Effective education in radiotherapy plan quality review requires a robust, regularly updated set of examples and the flexibility to demonstrate multiple possible planning approaches and their consequences. However, the current clinic-based paradigm does not support these needs. To address this, we have developed "Virtual Dosimetrist" models that can both generate training examples of suboptimal treatment plans and then allow trainees to improve the plan quality through simple natural language prompts, as if communicating with a dosimetrist. The dose generation and modification process is accurate, rapid, and requires only modest resources. This work is the first to combine dose distribution prediction with natural language processing; providing a robust pipeline for both generating suboptimal training plans and allowing trainees to practice their critical plan review and improvement skills that addresses the challenges of the current clinic-based paradigm.

Uncrewed Aerial Vehicle (UAV) research faces challenges with safety, scalability, costs, and ecological impact when conducting hardware testing. High-fidelity simulators offer a vital solution by replicating real-world conditions to enable the development and evaluation of novel perception and control algorithms. However, the large number of available simulators poses a significant challenge for researchers to determine which simulator best suits their specific use-case, based on each simulator's limitations and customization readiness. This paper includes a systematic overview of 38 existing UAV simulators and presents a set of decision factors for their selection, aiming to enhance the efficiency and safety of research endeavors.

When deploying modern machine learning-enabled robotic systems in high-stakes applications, detecting distribution shift is critical. However, most existing methods for detecting distribution shift are not well-suited to robotics settings, where data often arrives in a streaming fashion and may be very high-dimensional. In this work, we present an online method for detecting distribution shift with guarantees on the false positive rate - i.e., when there is no distribution shift, our system is very unlikely (with probability $< \epsilon$) to falsely issue an alert; any alerts that are issued should therefore be heeded. Our method is specifically designed for efficient detection even with high dimensional data, and it empirically achieves up to 11x faster detection on realistic robotics settings compared to prior work while maintaining a low false negative rate in practice (whenever there is a distribution shift in our experiments, our method indeed emits an alert). We demonstrate our approach in both simulation and hardware for a visual servoing task, and show that our method indeed issues an alert before a failure occurs.

Artificial intelligence (AI) has enormous potential to improve Air Force pilot training by providing actionable feedback to pilot trainees on the quality of their maneuvers and enabling instructor-less flying familiarization for early-stage trainees in low-cost simulators. Historically, AI challenges consisting of data, problem descriptions, and example code have been critical to fueling AI breakthroughs. The Department of the Air Force-Massachusetts Institute of Technology AI Accelerator (DAF-MIT AI Accelerator) developed such an AI challenge using real-world Air Force flight simulator data. The Maneuver ID challenge assembled thousands of virtual reality simulator flight recordings collected by actual Air Force student pilots at Pilot Training Next (PTN). This dataset has been publicly released at Maneuver-ID.mit.edu and represents the first of its kind public release of USAF flight training data. Using this dataset, we have applied a variety of AI methods to separate "good" vs "bad" simulator data and categorize and characterize maneuvers. These data, algorithms, and software are being released as baselines of model performance for others to build upon to enable the AI ecosystem for flight simulator training.

We propose an AI-based pilot trainer to help students learn how to fly aircraft. First, an AI agent uses behavioral cloning to learn flying maneuvers from qualified flight instructors. Later, the system uses the agent's decisions to detect errors made by students and provide feedback to help students correct their errors. This paper presents an instantiation of the pilot trainer. We focus on teaching straight and level flying maneuvers by automatically providing formative feedback to the human student.

More than two excruciatingly long years after the RTX 30-series reveal, a new generation of graphics cards is finally here. Nvidia CEO Jensen Huang unveiled the hotly anticipated GeForce RTX 4090 and not one, but two different RTX 4080 variants during the "Project Beyond" reveal event that kicked off GTC 2022. These graphics cards look absolutely monstrous, full stop, with the RTX 4090 leaving the RTX 3090 Ti stumbling in its wake. But while the performance of these next-gen GeForce GPUs promises to melt your face, the raw speeds are far from the only interesting aspect of this launch. Here are seven must-know facts from the RTX 4090 and RTX 4080 reveal, from ray tracing advancements to staggeringly high new sticker prices for Nvidia's GPUs. Nvidia clearly designed its new "Ada Lovelace" architecture to scream through ray tracing tasks.

With Azure Cognitive Services for Speech, customers can build voice-enabled apps confidently and quickly with the Speech SDK. We make it easy for customers to transcribe speech to text (STT) with high accuracy, produce natural-sounding text-to-speech (TTS) voices, and translate spoken audio. In the past few years, we have been inspired by the innovations coming out of the gaming industry, specific to AI. AI in gaming allows for flexible and reactive video game experiences. As technology continues to change and evolve, AI innovation has led to pioneering and tremendous advances in the gaming industry. Game dialogue prototyping with text to speech: Shorten the amount of time and money spent on the product to get the game to market sooner.

A team of researchers at Carnegie Mellon University believe they have developed the first AI pilot that enables autonomous aircraft to navigate a crowded airspace. The artificial intelligence can safely avoid collisions, predict the intent of other aircraft, track aircraft and coordinate with their actions, and communicate over the radio with pilots and air traffic controllers. The researchers aim to develop the AI so the behaviors of their system will be indistinguishable from those of a human pilot. "We believe we could eventually pass the Turing Test," said Jean Oh, an associate research professor at CMU's Robotics Institute (RI) and a member of the AI pilot team, referring to the test of an AI's ability to exhibit intelligent behavior equivalent to a human. To interact with other aircraft as a human pilot would, the AI uses both vision and natural language to communicate its intent with other aircraft, whether piloted or not.

AI algorithms that identify maneuvers from trajectory data could play an important role in improving flight safety and pilot training. AI challenges allow diverse teams to work together to solve hard problems and are an effective tool for developing AI solutions. AI challenges are also a key driver of AI computational requirements. The Maneuver Identification Challenge hosted at maneuver-id.mit.edu provides thousands of trajectories collected from pilots practicing in flight simulators, descriptions of maneuvers, and examples of these maneuvers performed by experienced pilots. Each trajectory consists of positions, velocities, and aircraft orientations normalized to a common coordinate system. Construction of the data set required significant data architecture to transform flight simulator logs into AI ready data, which included using a supercomputer for deduplication and data conditioning. There are three proposed challenges. The first challenge is separating physically plausible (good) trajectories from unfeasible (bad) trajectories. Human labeled good and bad trajectories are provided to aid in this task. Subsequent challenges are to label trajectories with their intended maneuvers and to assess the quality of those maneuvers.

Microsoft Flight Simulator is one of the most demanding video games ever made. Microsoft Flight Simulator on consoles both rides the clouds and is powered by them. Today the company confirmed that Flight Simulator's console release is driven in part by Microsoft's potent Azure servers, which can stream the massive 2.5 petabytes of Flight Sim data from the servers directly to console hardware. "The Series X is a super-powerful console and we're also using the Microsoft tech stack in an interesting way. Microsoft Flight Simulator releases on Xbox Series X/S consoles on July 27, 2021. Microsoft Flight Simulator is one of the most demanding video games ever made. Microsoft Flight Simulator on consoles both rides the clouds and is powered by them. Today the company confirmed that Flight Simulator's console release is driven in part by Microsoft's potent Azure servers, which can stream the massive 2.5 petabytes of Flight Sim data from the servers directly to console hardware. "The Series X is a super-powerful console and we're also using the Microsoft tech stack in an interesting way.