Uncontrolled intersections account for a significant fraction of roadway crashes due to ambiguous right-of-way rules, occlusions, and unpredictable driver behavior. While autonomous vehicle research has explored uncertainty-aware decision making, few systems exist to retrofit human-operated vehicles with assistive navigation support. We present a driver-assist framework for right-of-way reasoning at uncontrolled intersections, formulated as a Partially Observable Markov Decision Process (POMDP). Using a custom simulation testbed with stochastic traffic agents, pedestrians, occlusions, and adversarial scenarios, we evaluate four decision-making approaches: a deterministic finite state machine (FSM), and three probabilistic planners: QMDP, POMCP, and DESPOT. Results show that probabilistic planners outperform the rule-based baseline, achieving up to 97.5 percent collision-free navigation under partial observability, with POMCP prioritizing safety and DESPOT balancing efficiency and runtime feasibility. Our findings highlight the importance of uncertainty-aware planning for driver assistance and motivate future integration of sensor fusion and environment perception modules for real-time deployment in realistic traffic environments.

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for deployment and governance decisions. We investigate whether frontier language models can accurately classify transcripts based on whether they originate from evaluations or real-world deployment, a capability we call evaluation awareness. To achieve this, we construct a diverse benchmark of 1,000 prompts and transcripts from 61 distinct datasets. These span public benchmarks (e.g., MMLU, SWEBench), real-world deployment interactions, and agent trajectories from scaffolding frameworks (e.g., web-browsing agents). Frontier models clearly demonstrate above-random evaluation awareness (Gemini-2.5-Pro reaches an AUC of $0.83$), but do not yet surpass our simple human baseline (AUC of $0.92$). Furthermore, both AI models and humans are better at identifying evaluations in agentic settings compared to chat settings. Additionally, we test whether models can identify the purpose of the evaluation. Under multiple-choice and open-ended questioning, AI models far outperform random chance in identifying what an evaluation is testing for. Our results indicate that frontier models already exhibit a substantial, though not yet superhuman, level of evaluation-awareness. We recommend tracking this capability in future models.

Neuromorphic computing aims to replicate the brain's remarkable energy efficiency and parallel processing capabilities for large-scale artificial intelligence applications. In this work, we present a comprehensive comparative study of three spiking neuron circuit architectures-Leaky-Integrate-and-Fire (LIF), Morris-Lecar (ML), and Axon-Hillock (AH)-implemented in a 7 nm FinFET technology. Through extensive SPICE simulations, we explore the optimization of spiking frequency, energy per spike, and static power consumption. Our results show that the AH design achieves the highest throughput, demonstrating multi-gigahertz firing rates (up to 3 GHz) with attojoule energy costs. By contrast, the ML architecture excels in subthreshold to near-threshold regimes, offering robust low-power operation (as low as 0.385 aJ/spike) and biological bursting behavior. Although LIF benefits from a decoupled current mirror for high-frequency operation, it exhibits slightly higher static leakage compared to ML and AH at elevated supply voltages. Comparisons with previous node implementations (22 nm planar, 28 nm) reveal that 7 nm FinFETs can drastically boost energy efficiency and speed albeit at the cost of increased subthreshold leakage in deep subthreshold regions. By quantifying design trade-offs for each neuron architecture, our work provides a roadmap for optimizing spiking neuron circuits in advanced nanoscale technologies to deliver neuromorphic hardware capable of both ultra-low-power operation and high computational throughput.

Soft robot arms have made significant progress towards completing human-scale tasks, but designing arms for tasks with specific load and workspace requirements remains difficult. A key challenge is the lack of model-based design tools, forcing advancement to occur through empirical iteration and observation. Existing models are focused on control and rely on parameter fits, which means they cannot provide general conclusions about the mapping between design and performance or the influence of factors outside the fitting data. As a first step toward model-based design tools, we introduce a novel method of analyzing whether a proposed arm design can complete desired tasks. Our method is informative, interpretable, and fast; it provides novel metrics for quantifying a proposed arm design's ability to perform a task, it yields a graphical interpretation of performance through segment forces, and computing it is over 80x faster than optimization based methods. Our formulation focuses on antagonistic, pneumatically-driven soft arms. We demonstrate our approach through example analysis, and also through consideration of antagonistic vs non-antagonistic designs. Our method enables fast, direct and task-specific comparison of these two architectures, and provides a new visualization of the comparative mechanics. While only a first step, the proposed approach will support advancement of model-based design tools, leading to highly capable soft arms.

Non-local operations play a crucial role in computer vision enabling the capture of long-range dependencies through weighted sums of features across the input, surpassing the constraints of traditional convolution operations that focus solely on local neighborhoods. Non-local operations typically require computing pairwise relationships between all elements in a set, leading to quadratic complexity in terms of time and memory. Due to the high computational and memory demands, scaling non-local neural networks to large-scale problems can be challenging. This article introduces a hybrid quantum-classical scalable non-local neural network, referred to as Quantum Non-Local Neural Network (QNL-Net), to enhance pattern recognition. The proposed QNL-Net relies on inherent quantum parallelism to allow the simultaneous processing of a large number of input features enabling more efficient computations in quantum-enhanced feature space and involving pairwise relationships through quantum entanglement. We benchmark our proposed QNL-Net with other quantum counterparts to binary classification with datasets MNIST and CIFAR-10. The simulation findings showcase our QNL-Net achieves cutting-edge accuracy levels in binary image classification among quantum classifiers while utilizing fewer qubits.

