Vision-language-model (VLM)-guided reinforcement learning (RL) has recently attracted significant attention for it, replacing brittle hand-crafted rewards with semantically grounded signals; however, deploying such simulation-trained policies on real vehicles remains a fundamental challenge, because they rely on simulator-native observations and simulator-coupled action semantics with no counterpart on physical hardware. We identify a general principle: the simulation-to-reality gap decomposes into two largely orthogonal axes, a sensing-and-dynamics domain gap and a task-and-geometry gap, the former closable without real-world policy training by re-projecting real perception and control onto the policy's training manifold. We formalize this as a transfer guarantee that bounds the deployment gap by three independently controllable error terms, and instantiate it as Sim2Real-AD, which combines a Geometric Observation Bridge, a Physics-Aware Action Mapping, a Two-Phase Progressive Training curriculum, and a Real-time Deployment Pipeline. As a proof of concept, a CARLA-trained VLM-guided RL policy is transferred zero-shot to a full-scale battery-electric Ford E-Transit van in Madison, WI, USA, and drives across car-following, obstacle-avoidance, and stop-sign scenarios using no real-world training data. To our knowledge, this is among the first zero-shot closed-loop deployments of a CARLA-trained VLM-guided RL policy on a full-scale real vehicle, and the decomposition offers a principled, broadly applicable route for moving simulation-trained, foundation-model-guided policies into the physical world, supporting energy-efficient intelligent driving on electrified transportation platforms. The demo video, code, and model checkpoint are available at: https://zilin-huang.github.io/Sim2Real-AD-website/.
Ethereum marked the beginning of stateful and Turing-Complete blockchains, where the final result of transactions depends on their execution order. This subtle distinction is of great import, especially in Decentralized Finance (DeFi) applications like exchanges or lending platforms, where execution order plays a key role in making profits or losses and gives adversarial actors enormous incentives to manipulate or influence the ordering of transactions on blockchains. Maximal Extractable Value (MEV) represents the potential profit block producers can gain by manipulating transaction inclusion within a block they create. Other blockchain participants can also extract MEV, often through tactics such as front-running attacks. The MEV problem also affects Layer-2 (L2) networks, which are a subset of stateful chains created to improve scalability for Layer-1 (L1) chains like Ethereum. Prominent examples of L2 networks include rollups such as Arbitrum and Optimism. To mitigate the MEV problem, many rollups are characterized by a single sequencer that employs the First-Come-First-Served (FCFS) transaction ordering policy, which prevents greedy reordering based on the value extracted per transaction. While FCFS policy guarantees order fairness by processing transactions according to receive times, it has some drawbacks, such as encouraging spam transactions to ensure early inclusion in a block, and sequencer orderings favoring users with lower latency. To reduce the risks of the FCFS ordering algorithm, we propose a fair ordering mechanism by adding fairness granularity to the original FCFS policy. We then introduce a method to measure the granularity interval of the Arbitrum chain, using a statistical technique that can be adapted for use with other L2 chains. We evaluate our proposed ordering algorithm using a dataset based on Arbitrum network specifications and quantify the accuracy of our final ordering by measuring its proximity to the ideal ordering. Our results show a high accuracy with different network latencies and different datasets. We also assess the effectiveness of our approach for MEV mitigation by reducing front-running compared to FCFS.
The emergence of decentralized finance has transformed asset trading on the blockchain, making traditional financial instruments more accessible while also introducing a series of exploitative economic practices known as Maximal Extractable Value (MEV). Concurrently, decentralized finance has embraced rollup-based Layer-2 solutions to facilitate asset trading at reduced transaction costs compared to Layer-1 solutions such as Ethereum. However, rollups lack a public mempool like Ethereum, making the extraction of MEV more challenging. In this paper, we investigate the prevalence and impact of MEV on Ethereum and prominent rollups such as Arbitrum, Optimism, and zkSync over a nearly three-year period. Our analysis encompasses various metrics including volume, profits, costs, competition, and response time to MEV opportunities. We discover that MEV is widespread on rollups, with trading volume comparable to Ethereum. We also find that, although MEV costs are lower on rollups, profits are also significantly lower compared to Ethereum. Additionally, we examine the prevalence of sandwich attacks on rollups. While our findings did not detect any sandwiching activity on popular rollups, we did identify the potential for cross-layer sandwich attacks facilitated by transactions that are sent across rollups and Ethereum. Consequently, we propose and evaluate the feasibility of three novel attacks that exploit cross-layer transactions, revealing that attackers could have already earned approximately 2 million USD through cross-layer sandwich attacks.
