a safe set but often fail to account for realistic input constraints. To address this problem, we leverage the Pareto multi-task learning framework to balance competing objectives of safety and safe set volume. The PCBF algorithm is applicable to high-dimensional systems and is computationally efficient. We validate its effectiveness through comparison with Hamilton-Jacobi reachability for an inverted pendulum and through simulations on a 12-dimensional quadrotor system. Results show that the PCBF consistently outperforms existing methods, yielding larger safe sets and ensuring safety under input constraints.

math.OC↗

arXiv2024

Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test

In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the results in both simulation and deployment, discussing the flow-smoothing benefits of the RL controller. From understanding the basics of Markov decision processes to exploring advanced techniques such as deep RL, our article offers a comprehensive overview and deep dive of the theoretical foundations and practical implementations driving this rapidly evolving field. We also showcase real-world case studies and alternative research projects that highlight the impact of RL controllers in revolutionizing autonomous driving. From tackling complex urban environments to dealing with unpredictable traffic scenarios, these intelligent controllers are pushing the boundaries of what automated vehicles can achieve. Furthermore, we examine the safety considerations and hardware-focused technical details surrounding deployment of RL controllers into automated vehicles. As these algorithms learn and evolve through interactions with the environment, ensuring their behavior aligns with safety standards becomes crucial. We explore the methodologies and frameworks being developed to address these challenges, emphasizing the importance of building reliable control systems for automated vehicles.

eess.SY↗

arXiv2024

Designing, simulating, and performing the 100-AV field test for the CIRCLES consortium: Methodology and Implementation of the Largest mobile traffic control experiment to date

Previous controlled experiments on single-lane ring roads have shown that a single partially autonomous vehicle (AV) can effectively mitigate traffic waves. This naturally prompts the question of how these findings can be generalized to field operational, high-density traffic conditions. To address this question, the Congestion Impacts Reduction via CAV-in-the-loop Lagrangian Energy Smoothing (CIRCLES) Consortium conducted MegaVanderTest (MVT), a live traffic control experiment involving 100 vehicles near Nashville, TN, USA. This article is a tutorial for developing analytical and simulation-based tools essential for designing and executing a live traffic control experiment like the MVT. It presents an overview of the proposed roadmap and various procedures used in designing, monitoring, and conducting the MVT, which is the largest mobile traffic control experiment at the time. The design process is aimed at evaluating the impact of the CIRCLES AVs on surrounding traffic. The article discusses the agent-based traffic simulation framework created for this evaluation. A novel methodological framework is introduced to calibrate this microsimulation, aiming to accurately capture traffic dynamics and assess the impact of adding 100 vehicles to existing traffic. The calibration model's effectiveness is verified using data from a six-mile section of Nashville's I-24 highway. The results indicate that the proposed model establishes an effective feedback loop between the optimizer and the simulator, thereby calibrating flow and speed with different spatiotemporal characteristics to minimize the error between simulated and real-world data. Finally, We simulate AVs in multiple scenarios to assess their effect on traffic congestion. This evaluation validates the AV routes, thereby contributing to the execution of a safe and successful live traffic control experiment via AVs.

eess.SY↗

arXiv2024

Hierarchical Speed Planner for Automated Vehicles: A Framework for Lagrangian Variable Speed Limit in Mixed Autonomy Traffic

This paper introduces a novel control framework for Lagrangian variable speed limits in hybrid traffic flow environments utilizing automated vehicles (AVs). The framework was validated using a fleet of 100 connected automated vehicles as part of the largest coordinated open-road test designed to smooth traffic flow. The framework includes two main components: a high-level controller deployed on the server side, named Speed Planner, and low-level controllers called vehicle controllers deployed on the vehicle side. The Speed Planner designs and updates target speeds for the vehicle controllers based on real-time Traffic State Estimation (TSE) [1]. The Speed Planner comprises two modules: a TSE enhancement module and a target speed design module. The TSE enhancement module is designed to minimize the effects of inherent latency in the received traffic information and to improve the spatial and temporal resolution of the input traffic data. The target speed design module generates target speed profiles with the goal of improving traffic flow. The vehicle controllers are designed to track the target speed meanwhile responding to the surrounding situation. The numerical simulation indicates the performance of the proposed method: the bottleneck throughput has increased by 5.01%, and the speed standard deviation has been reduced by a significant 34.36%. We further showcase an operational study with a description of how the controller was implemented on a field-test with 100 AVs and its comprehensive effects on the traffic flow.

eess.SY↗

arXiv2024

Traffic Control via Connected and Automated Vehicles: An Open-Road Field Experiment with 100 CAVs

