We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only on-board perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k observation-action pairs from an expert MPC with privileged state and dynamics information, randomized over dynamics parameters and spatial disturbances. We then distill this expert MPC into an end-to-end visuomotor policy with a lightweight neural architecture, called SV-Net. SV-Net processes color image, optical flow and IMU data streams into low-level body rate and thrust commands at 20Hz onboard a drone. Crucially, SV-Net includes a Rapid Motor Adaptation (RMA) module that adapts at runtime to variations in drone dynamics. In a campaign of 105 hardware experiments, we show SOUS VIDE policies to be robust to 30% mass variations, 40 m/s wind gusts, 60% changes in ambient brightness, shifting or removing objects from the scene, and people moving aggressively through the drone's visual field. Code, data, and experiment videos can be found on our project page: https://stanfordmsl.github.io/SousVide/.

Ranking passages by prompting a large language model (LLM) can achieve promising performance in modern information retrieval (IR) systems. A common approach is to sort the ranking list by prompting LLMs for pairwise comparison. However, sorting-based methods require consistent comparisons to correctly sort the passages, which we show that LLMs often violate. We identify two kinds of intrinsic inconsistency in LLM-based pairwise comparisons: order inconsistency which leads to conflicting results when switching the passage order, and transitive inconsistency which leads to non-transitive triads among all preference pairs. In this paper, we propose LLM-RankFusion, an LLM-based ranking framework that mitigates these inconsistencies and produces a robust ranking list. LLM-RankFusion mitigates order inconsistency using in-context learning (ICL) to demonstrate order-agnostic comparisons and calibration to estimate the underlying preference probability between two passages. We then address transitive inconsistency by aggregating the ranking results from multiple rankers. In our experiments, we empirically show that LLM-RankFusion can significantly reduce inconsistent pairwise comparison results, and improve the ranking quality by making the final ranking list more robust.

Amazon unofficially kicked things off on Prime Day last month, and now we're starting to see a number of early Black Friday deals pop up at other retailers. Walmart will actually have a couple of rounds of deals going live on its website and in its stores this month, and the first rolled out online tonight at 7pm ET. We sifted through the list and found the best tech deals you can get right now. This is a new all-time-low price for Apple's standard AirPods with wired charging case. The previous low came last month during Amazon Prime Day when these earbuds dropped to $115.

If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA TODAY's newsroom and any business incentives. I've always loved gadgets and gizmos, especially those that make my life better. And with Shark Tank and Kickstarter and things like that, it seems like you can't go more than a day without learning about some new amazing product to solve some problem or other. Over the years, I've taken chances on lots of snake oil-like products. Some have been complete garbage, like a third-party Alexa-enabled smart speaker that is painfully slow and sounds like crap.

Sharp's newest fridge freezer doesn't have a water fountain or a voice assistant. Instead it houses a vacuum-packing slot that will help keep produce fresh for longer, reduce food waste (leftovers!) and, yes, even prep food for that millennial cooking style of choice -- sous vide. The VacPac Pro fridge-freezer had its debut at IFA 2018, and doesn't require proprietary bags. You can use any sealer bag, and the slot will suck out the air at the touch of a button -- which we proceeded to do on some plastic fruit. The company believes the method can extend the longevity of meat and dairy by up to eight times, and a spokesperson confirmed that the sealed bags are ideal for sous vide-style preparation, ensuring perfect edge-to-edge cooking, retaining the juices, nutrients and other good things.