In May 2022, an apparent speculative attack, followed by market panic, led to the precipitous downfall of UST, one of the most popular stablecoins at that time. However, UST is not the only stablecoin to have been depegged in the past. Designing resilient and long-term stable coins, therefore, appears to present a hard challenge. To further scrutinize existing stablecoin designs and ultimately lead to more robust systems, we need to understand where volatility emerges. Our work provides a game-theoretical model aiming to help identify why stablecoins suffer from a depeg. This game-theoretical model reveals that stablecoins have different price equilibria depending on the coin's architecture and mechanism to minimize volatility. Moreover, our theory is supported by extensive empirical data, spanning $1$ year. To that end, we collect daily prices for 22 stablecoins and on-chain data from five blockchains including the Ethereum and the Terra blockchain.
This brief addresses the robust lateral control problem for self-driving racecars. It proposes a discrete-time estimation and control solution consisting of a delayed unknown input-state observer (UIO) and a robust tracking controller. Based on a nominal vehicle model, describing its motion with respect to a generic desired trajectory and requiring no information about the surrounding environment, the observer reconstructs the total force disturbance signal, resulting from imperfect knowledge of the time-varying tire-road interface characteristics, presence of other vehicles nearby, wind gusts, and other model uncertainty. Then, the controller actively compensates the estimated force and asymptotically steers the tracking error to zero. The brief also presents a closed-loop stability proof of the method, ensuring perfect asymptotic estimation and tracking by the controlled vehicle. The proposed solution advantageously needs no a-priori information about the total disturbance boundedness, additional variables to model uncertainty, or observer parameters to be tuned. Its effectiveness and superiority to existing methods are studied in theory and shown in simulations where a full racecar model, based on the vehicle dynamics blockset, is required to track aggressive maneuvers. Through a faster and more accurate disturbance estimation, the solution robustly ensures better dynamic responses even with measurement noise.
Antonella Ferrara, Renato Librino, A. Massola, M. Miglietta · 5 authors
In the short term future, cybernetic transport systems (CTS), based on fully automated urban vehicles (the so-called Cybercars), will be seen on city roads and on new dedicated infrastructures. The objective of the Cybercars is to achieve a more effective organization of urban transport, resulting in a more rational use of motorized traffic, with less congestion and pollution and safer driving. One necessary functionality of Cybercars is the ability to cooperate and run in a platoon at close range. Platooning of these automatic guided cars is addressed in this paper, and decentralized control schemes for autonomous vehicle are proposed. Due to system uncertainties and the wide range of operating conditions, which are typical of the automotive context, a robust control technique is required to solve the problem. The robust control methodologies adopted in this paper are first order and second order sliding mode control, which result particularly suitable to deal with uncertain nonlinear time-varying systems. The proposed control schemes are compared through simulations.
Although ABS has been widely spread on the commercial market for twenty years, throughgoing investigations with rigorous theoretical background have been lacking in the automotive literature. The control strategies of commercial ABS are mostly based on table rules to be calibrated through various experiments and tests, and the system dynamics cannot be effectively considered in the controller design. Due to the challenges in the automobile industry it is desired to develop a technique which still enhances the control performance and robustness with respect to various vehicle types and environment conditions. Motivated by these goals, a robust adaptive control algorithm is developed in this work. The proof of asymptotic stability is based on the Lyapunov method. The objective of such control is to maximize the tire friction under the assumption of knowing the optimal value of target slip. It is shown that, without any prior knowledge of the tire force and system parameters, the slip error is bound to converge to zero asymptotically. The robustness of the control system with respect to variation of the system parameters is guaranteed. The brake dynamic system to be controlled includes mechanical motion equations and the hydraulic circuit equations. A two-level control scheme is applied for the controller design, which considers the both parts separately.