Logo

SemiVoice

Recent #robots news in the semiconductor industry

electronicsforu
2 months ago

3D-Printed Robots That Walk Without Electronics

➀ Researchers at UC San Diego's Bioinspired Robotics Lab have developed 3D-printed robots capable of walking without electronics, powered by compressed gas.

➁ These robots are designed to operate in extreme environments like high radiation zones, disaster areas, and space missions, showcasing continuous operation for three days when connected to a gas supply.

➂ The robots feature a monolithic design printed in one piece using flexible materials, with future plans to integrate gas storage and biodegradable components for enhanced functionality.

AIrobots
electronicsforu
4 months ago

Training Robots For Athletic Movements

➀ Researchers from Carnegie Mellon University and NVIDIA have developed a new model to train robots to move like human athletes.

➁ The model, called ASAP, involves a two-stage training framework that improves the adaptability and fluidity of robot movements.

➂ While the robot successfully replicated several iconic sports moves, more work is needed to make robots as athletic as professional athletes.

AISimulationrobots
electronicsforu
5 months ago

Robots Get Moose-Inspired Feet

➀ Researchers at Tallinn University of Technology (TalTech) have developed bio-inspired robot feet to enhance mobility on challenging terrains like mud and wet snow; ➁ The design is inspired by the moose's hooves, which break suction force when stepping out of mud; ➂ The robot's sinkage and suction force are reduced by half, and energy consumption is lowered by up to 70%.
robots
electronicsforu
7 months ago

Robots Learning To Sense Like Humans

➀ Researchers from Duke University have developed a system called SonicSense, which allows robots to interact with their environment through a robotic hand with microphones on its fingertips. The system captures vibrations and analyzes them to determine the material and shape of objects. ➁ SonicSense uses AI to identify objects with complex shapes and multiple materials, and it can learn from interactions to improve its recognition capabilities. ➂ The system is designed to be affordable and easy to integrate into robots, potentially enhancing their ability to navigate unpredictable environments.
AIrobots
electronicsweekly
7 months ago

Septentrio and GNSS Store hook up

➀ Septentrio, a GNSS positioning specialist, has partnered with GNSS OEM Store to offer centimetre-level GNSS modules, antennas, and development kits. ➁ GNSS Store has developed various evaluation boards, dongles, compact smart antennas, and plug-and-play systems based on the mosaic GNSS module. ➂ These products provide sub-centimetre level location accuracy with multi-band, multi-constellation, and high-precision RTK capabilities, suitable for high-precision navigation and positioning applications like precision agriculture, UAVs, and robots.
GNSSrobots
electronicsforu
9 months ago

New Woven Tech For Robots And Wearables

➀ Researchers from Jiangnan University have developed a scalable and customizable method for creating textile actuators for healthcare and robotics. ➁ The method involves precise weaving of warp and weft yarns to create actuators that can detect strain and maintain flexibility. ➂ This technique allows for the production of multi-morphing soft actuators capable of bilateral bending, twisting, and spiraling.
Textile Engineeringrobotswearables
electronicsforu
12 months ago

Can Large Language Models Help Robots To Navigate?

1. Researchers from MIT and MIT-IBM Watson AI Lab have developed a new navigation method for robots that translates visual inputs into text descriptions. 2. This method uses a large language model to process these descriptions and guide the robot through multistep tasks. 3. The language-based approach offers advantages such as efficient synthetic data generation and versatility across different tasks, though it does not outperform vision-based methods.
Large Language Modelsnavigationrobots