EP.1 ROBOT AS A STEERING WHEEL
Tom & Jerry as robots. Gripper like octopus' tentacles and more...
This drone flies so smoothly… through walls 🛸
A tiny drone made by the National Robotics Engineering Center is seen flying quickly in a video, traveling at 3 m/s while avoiding moving obstacles. Neither visual fiducials nor environmental knowledge is used beforehand. The aerial system uses range data from a front-facing depth camera to determine open space and then uses collision avoidance technologies to steer the drone through it. A tracking camera that faces the back provides a state estimate. All bespoke software is executed on a Raspberry PI 4 computer with a 1.8GHz ARM CPU. The combined CPU use of the path following and collision avoidance modules is just 20%, and the planning time is less than 0.1 milliseconds.
A gripper shaped like the tentacles of an octopus!? 🐙
Researchers at Harvard John A. Paulson School of Engineering and Applied Sciences developed a new kind of soft, robotic gripper. It mimics the way jellyfish capture stunned prey by entangling and ensnaring items with a network of tiny tentacles.
Individual filaments, or tentacles, are not very strong on their own. However, when used as a group, the filaments can firmly grip and hold things of all shapes and sizes. The gripper doesn't need sensing, planning, or feedback control. It only uses straightforward inflation to wrap around items. The robotic arm from Universal Robots was used for that purpose.
Tom & Jerry as robots? 🐈🐁
No, it's not them. It's a mini quadruped robot project based on Arduino and the ROS system. With the project, you can learn how to calculate the robot's kinematics, which enables its movements. Using the sensors and microprocessor chips there, you can make the robot move autonomously. The Mini Pupper uses LIDAR and OpenCV 3D camera modules to perform self-driving functions like SLAM (Simultaneous Localization and Mapping), navigation, and object tracking. There are endless possibilities. With GRF (ground reaction force) feedback, you can explore closed-loop control similar to Boston Dynamics Spot and the Mini Cheetah robot dog.
It looks really interesting - especially for robotics enthusiasts and students who can ignite the spark of their passion! A good and valuable platform that introduces the world of robotics.
If you want to try it, you can buy that tiny robot called Mini Pupper 2 here 👇🏼:
Robot as a steering wheel? 🚘
Collaborative robot from KUKA as the steering wheel?
It's a very old concept from 2015 presented by HARMAN based on the electrically-driven BMW i3, back then expected to be the next generation of autonomous urban driving. Economically absurdly unreasonable, yet satisfying to watch! 🦾
Imagine the 'let me drive!' arguments...
Drone or robot? Aerial manipulation.
This drone can manipulate objects while in the air. I will try to describe what the approach and methodology are for this robotic drone called DRAGON.
The main objective is to control the flight of a drone that can change shape using a special type of thrust force that can be adjusted.
It allows integration with external and internal objects manipulation and grasping.
Next, a way to plan the motion of an object being manipulated by a robot arm was developed. The robot arm uses feedback from the object's position to control the force it applies. This allows the robot arm to manipulate the object more effectively.
The unique point of the proposed grasping style is the vectorizable thrust force is used as the internal wrench instead of the joint torque.
Just imagine that: 'hey Dragon, gimme the remote, please!" 📺
ChatGPT is ready to become a lawyer 👔
We know that ChatGPT can write poems, refactor, write completely new code, and answer very hard questions. ChatGPT is a type of natural language processing (NLP) model that is trained to generate human-like responses to text input. It is based on the GPT-3 (Generative Pretrained Transformer-3) model, which uses machine learning algorithms to generate text that is similar to human writing. ChatGPT is specifically designed to be used in chat applications, such as online customer service platforms, to provide quick and accurate responses to user inquiries.
It can be used by businesses to improve customer experience and reduce the need for human customer service representatives. Some internet users decided to check whether ChatGPT could become a lawyer and actually pass the law test. It turned out that Chat passed the test by 70% scoring 35 out of 50. There is a 0.00000001% chance of guessing randomly. WOW. The potential here is unlimited!
[MORE HERE 👉🏼: Will ChatGPT make lawyers obsolete?]
Robotics term of the week
Denavit-Hartenberg Equation
The D-H equations are a method for describing the kinematics of a robot manipulator. They provide a way to define the position and orientation of each link (joint) in a robot in relation to its neighboring links (joints). This information is used to analyze and control the motion of the robot. The D-H equations are widely used in robotics research and engineering.
To effectively present the issue of D-H notation will be very difficult to do it with a few sentences. Therefore, for those who are inquisitive, I leave a video, which brilliantly details the discussed issues of Denavit-Hartenberg notation.
Feel free to comment, ask, question everything you see here!