Add BrightSurf on Google Email

Six-legged robot learns to walk from a stick insect

Researchers trained AI on stick insect walking cycle to find optimal walking strategy, resulting in a six-legged robot that can navigate treacherous terrain and adapt to missing limbs. The approach allows for cheaper and faster robot production, enabling potential disaster response applications.

SourceTohoku University·JournalBioinspiration & Biomimetics·DateAug 27, 2026

Robotic hip exoskeleton shows promise for helping stroke patients regain their stride

A portable robotic device has been developed to improve walking function in stroke survivors by altering gait asymmetry. The study, published in IEEE Transactions on Neural Systems and Rehabilitation Engineering, reveals that the exoskeleton can effectively train individuals to modify their walking asymmetry.

SourceUniversity of Massachusetts Amherst·JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering·TypeExperimental study·DateMar 4, 2024

Can we fight back against Parkinson’s disease? These research volunteers hope so

Researchers at Boston University's Center for Neurorehabilitation have made two important advances that may help people with Parkinson's disease walk more smoothly. Wearable soft robotic apparel and a music-based technology were tested in studies, showing promising results in increasing walking duration and distance.

SourceBoston University·JournalNature Medicine·TypeRandomized controlled/clinical trial·DateJan 5, 2024

A single parameter to describe animal locomotion

Researchers develop a phase shift parameter to describe animal locomotion, combining forces of inertia, gravity, elasticity and viscosity into one dimensionless number. This new parameter predicts muscle activation patterns in a wide range of animals during locomotion.

SourcePNAS Nexus·JournalPNAS Nexus·DateOct 10, 2023

Insect cyborgs: towards precision movement

Researchers at Tohoku University have developed a model predicting torque generated from electrical stimulation in stick insect leg muscles, allowing for precise control of insect movement. The study's findings have the potential to refine motor control of tuned biohybrid robots and enable adaptable devices with various applications.

SourceTohoku University·JournaleLife·DateOct 4, 2023

Instant evolution: AI designs new robot from scratch in seconds

A team of researchers at Northwestern University developed an AI capable of intelligently designing robots from scratch, compressing evolution into lightning speed. The AI designed a successfully walking robot in mere seconds, with a novel structure and three legs, fins along its back, and a flat face.

SourceNorthwestern University·JournalProceedings of the National Academy of Sciences·TypeExperimental study·DateOct 3, 2023

Advanced universal control system may revolutionize lower limb exoskeleton control and optimize user experience

Researchers developed a new method for controlling lower limb exoskeletons using deep reinforcement learning, enabling more robust and natural walking control. The system has the potential to benefit users with spinal cord injuries, multiple sclerosis, stroke, and other neurological conditions.

SourceKessler Foundation·JournalJournal of NeuroEngineering and Rehabilitation·TypeComputational simulation/modeling·DateJun 15, 2023

Robot centipedes go for a walk

Researchers from Osaka University developed a biomimetic robot that uses dynamic instability to navigate uneven terrain. The robot can switch between straight and curved walking motions, making it suitable for search and rescue operations or planetary exploration.

SourceOsaka University·JournalSoft Robotics·TypeExperimental study·DateMay 29, 2023

Scurrying centipedes inspire many-legged robots that can traverse difficult landscapes

Researchers developed a new theory of multilegged locomotion, creating robotic models that can move across uneven surfaces without sensors. The robot's leg redundancy enables it to transport itself and loads on challenging terrain, making it suitable for applications like agriculture, space exploration, and search and rescue.

SourceGeorgia Institute of Technology·JournalScience·TypeExperimental study·DateMay 4, 2023

RaiBo - a versatile robo-dog runs through the sandy beach at 3 meters/sec

Researchers at KAIST developed a quadrupedal robot control technology that enables robots to walk robustly on deformable terrain like sandy beaches. The technology uses artificial neural networks to simulate ground characteristics and adapt to changing environments, allowing the robot to maintain balance and perform high-speed walking.

Engineered by KAIST mechanics - a quick but clingy creepy-crawler that will MARVEL you

M.A.R.V.E.L.'s magnetic soles made of Electro-Permanent Magnet (EPM) and Magneto-Rheological Elastomer (MRE) enable fast movement on uneven surfaces. The robot can climb at speeds of up to 70 cm/s on walls and 50 cm/s on ceilings, making it the world's fastest walking climbing robot.

SourceThe Korea Advanced Institute of Science and Technology (KAIST)·JournalScience Robotics·TypeMeta-analysis·DateDec 31, 2022

Hey robot, shimmy like a centipede

The study reveals that taming instability is a key factor in the centipede's success, allowing it to move quickly and over obstacles with ease. By harnessing instability, the creature produces an undulating movement that enhances its locomotion maneuverability.

SourceKyoto University·JournalScientific Reports·DateJul 22, 2016

Tinkertoy Robot Shows How Humans Walk

A Cornell University robot made from plastic Tinkertoy parts has been shown to perform repeatable, chattering, human-like stable steps without falling over on a gentle slope. The robot's design provides new insights into the mechanics of walking and may have implications for designing better powered and controlled biped robots.

SourceCornell University·JournalPhysical Review Letters·DateApr 7, 1998