EP.6 THE MOST ADVANCED HUMANOID ROBOT MOVES LIKE A HUMAN
Gecko-like inspection robot, the story of handwriting recognition, a famous robot gets a grip and much more.
The power of convolutional networks: The story of LeNet 1 and its impact on AI 💻
In 1989, Yann LeCun revolutionized the field of AI by demoing breakthrough research in handwriting recognition. It was almost 35 years ago!
In the early days of artificial intelligence, researchers at Bell Labs set out to create a program that could recognize handwritten digits with speed and accuracy. They developed LeNet 1, the first convolutional network, which was able to achieve this feat. The team trained the network using an early neural net simulator and was able to demonstrate it in a real-time demo running on a PC with a video camera and specialized hardware.
The success of LeNet 1 caught the attention of a subsidiary of AT&T which saw the potential for the technology in their ATMs. They partnered with the team at Bell Labs to deploy the convolutional network in ATMs to help read the numerical amounts on checks. The technology proved to be highly effective, and at its peak, these machines were processing 10 to 20% of all checks in the US.
Climbing to the top: The future of infrastructure inspections 🦎
One innovative solution that has emerged in recent years is the use of climbing robots for ultrasonic inspections. Gecko Robotics, Inc. has developed a robot that can climb structures and provide ultrasonic inspections to understand the current condition of critical infrastructure. This technology allows for more efficient and accurate inspections, helping to identify potential issues before they become major b.
Assets, equipment, and infrastructure are crucial components of any industry and play a vital role in ensuring smooth operations. Regular inspection and maintenance are key to ensuring the longevity and reliability of these assets. As technology continues to advance, solutions like these climbing robots will become increasingly common and will play a crucial role in maintaining the infrastructure.
Ottonomy delivery robot hits the streets 📦
Ottonomy has launched the Ottobot Yeti, an autonomous delivery robot that aims to revolutionize the way goods are delivered. The robot is equipped with advanced navigation and perception technologies, allowing it to navigate through complex environments and perform autonomous deliveries. It also has a robust payload capacity and is perfect for use in crowded urban areas.
The Ottobot Yeti also has safety features such as obstacle detection, as well as cameras and sensors to navigate in dark or low-light environments. This new technology is expected to improve efficiency and reduce costs for delivery companies, while also being environmentally friendly.
Source: https://www.therobotreport.com/ottonomy-launches-new-ottobot-yeti-autonomous-delivery-robot/
A buzzworthy humanoid robot gets a grip 🦾
Atlas, a humanoid robot developed by Boston Dynamics, is capable of displaying a level of dexterity and athleticism never before seen in a robot. Its advanced sensors allow it to navigate and interact with its environment with ease, and its state-of-the-art locomotion system allows for smooth and agile movements. Atlas is also equipped with a range of sensors, including stereo cameras, LiDAR, and force-sensitive skin, which enable it to perceive and understand its environment in a similar way to humans. This allows Atlas to interact with objects in a natural and intuitive way, and to accomplish tasks that were previously thought impossible for robots.
Boston Dynamics has recently announced a breakthrough in its development with the new control algorithm called Picking Momentum, which enables Atlas to pick up and move objects with greater ease and speed. This is an exciting time in the robotics field as advancements in technology, such as Picking Momentum, push the boundaries of what's possible and bring us closer to a future where robots can work seamlessly alongside humans.
Robotics term of the week
End-effector 🕹️
An end-effector is a device that is mounted on the end of a robot's arm or other mechanical appendage and it is used to interact with the environment. This device can take many forms, depending on the task that the robot is designed to perform. The end-effector is a crucial part of a robot as it allows the robot to perform its intended task. Some examples of end-effectors are:
Gripper: A device used to grasp and hold objects, often used in assembly and packaging tasks. Grippers can vary in complexity, from simple jaws to multi-fingered hands.
Tool: A specialized device used for a specific task, such as welding, painting, or drilling.
Sensor: A device that can detect the environment, such as cameras, force sensors, or touch sensors. These sensors can be mounted on the end-effector or on other parts of the robot to gather information about the environment.
Manipulator: A device that can move objects, such as a suction cup or a magnet.
Combination: A device that can perform multiple tasks, such as a gripper with integrated sensors or a tool with integrated force sensing.