Robot Grasping in a Heavily Cluttered Environment

Robot Grasping in a Heavily Cluttered Environment

Korea Advanced Institute of Science and Technology (KAIST) student Dongwon Son has recently published interesting research about reactive grasping in a heavily cluttered environment in IEEE Robotics and Automation Letters. Reactive robot grasping in a Heavily cluttered environment. Courtesy of Samsung Research and Dongwon Son. This study proposed a closed-loop framework for predicting the six-degree-of-freedom (dof) grasp in a heavily cluttered environment using vision observations. prediction results in robot grasping. Courtesy of Samsung Research and Dongwon Son. Experimental results on a robot in an environment with a lot of clutter showed that the grasping success rate had improved quantitatively compared…
Read More
Controlling a Robotic Arm with Brain

Controlling a Robotic Arm with Brain

Two research groups at EPFL (École polytechnique fédérale de Lausanne) supervised by Prof. Aude G. Billard, and Prof. José del R. Millán developed a machine learning (ML) algorithm that can learn from the patient's thoughts and enables to control a robot's movements based on electrical signals from the brain. Image credit: EPFL (École polytechnique fédérale de Lausanne) This research has potential applications to help tetraplegic patients who are unable to speak or perform any movement to independently perform activities of daily living (ADL). Key points: Patients move the robot with their thoughts, and no auditory or tactile feedback is needed.The…
Read More
a Bioinspired Advanced Neural Control for Autonomous Walking Robots

a Bioinspired Advanced Neural Control for Autonomous Walking Robots

Researchers from BRAIN-lab at VISTEC in Thailand developed a bioinspired advanced neural control with proactive behavior learning and short-term memory for autonomous walking robots that enables them to traverse complex terrain. Image credit: BRAIN-lab at VISTEC The proposed control consists of three main modular neural mechanisms to create insect-like gaits, adapt robot joint movement individually with respect to the terrain during the stance phase using only the torque feedback, and generate a short-term memory for proactive obstacle avoidance during the swing phase. Their proposed control: does not require robot and environmental models, exteroceptive feedback, or multiple learning trialsdepends only on…
Read More
John Deere’s Fully Autonomous Tractor for Large-scale Production

John Deere’s Fully Autonomous Tractor for Large-scale Production

John Deere's new autonomous tractor is all the fast-growing population needs for large-scale production. The tractor can do the job autonomously while the farmer is doing other tasks, and they can monitor its status through an app on their mobile phone. Image credit: John Deere Key features: GPS guidance systemsix pairs of stereo cameras for 360-deg visual perceptionimages are processed through a deep neural network for obstacle detection This tractor will be available to all farmers in late 2022! Watch a short video of this below: More information: https://ces2022.deere.com/https://www.linkedin.com/company/john-deere/ If you enjoyed this post, please consider contributing to help us…
Read More