Image Credit: Hyundai
Weekly Robotics community meeting is ON this week! Scroll down to the announcement section for more details and talk to you on Thursday! The most clicked link last week was The Black Magic of Disappearing Actuator with 12.9% opens. As usual in the past couple of weeks, the publication of the week section is manned by Rodrigo.
Hyundai Motor Group Introduces Two New Robots
Hyundai had announced two new robots: the first one is an 80kg humanoid-ish customer service robot called DAL-e. The second robot is called TIGER, a mobility platform (or Ultimate Mobility Vehicle, UMV as Hyundai calls it) is a wheeled-legged robot with a good potential to traverse obstacles yielding a solid delivery platform. Hyundai plans to commercialize this platform in the next five years.
NanoSaur Mobile Robot
NanoSaur is an open-source tracked mobile robot by Raffaello Bonghi. The brains of the robot is an NVIDIA Jetson Nano running ROS2. Parts of the project page are still under construction but the build seems very solid.
A Versatile Inverse Kinematics Formulation for Retargeting Motions onto Robots with Kinematic Loops
Via video description: Robots with kinematic loops are known to have superior mechanical performance. However, due to these loops, their modeling and control is challenging, and prevents a more widespread use. In this paper, we describe a versatile Inverse Kinematics (IK) formulation for the retargeting of expressive motions onto mechanical systems with loops. We support the precise control of the position and orientation of several end-effectors, and the Center of Mass (CoM) of slowly walking robots. Our formulation safeguards against a disassembly when IK targets are moved outside the workspace of the robot, and we introduce a regularizer that smoothly circumvents kinematic singularities where velocities go to infinity. With several validation examples and three physical robots, we demonstrate the versatility and efficacy of our IK on overactuated systems with loops, and for the retargeting of an expressive motion onto a bipedal robot.
Fabricating Fully Functional Drones
A group from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) recently developed a new system to print functional, custom-made devices and robots, without human intervention. Their single system uses a three-ingredient recipe that lets users create structural geometry, print traces, and assemble electronic components like sensors and actuators.
Mesmer Demo Jan 2021
Perseverance Rover Landing
Perseverance will land on Mars on 18th of February at around 12:55 PST (21:55 CET). You can see the stream of the landing on YouTube. We will see how the WR community meeting goes, maybe we will even make it to touchdown time and watch it together!
Publication of the Week - Development of a Robotic System for Automated Decaking of 3D-Printed Parts (2020)
One of the boring tasks of 3D printing is to remove the excess filament or powder used to support the object during the printing phase. This article proposes a solution using Deep Learning with robotics arms to remove the excess material. Although the method is limited to certain shapes and sizes, with the robotic arm there is enough freedom to work with complex geometries. I hope that soon we have robotics arms printing, “decaking”, drilling and doing many other tasks as if it was an all-in-one solution adding more value for the printed part.
Weekly Robotics Community Meeting #1
On Thursday, 18th of February at 7PM CET, we will hold the first WR community meeting that will be open to the public! We will kick-off the meeting with a short sneak peek of an iPhone app by Kenneth Blomqvist has been working on that you can use to collect RGB + depth datasets using LiDAR. After the presentation, you will have a chance to have a chat with fellow roboticists. We are going to use this wonder.me room for the meeting, to join us just visit the room at 7PM CET on 18th Feb.
Rydesafely (Toronto, Canada / Remote) - Various Positions
Rydesafely is in a pursuit to solve the grand problem of infeasible validation of ML based automotive software. Solving this problem will help automotive companies deploy and scale smart driving solutions across geographies in a cost-effective way while adhering to all the safety requirements and regulations. This process otherwise is tedious and expensive to an extent that has put a question mark on the feasibility of autonomous driving.
Kopernikus Automotive (Leipzig or Berlin, Germany / Remote) - Software Engineer - Vehicle and Infrastructure
A position is available at a dynamic and multi-cultural startup working on autonomous valet parking. We are looking for a passionate developer to contribute to our infrastructure systems, tools and facilitate collaboration with our computer vision team. If you’ve always wanted to move big machines with small computers using Rust, then this is an excellent opportunity!