Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 2,129

SQuad: A miniature robot that can walk and climb obstacles

Researchers at Bilkent University in Turkey have recently created a small quadruped robot called SQuad, which is made of soft structural materials. This unique robot, presented in a paper published in IEEE Robotics and Automation Letters, is more flexible than existing miniature robots and is thus better at climbing or circumventing obstacles in its surroundings.

“We have been working on for almost a decade now,” Onur Ozcan, one of the researchers who carried out the study, told TechXplore. “Even though miniature robots have many advantages, such as being cheap, as they require fewer materials, and the ability to access confined spaces, one of their major drawbacks is their lack of locomotion capabilities, especially on uneven terrain.”

Tiny robots tend to get stuck easily while moving in the surrounding environment, as their height does not allow them to climb or avoid obstacles. Ozcan and his colleagues tried to overcome this limitation by implementing a principle known as ‘body compliance.”

Differential Equations as a Neural Network Layers

The main idea of artificial neural networks (ANN) is to build up representations for complicated functions using compositions of relatively simple functions called layers.

A deep neural network is one that has many layers, or many functions composed together.

Although layers are typically simple functions(e.g. relu(Wx + b)) in general they could be any differentiable functions.

KIA Teases 800 Volt 300 Mile EV With 25 Minute Recharge Time

KIA and corporate cousin Hyundai build some efficient EVs that challenge industry leaders like Tesla. Yes, Elon an his minions are miles ahead in self-driving tech, but the Hyundai Kona EV and KIA Niro EV are world class cars that come close to meeting Elon’s plea to other manufacturers to build compelling electric cars.

The problem is, KIA and Hyundai don’t have a dedicated battery electric platform. Both the Kona and Niro share their underpinnings with hybrid and plug-in hybrid models. A pure battery electric car may be coming soon from KIA, however. Recently, Hyundai said it is planning to bring two new all electric models — the 45 Concept and the Prophesy Concept — to market this year and next. Both will be built on the company’s new Electric Global Modular Platform known internally as E-GMP.

Tesla Achieved The Accuracy Of Lidar With Its Advanced Computer Vision Tech

Tesla’s progress with artificial intelligence and neural nets has propelled its Autopilot and Full Self Driving solutions to the front of the pack. This is the result of the brilliant work of a large team of Autopilot directors and staff, including Tesla’s Senior Director of AI, Andrej Karpathy. Karpathy presented Tesla’s methods for training its AI at the Scaled ML Conference in February. Along the way, he shared specific insights into Tesla’s methods for achieving the accuracy of traditional laser-based lidar with just a handful of cameras.

The secret sauce in Tesla’s ever-evolving solution is not the cameras themselves, but rather the advanced processing and neural nets they have built to make sense of the wide range and quality of inputs. One new technique Tesla’s AI team has built is called pseudo-lidar. It blends the lines between traditional computer vision and the powerful point map world of lidar.

Traditional lidar-based systems rely on an array of lidar hardware to provide an unparalleled view of the world around the vehicle. These systems leverage invisible lasers or similar tech to send a massive number of pings out into the world to detect surrounding objects.

An algorithm to enhance the robotic assembly of customized products

Robots could soon assist humans in a variety of fields, including in manufacturing and industrial settings. A robotic system that can automatically assemble customized products may be particularly desirable for manufacturers, as it could significantly decrease the time and effort necessary to produce a variety of products.

To work most effectively, such a robot should integrate an assembly planner, a component that plans the sequence of movements and actions that a robot should perform to manufacture a specific product. Developing an assembly planner that can rapidly plan the sequences of movements necessary to produce different customized products, however, has so far proved to be highly challenging.

Researchers at the German Aerospace Center (DLR) have recently developed an algorithm that can transfer knowledge acquired by a robot while assembling products in the past to the assembly of new items. This algorithm, presented in a paper published in IEEE Robotics and Automation Letters, can ultimately reduce the amount of time required by an assembly planner to come up with action sequences for the manufacturing of new customized products.

Lockheed Martin wins DARPA contract to integrate Blackjack satellites

WASHINGTON — The Defense Advanced Research Projects Agency awarded Lockheed Martin a $5.8 million contract for satellite integration work for the Blackjack program, the company announced April 24.

Blackjack is a project to deploy a constellation of 20 satellites in low Earth orbit by 2022 and demonstrate that a LEO system can provide global high-speed communications.

Lockheed Martin will define and manage interfaces between Blackjack’s satellite buses, payloads and the so-called Pit Boss autonomous data processor. The work will be performed at the company’s satellite manufacturing plant in Sunnyvale, California.

/* */