Most on-device sensor calibration studies benchmark models only against three macroscopic requirements (i.e., accuracy, real-time, and resource efficiency), thereby hiding deployment bottlenecks such as instantaneous error and worst-case latency. We therefore decompose this triad into eight microscopic requirements and introduce Scare (Sensor Calibration model balancing Accuracy, Real-time, and Efficiency), an ultra-compressed transformer that fulfills them all. SCARE comprises three core components: (1) Sequence Lens Projector (SLP) that logarithmically compresses time-series data while preserving boundary information across bins, (2) Efficient Bitwise Attention (EBA) module that replaces costly multiplications with bitwise operations via binary hash codes, and (3) Hash optimization strategy that ensures stable training without auxiliary loss terms. Together, these components minimize computational overhead while maintaining high accuracy and compatibility with microcontroller units (MCUs). Extensive experiments on large-scale air-quality datasets and real microcontroller deployments demonstrate that Scare outperforms existing linear, hybrid, and deep-learning baselines, making Scare, to the best of our knowledge, the first model to meet all eight microscopic requirements simultaneously.

In this interview series, we're meeting some of the AAAI/SIGAI Doctoral Consortium participants to find out more about their research. Ananya Joshi recently completed her PhD, where she developed a system that experts have used for the past two years to identify respiratory outbreaks (like COVID-19) in large-scale healthcare streams across the United States using her novel algorithms for ranking real-time events from large-scale time series data. In this interview, she tells us more about this project, how healthcare applications inspire basic AI research, and her future plans. When I started my PhD during the COVID-19 pandemic, there was an explosion in continuously-updated human health data. Still, it was difficult for people to figure out which data was important so that they could make decisions like increasing the number of hospital beds at the start of an outbreak or patching a serious data problem that would impact disease forecasting.

Underwater ROVs (Remotely Operated Vehicles) are unmanned submersible vehicles designed for exploring and operating in the depths of the ocean. Despite using high-end cameras, typical teleoperation engines based on first-person (egocentric) views limit a surface operator's ability to maneuver and navigate the ROV in complex deep-water missions. In this paper, we present an interactive teleoperation interface that (i) offers on-demand "third"-person (exocentric) visuals from past egocentric views, and (ii) facilitates enhanced peripheral information with augmented ROV pose in real-time. We achieve this by integrating a 3D geometry-based Ego-to-Exo view synthesis algorithm into a monocular SLAM system for accurate trajectory estimation. The proposed closed-form solution only uses past egocentric views from the ROV and a SLAM backbone for pose estimation, which makes it portable to existing ROV platforms. Unlike data-driven solutions, it is invariant to applications and waterbody-specific scenes. We validate the geometric accuracy of the proposed framework through extensive experiments of 2-DOF indoor navigation and 6-DOF underwater cave exploration in challenging low-light conditions. We demonstrate the benefits of dynamic Ego-to-Exo view generation and real-time pose rendering for remote ROV teleoperation by following navigation guides such as cavelines inside underwater caves. This new way of interactive ROV teleoperation opens up promising opportunities for future research in underwater telerobotics.

A key challenge to ensuring the rapid transition of robotic systems from the industrial sector to more ubiquitous applications is the development of algorithms that can guarantee safe operation while in close proximity to humans. Motion planning and control methods, for instance, must be able to certify safety while operating in real-time in arbitrary environments and in the presence of model uncertainty. This paper proposes Wrench Analysis for Inertial Transport using Reachability (WAITR), a certifiably safe motion planning and control framework for serial link manipulators that manipulate unsecured objects in arbitrary environments. WAITR uses reachability analysis to construct over-approximations of the contact wrench applied to unsecured objects, which captures uncertainty in the manipulator dynamics, the object dynamics, and contact parameters such as the coefficient of friction. An optimization problem formulation is presented that can be solved in real-time to generate provably-safe motions for manipulating the unsecured objects. This paper illustrates that WAITR outperforms state of the art methods in a variety of simulation experiments and demonstrates its performance in the real-world.

We present CaptAinGlove, a textile-based, low-power (1.15Watts), privacy-conscious, real-time on-the-edge (RTE) glove-based solution with a tiny memory footprint (2MB), designed to recognize hand gestures used for drone control. We employ lightweight convolutional neural networks as the backbone models and a hierarchical multimodal fusion to reduce power consumption and improve accuracy. The system yields an F1-score of 80% for the offline evaluation of nine classes; eight hand gesture commands and null activity. For the RTE, we obtained an F1-score of 67% (one user).

Midjourney AI is great for images, while Microsoft's ChatGPT for robotics could be a game changer for anyone interacting with robots. Instead of learning complex programming languages or details around robotic systems, ChatGPT can be used to provide high-level feedback to the large language model (LLM) while monitoring the robot's performance. ChatGPT can generate code for robotics scenarios in real-time, without having to fine-tune any settings. One can leverage the LLM's knowledge to control different robots form factors for a variety of tasks, including solving robotics puzzles, along with complex robot deployments in the manipulation, aerial, as well as navigation domains. Whether it be in Microsoft AirSim simulator or just manipulating objects, ChatGPT is able to perform the task with just a few prompts.

The Internet of Things (IoT) adds value to practically every industry, from manufacturing and logistics to retail and resource management. Drones, delivery vehicles, medical gadgets, security cameras, and construction equipment are among the linked "things" that the Internet of Things collects data from. While IoT sensors and devices collect a plethora of data, they also generate massive, difficult-to-manage, high-speed data streams that must be managed, analyzed, stored, and protected. IoT data is also perishable, and without the right tools, companies will miss out on the most valuable time-sensitive insights. This post will look at how real-time data analytics and IoT applications work together to open up new possibilities in various industries.

By 2050, the National Institute of Health (NIH) National Eye Institute estimates that 14.6 million Americans will have diabetic retinopathy. A new study published in The Lancet demonstrates how artificial intelligence (AI) machine learning can screen in real-time for diabetic retinopathy--a leading cause of preventable blindness, particularly in areas with low-income or middle-income economies. According to the Centers for Disease Control (CDC), one in four American adults with vision loss reported anxiety or depression. Moreover, vision loss has been linked to fear, anxiety, worry, social isolation, and loneliness. Scientists affiliated with Google Health and their collaborators applied artificial intelligence (AI) machine learning to detect one of the most common causes of preventable blindness--diabetic retinopathy.

Maker Kevin Lewis has created a Raspberry Pi-powered solution to understanding speech that's hard to hear or, in many cases today, muffled by a mask. He's created a wearable badge that features a small display that generates text from speech using AI to help with accuracy. According to Lewis, the transcription process is aided using DeepgramAI an API service which uses AI to transcribe your speech in real-time. The project is flexible in nature and could also serve as a tool for anyone hard of hearing. Lewis indicates the total cost for the project was around $81 (£60).

Implementing real time object detection using python PyTorch OpenCV. Using yolo to build real time object detection system in python. The course will teach you how to make your own classifier from only one positive image. The project is about the real time streaming, and detect objects in video games as well.