It is my pleasure to welcome you to 2023. I hope it will be calm and full of interesting development in robotics. As for the newsletter, I’m excited to report we hit 21.37% growth in e-mail subscriptions this year. As usual, the publication of the week section is manned by Rodrigo. Last week’s most clicked link was the Mini Cheetah clone teardown, with 16.0% opens.
Weekly Robotics is being developed thanks to the Patreon supporters and the following business sponsors:
Introduction to Robotics
Anirudha Majumdar teaches this course at Princeton University. The course covers feedback control, motion planning, state estimation, and computer vision and uses a Crazyflie quadrotor throughout the course.
3D-Printed Self-Balancing Robot Brings Control Theory To Life
This two-wheel balancing robot by Limenitis Reducta is driven by stepper motors, an MPU-9250 IMU, and is controlled by a Raspberry Pi Pico. You can find more info about this project from the project repository.
Predictions Scorecard, 2023 January 01
Every year, Rodney Brooks revises his predictions from 2018 about self-driving cars, robotics, AI, and Space. I liked this one: “No car company is going to produce a humanoid robot that will change manufacturing at all. Dexterity is a long way off, and innovations in manufacturing will take very different functional and process forms, perhaps hardly seeming at all like a robot from popular imagination”.
Merry Christmas from Czech Technical University - robot light show [bag included]
Roboticists from CTU were kind enough to share bagfiles of their event, where they simultaneously ran multiple robots with their DARPA SubT challenge payloads and some extra lights. Cool stuff!
10 Crazy Rejected BattleBots Designs
In this video, we can learn about some exciting designs that didn’t make it to the BattleBots. I love how creative some of these designs are!
Swiss Drone-Busting Eagle Squadron Permanently Grounded
I’m not surprised by this decision at all. After all, to outrun a bird with a drone, it’s enough you fly up.
Publication of the Week - Circular Accessible Depth: A Robust Traversability Representation for UGV Navigation (2022)
Some autonomous vehicles make use of a bird’s-eye view (BEV) to identify vehicles, pedestrians, and obstacles. This paper presents the Circular Accessible Depth (CAD) method based on BEV for a more robust traversability representation using LiDAR point clouds. CAD predicts the location of the objects rather than their shape, and due to its polar coordinate systems, it is also easier to identify thin objects as they come closer to the robot. The authors also created CADnet, which extracts spatial features from the point clouds. The results from the simulation and real-world tests validated the robustness and precision of the method. You can check the video here](https://youtu.be/pHm4dq6Neyw) of the system running on a robot.