Deployment of teams of aerial robots could enable large-scale filming of dynamic groups of people (actors) in complex environments for novel applications in areas such as team sports and cinematography. Toward this end, methods for submodular maximization via sequential greedy planning can be used for scalable optimization of camera views across teams of robots but face challenges with efficient coordination in cluttered environments. Obstacles can produce occlusions and increase chances of inter-robot collision which can violate requirements for near-optimality guarantees. To coordinate teams of aerial robots in filming groups of people in dense environments, a more general view-planning approach is required. We explore how collision and occlusion impact performance in filming applications through the development of a multi-robot multi-actor view planner with an occlusion-aware objective for filming groups of people and compare with a greedy formation planner. To evaluate performance, we plan in five test environments with complex multiple-actor behaviors. Compared with a formation planner, our sequential planner generates 14% greater view reward over the actors for three scenarios and comparable performance to formation planning on two others. We also observe near identical performance of sequential planning both with and without inter-robot collision constraints. Overall, we demonstrate effective coordination of teams of aerial robots for filming groups that may split, merge, or spread apart and in environments cluttered with obstacles that may cause collisions or occlusions.

Abstract-- We present a system for creating building-scale, easily navigable 3D maps using mainstream smartphones. In our approach, we formulate the 3D-mapping problem as an instance of Graph SLAM and infer the position of both building landmarks (fiducial markers) and navigable paths through the environment (phone poses). Our results demonstrate the system's ability to create accurate 3D maps. Three of the AprilTags used as fiducial markers by our mapping system. Indoor 3D mapping and navigation are of vital importance To combat the shortcomings of VIO, we use fiducial in a number of applications including autonomous mobile markers (or "tags") with planar patterns that can be readily robots which need to both accurately determine their position identified in a camera image.

Generating code from a natural language using Large Language Models (LLMs) such as ChatGPT, seems groundbreaking. Yet, with more extensive use, it's evident that this approach has its own limitations. The inherent ambiguity of natural language presents challenges for complex software designs. Accordingly, our research offers an Agile Model-Driven Development (MDD) approach that enhances code auto-generation using OpenAI's GPT-4. Our work emphasizes "Agility" as a significant contribution to the current MDD method, particularly when the model undergoes changes or needs deployment in a different programming language. Thus, we present a case-study showcasing a multi-agent simulation system of an Unmanned Vehicle Fleet. In the first and second layer of our approach, we constructed a textual representation of the case-study using Unified Model Language (UML) diagrams. In the next layer, we introduced two sets of constraints that minimize model ambiguity. Object Constraints Language (OCL) is applied to fine-tune the code constructions details, while FIPA ontology is used to shape communication semantics and protocols. Ultimately, leveraging GPT-4, our last layer auto-generates code in both Java and Python. The Java code is deployed within the JADE framework, while the Python code is deployed in PADE framework. Concluding our research, we engaged in a comprehensive evaluation of the generated code. From a behavioural standpoint, the auto-generated code aligned perfectly with the expected UML sequence diagram. Structurally, we compared the complexity of code derived from UML diagrams constrained solely by OCL to that influenced by both OCL and FIPA-ontology. Results indicate that ontology-constrained model produce inherently more intricate code, but it remains manageable and low-risk for further testing and maintenance.

Snake robots are characterized by their ability to navigate through small spaces and loose terrain by utilizing efficient cyclic forms of locomotion. Soft snake robots are a subset of these robots which utilize soft, compliant actuators to produce movement. Prior work on soft snake robots has primarily focused on planar gaits, such as undulation. More efficient spatial gaits, such as sidewinding, are unexplored gaits for soft snake robots. We propose a novel means of constructing a soft snake robot capable of sidewinding, and introduce the Helical Inflating Soft Snake Robot (HISSbot). We validate this actuation through the physical HISSbot, and demonstrate its ability to sidewind across various surfaces. Our tests show robustness in locomotion through low-friction and granular media.

NEEDHAM, Mass., March 7, 2023 – A new forecast from the International Data Corporation (IDC) Worldwide Artificial Intelligence Spending Guide shows that global spending on artificial intelligence (AI), including software, hardware, and services for AI-centric systems*, will reach $154 billion in 2023, an increase of 26.9% over the amount spent in 2022. The ongoing incorporation of AI into a wide range of products will result in a compound annual growth rate (CAGR) of 27.0% over the 2022-2026 forecast with spending on AI-centric systems expected to surpass $300 billion in 2026. "Companies that are slow to adopt AI will be left behind – large and small. AI is best used in these companies to augment human abilities, automate repetitive tasks, provide personalized recommendations, and make data-driven decisions with speed and accuracy," said Mike Glennon, senior market research analyst with IDC's Customer Insights & Analysis team. "Suppliers of AI technologies need to know which are the largest and fastest growing opportunities, but without data they become just another opinion. IDC's AI Spending Guide provides the foundation for marketing strategy through its comprehensive coverage of AI opportunities and gives a robust basis for a market focus that ties with companies' capabilities."