The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. These "phantom jams" or "stop-and-go waves,"are a significant source of wasted energy. Toward this goal, the CIRCLES project designed a control system referred to as the MegaController by the CIRCLES team, that could be deployed in real traffic. Our field experiment leveraged a heterogeneous fleet of 100 longitudinally-controlled vehicles as Lagrangian traffic actuators, each of which ran a controller with the architecture described in this paper. The MegaController is a hierarchical control architecture, which consists of two main layers. The upper layer is called Speed Planner, and is a centralized optimal control algorithm. It assigns speed targets to the vehicles, conveyed through the LTE cellular network. The lower layer is a control layer, running on each vehicle. It performs local actuation by overriding the stock adaptive cruise controller, using the stock on-board sensors. The Speed Planner ingests live data feeds provided by third parties, as well as data from our own control vehicles, and uses both to perform the speed assignment. The architecture of the speed planner allows for modular use of standard control techniques, such as optimal control, model predictive control, kernel methods and others, including Deep RL, model predictive control and explicit controllers. Depending on the vehicle architecture, all onboard sensing data can be accessed by the local controllers, or only some. Control inputs vary across different automakers, with inputs ranging from torque or acceleration requests for some cars, and electronic selection of ACC set points in others. The proposed architecture allows for the combination of all possible settings proposed above. Most configurations were tested throughout the ramp up to the MegaVandertest.

eess.SY↗

arXiv2024

Traffic Smoothing Controllers for Autonomous Vehicles Using Deep Reinforcement Learning and Real-World Trajectory Data

Designing traffic-smoothing cruise controllers that can be deployed onto autonomous vehicles is a key step towards improving traffic flow, reducing congestion, and enhancing fuel efficiency in mixed autonomy traffic. We bypass the common issue of having to carefully fine-tune a large traffic microsimulator by leveraging real-world trajectory data from the I-24 highway in Tennessee, replayed in a one-lane simulation. Using standard deep reinforcement learning methods, we train energy-reducing wave-smoothing policies. As an input to the agent, we observe the speed and distance of only the vehicle in front, which are local states readily available on most recent vehicles, as well as non-local observations about the downstream state of the traffic. We show that at a low 4% autonomous vehicle penetration rate, we achieve significant fuel savings of over 15% on trajectories exhibiting many stop-and-go waves. Finally, we analyze the smoothing effect of the controllers and demonstrate robustness to adding lane-changing into the simulation as well as the removal of downstream information.

eess.SY↗

arXiv2023

Traffic smoothing using explicit local controllers

The dissipation of stop-and-go waves attracted recent attention as a traffic management problem, which can be efficiently addressed by automated driving. As part of the 100 automated vehicles experiment named MegaVanderTest, feedback controls were used to induce strong dissipation via velocity smoothing. More precisely, a single vehicle driving differently in one of the four lanes of I-24 in the Nashville area was able to regularize the velocity profile by reducing oscillations in time and velocity differences among vehicles. Quantitative measures of this effect were possible due to the innovative I-24 MOTION system capable of monitoring the traffic conditions for all vehicles on the roadway. This paper presents the control design, the technological aspects involved in its deployment, and, finally, the results achieved by the experiment.

eess.SY↗

arXiv2023

Reducing Detailed Vehicle Energy Dynamics to Physics-Like Models

The energy demand of vehicles, particularly in unsteady drive cycles, is affected by complex dynamics internal to the engine and other powertrain components. Yet, in many applications, particularly macroscopic traffic flow modeling and optimization, structurally simple approximations to the complex vehicle dynamics are needed that nevertheless reproduce the correct effective energy behavior. This work presents a systematic model reduction pipeline that starts from complex vehicle models based on the Autonomie software and derives a hierarchy of simplified models that are fast to evaluate, easy to disseminate in open-source frameworks, and compatible with optimization frameworks. The pipeline, based on a virtual chassis dynamometer and subsequent approximation strategies, is reproducible and is applied to six different vehicle classes to produce concrete explicit energy models that represent an average vehicle in each class and leverage the accuracy and validation work of the Autonomie software.

eess.SY↗

arXiv2023

Cooperative Driving for Speed Harmonization in Mixed-Traffic Environments

Autonomous driving systems present promising methods for congestion mitigation in mixed autonomy traffic control settings. In particular, when coupled with even modest traffic state estimates, such systems can plan and coordinate the behaviors of automated vehicles (AVs) in response to observed downstream events, thereby inhibiting the continued propagation of congestion. In this paper, we present a two-layer control strategy in which the upper layer proposes the desired speeds that predictively react to the downstream state of traffic, and the lower layer maintains safe and reasonable headways with leading vehicles. This method is demonstrated to achieve an average of over 15% energy savings within simulations of congested events observed in Interstate 24 with only 4% AV penetration, while restricting negative externalities imposed on traveling times and mobility. The proposed strategy that served as part of the "speed planner" was deployed on 100 AVs in a massive traffic experiment conducted on Nashville's I-24 in November 2022.

eess.SY↗