Lifeboat Foundation

In this video accompaniment to our paper “ChatGPT for Robotics: Design Principles and Model Abilities”, we demonstrate how ChatGPT can help a user control a real drone with only language instructions.

ChatGPT provided an extremely intuitive interface between the user and the robot, writing robot code based on ambiguous and ill-defined instructions, and asking clarification questions when necessary. The model was also able to write complex code structures for drone navigation (circular and lawnmower inspection) based solely on the prompt’s base APIs.

Ross Perot Jr. described the STEM education event as a “first-of-its-kind” across the country. The event comes days before Pres. Bush, Gov. Abbott, several Republican presidential candidates and executives from Amazon, Microsoft, Walmart and more gather at mobility summit.

An unnamed Ukrainian scientist has allegedly developed a new material that can mask heat signatures of troops and gear from Russian drones.

“Necessity is the mother of all inventions,” as the saying goes, and this saying has never been more accurate than when applied to wargear. The latest exemplar of this is a new “invisibility cloak” developed by a Ukrainian material scientist to help protect Ukrainians from Russian drones. As reported by inews.

Aurumarcus/iStock.

Continue reading “New Ukrainian nanotech ‘cloak’ can hide people from drones” »

Nearly three decades later, the Apache’s status as the world’s premier attack helicopter remains largely unchallenged.

Here’s What You Need to Remember: The latest AH-64E Guardian model boasts uprated engines, remote drone-control capabilities, and a sensors designed to highlight muzzle flashes on the battlefield below. The Army has also experimentally deployed Apaches on U.S. Navy ships and had them practice anti-ship missions, and even tested a laser-armed Apache.

Early in the morning of January 17, 1991, eight sleek helicopters bristling with missiles swooped low over the sands of the An Nafud desert in as they soared towards the border separating Saudi Arabia from Iraq.

Skydio X10 autonomous drones deliver the best sensors for a drone this small, piloted by the most advanced AI in the sky.

Helsinki’s Callboats pioneers autonomous water taxis, aiming to cut costs, improve island access, and reduce captain shortages.

Autonomous electric water transport could be the answer to improving accessibility, achieving carbon neutrality, and addressing a shortage of skippers in the Helsinki archipelago. However, current legislation is a barrier to the operation of remotely controlled boats, according to a Helsinki Times.

Over the years, Forum Virium Helsinki, the innovation agency of the City of Helsinki, has accelerated various business ideas through its rapid innovation experiments. Successful innovations in smart mobility include autonomous transportation solutions like robot buses, drones delivering first aid supplies, and sweeping robot machines.

A private Chinese company, Thrust-to-Weight Ratio Engine, was able to test a rotary detonation engine on a drone. This is the first such test. Previously, only bench tests were conducted.

Here’s What We Know.

The rotary detonation engine will open the way to the development of hypersonic transport systems, including aircraft and missiles. Another feature of the propulsion system is reduced fuel consumption.

Continue reading “China tested the first ever drone equipped with a rotary detonation engine — the propulsion system will open the way to the creation of hypersonic aircraft and missiles” »

Scientists at the University of Washington have developed flying robots that change shape in mid-air, all without batteries, as originally published in the research journal Science Robotics. These miniature Transformers snap into a folded position during flight to stabilize descent. They weigh just 400 milligrams and feature an on-board battery-free actuator complete with a solar power-harvesting circuit.

Here’s how they work. These robots actually mimic the flight of different leaf types in mid-air once they’re dropped from a drone at an approximate height of 130 feet. The origami-inspired design allows them to transform quickly from an unfolded to a folded state, a process that takes just 25 milliseconds. This transformation allows for different descent trajectories, with the unfolded position floating around on the breeze and the folded one falling more directly. Small robots are nothing new, but this is the first solar-powered microflier that allows for control over the descent, thanks to an onboard pressure sensor to estimate altitude, an onboard timer and a simple Bluetooth receiver.

Even with all the technological advancements in recent years, autonomous systems have never been able to keep up with top-level human racing drone pilots. However, it looks like that gap has been closed with Swift – an autonomous system developed by the University of Zurich’s Robotics and Perception Group.

Previous research projects have come close, but they relied on optical motion capture settings in a tightly controlled environment. In contrast, Swift is completely independent of remote inputs and utilizes only an onboard computer, IMU, and camera for real-time for navigation and control. It does however require a pretrained machine learning model for the specific track, which maps the drone’s estimated position/velocity/orientation directly to control inputs. The details of how the system works is well explained in the video after the break.

The paper linked above contains a few more interesting details. Swift was able to win 60% of the time, and it’s lap times were significantly more consistent than those of the human pilots. While human pilots were often faster on certain sections of the course, Swift was faster overall. It picked more efficient trajectories over multiple gates, where the human pilots seemed to plan one gate in advance at most. On the other hand human pilots could recover quickly from a minor crash, where Swift did not include crash recovery.