The electrification and automation of mobility are reshaping how cities operate on-demand transport systems. Managing Electric Autonomous Mobility-on-Demand (EAMoD) fleets effectively requires coordinating dispatch, rebalancing, and charging decisions under multiple uncertainties, including travel demand, travel time, energy consumption, and charger availability. We address this challenge with a combined stochastic and robust model predictive control (MPC) framework. The framework integrates spatio-temporal Bayesian neural network forecasts with a multi-stage stochastic optimization model, formulated as a large-scale mixed-integer linear program. To ensure real-time applicability, we develop a tailored Nested Benders Decomposition that exploits the scenario tree structure and enables efficient parallelized solution. Stochastic optimization is employed to anticipate demand and infrastructure variability, while robust constraints on energy consumption and travel times safeguard feasibility under worst-case realizations. We evaluate the framework using high-fidelity simulations of San Francisco and Chicago. Compared with deterministic, reactive, and robust baselines, the combined stochastic and robust approach reduces median passenger waiting times by up to 36% and 95th-percentile delays by nearly 20%, while also lowering rebalancing distance by 27% and electricity costs by close to 35%. We also conduct a sensitivity analysis of battery size and vehicle efficiency, finding that energy-efficient vehicles maintain stable performance even with small batteries, whereas less efficient vehicles require larger batteries and greater infrastructure support. Our results emphasize the importance of jointly optimizing predictive control, vehicle capabilities, and infrastructure planning to enable scalable, cost-efficient EAMoD operations.
Large Language Models (LLMs) are increasingly applied to software engineering (SE), yet their potential for autonomous, role-oriented collaboration remains largely underexplored. Understanding how multiple LLM-based agents coordinate, maintain role alignment, and converge on solutions is critical for SE, as naively allowing agents to interact does not reliably lead to correct or stable outcomes. Recent empirical studies show that unstructured or poorly understood interaction dynamics can result in error propagation, premature consensus on incorrect solutions, or prolonged disagreement that prevents convergence, even when correct partial solutions are present early in the interaction. As an initial step towards addressing this underexplored area, we undertake a systematic analysis of conversations between two agents, a Designer and a Programmer across 12 model combinations from 7 open-source LLMs (Gemma 2, Gemma 3, LLaMA 3.2, LLaMA 3.3, DeepSeek-R1, MiniCPM, and Qwen3). Our systematic approach reveals three key dimensions of multi-agent interaction: efficiency (the speed and stability of convergence), consistency (the degree of role alignment visualized by BLEU and ROUGE), and effectiveness (the extent of compilation success and error resolution). Results show that the DeepSeek-R1:DeepSeek-R1 pair was unique in converging to the correct solution from the very first iteration and sustaining it consistently to the final iteration, while LLaMA 3.2:LLaMA 3.2 and Qwen3:Qwen3 demonstrated strong Designer:Programmer role alignment despite of diverging from the correct solution. The other pairs deviated from the task, never to converge to a result. These findings advance understanding of agentic programming and highlight the need for further research on understanding and calibrating convergence and stop conditions essential for future autonomous SE.
Autonomous driving systems (ADS) are increasingly deployed in real traffic, yet testing remains fundamentally challenging due to open environments, complex scenarios, and the lack of established processes and metrics. Despite extensive research, a gap persists between academic advances and their applicability in industrial practice. To address this, we conduct an interactive rapid review in collaboration with 21 practitioners from a leading automotive company. Practitioners identified 12 key challenges in ADS testing, and prioritised two as the most critical issues, namely approaches to and completeness of testing for End-to-End (E2E) ADS. We analyzed 17 research studies relevant to these two challenges, most of which focus on generating critical testing scenarios, and subsequently assessed their relevance and applicability in practice. Our study provides the first practitioner-driven review and evaluation of current ADS testing research, reveals practical challenges in ADS testing, offers rapid insights for practitioners, and highlights the need for more context-aware, industry-relevant solutions to bridge the gap between research and practice.
Anticipating the behavior of other road users is critical for safe driving. To anticipate the behavior of other road users in a timely manner, it is essential to recognize their intentions. Although artificial intelligence (AI)-based intention recognition systems for traffic scenarios have advanced significantly, their performance relative to human road user intention recognition (RUIR) remains largely unexplored. To address this gap, we conducted an experiment comparing the RUIR performance of human participants and a state-of-the-art end-to-end video recognition AI model on a set of 25 video scenarios. The selected scenarios offered a balanced representation of various road user types and a range of intention maneuvers. Among human participants (N=161), we found no statistically significant differences in RUIR performance with respect to age, self-perceived driving skill, annual driven kilometers, or years of driving experience. However, the average human participant exhibited slightly lower RUIR performance than the AI models.
This research paper presents Volvo SmartCell, an AC battery technology that integrates modular multilevel converters and battery cells to form a unified system for electric vehicle propulsion and power supply. The research work addresses the broader challenge of reducing driveline cost and complexity by replacing traditional components such as inverters, onboard chargers, centralized DC/DC converters, vehicle control units and many more. SmartCell uses distributed Cluster Boards comprised of H-bridges which are controlled via wireless communication to generate AC voltage, deliver redundant low voltage power, and support cell level protection mechanisms. The prototype testing demonstrates that the system can supply traction power by engaging clusters according to the required voltage depending on motor speed, achieve AC grid charging by synthesizing sinusoidal voltages without a dedicated charger, and provide autonomous DC/DC operation through cluster level voltage regulation. Simulations further indicate that multilevel voltage generation can reduce switching losses and improve electric machine efficiency compared to conventional systems. Additional benefits include active cell balancing, support for mixed cell chemistries, and high redundancy through multiple independent power branches. Challenges remain in wireless bandwidth limitations and cost optimization of Cluster Boards. Ongoing development aims to enhance communication robustness and validate safety for non-isolated grid charging.
